Patent application number | Description | Published |
20100114617 | DETECTING POTENTIALLY FRAUDULENT TRANSACTIONS - An approach that detects potentially fraudulent transactions is provided. In one embodiment, there is a fraud detection tool including, an identification component configured to identify a first person present within a zone of interest at a point of sale (POS) device using a set of sensor devices; a transaction component configured to determine whether the POS device has performed a first transaction and a second transaction while the first person is present within the zone of interest at the POS device; an analysis component configured to: analyze a transaction type of the first transaction and the second transaction; and detect whether the second transaction is potentially fraudulent based on a determination of whether the POS device has performed a first transaction and a second transaction while the first person is within the zone of interest at the POS device, and an analysis of the transaction type of the second transaction. | 05-06-2010 |
20100114802 | SYSTEM AND METHOD FOR AUTOMATICALLY DISTINGUISHING BETWEEN CUSTOMERS AND IN-STORE EMPLOYEES - An approach that automatically distinguishes between in-store customers and in-store employees is provided. In one embodiment, there is a learning tool configured to construct a model for an in-store employee; and a classifying tool, further comprising matching tool configured to: match attributes between a particular person and the constructed models for an in-store employee, the classifying tool configured to: classify persons into categories of employees and customers based on amount of matching attributes between a particular person and the model for an in-store employee. | 05-06-2010 |
20100157051 | SYSTEM AND METHOD FOR DETECTING AND DETERRING RFID TAG RELATED FRAUD - An approach that allows for detecting and deterring RFID tag related fraud is provided. In one embodiment, there is a generating tool configured to generate a set of tag-item models based on results of a cumulative training process; detecting tool configured to detect discrepancy between an expected appearance of the item as determined from analyzing corresponding tag-item model and an actual appearance of the item as captured by color camera, and an acknowledging tool configured to acknowledge said detected discrepancy. | 06-24-2010 |
20100169169 | SYSTEM AND METHOD FOR USING TRANSACTION STATISTICS TO FACILITATE CHECKOUT VARIANCE INVESTIGATION - An approach that allows for facilitating checkout related fraud investigation is presented. In one embodiment, there is described a generating tool configured to generate a set of benchmark parameters based on results of a cumulative learning process; a normalizing tool configured to normalize said set of benchmark parameters; an establishing tool configured to establish a confidence time interval required for identifying normal variations; a recording tool configured to record a particular checker's transactions during said confidence time interval, and an identifying tool configured to identify transactions, recorded during said confidence time interval, that fail meeting said set of benchmark parameters. | 07-01-2010 |
20100282841 | VISUAL SECURITY FOR POINT OF SALE TERMINALS - Under the present invention, item verification is automated and expedited. Specifically, items to be purchased can be scanned by the shopper using a barcode reader (e.g., a scanner), attached to or positioned near the checkout station. As items are scanned, they are identified based on their barcode, and added to an item list. Item verification can then be performed at checkout using imaging technology. Specifically, as items are scanned, an item verification unit will capture an appearance thereof (via a camera). Item verification software within the item verification unit will access a database that associates items with their images/appearances. The appearance will be compared for consistency to the identity as determined based on the scan. In general, the item verification unit is a separate unit from the cash register, but adapted to work in conjunction therewith (e.g., as a pluggable system, via wireless communication, etc.). | 11-11-2010 |
20110280547 | AUDITING VIDEO ANALYTICS THROUGH ESSENCE GENERATION - Video analytics data is audited through review of selective visual essence subsets of visual images from a visual image stream as a function of a temporal relationship of the essence subset images to a triggering alert event. The visual essence subset comprehends an image contemporaneous with the triggering alert event and one or more other images occurring before or after the contemporaneous image. The generated visual essence is presented for review to determine whether the triggering alert event is a true or false alert, or whether additional data from the visual image stream is required to make such a determination. If determined from the presented visual essence that the additional data is required make the true or false determination, then additional data is presented from the visual image stream for review. | 11-17-2011 |
20120093370 | EVENT DETERMINATION BY ALIGNMENT OF VISUAL AND TRANSACTION DATA - Determination of human behavior from an alignment of data streams includes acquiring visual image primitives from a video input comprising visual information relevant to a human activity. The primitives are temporally aligned to an optimally hypothesized sequence of primitives transformed from a sequence of transactions as a function of a distance metric between the observed primitive sequence and the transformed primitive sequence. More particularly, transforming includes comparing the distance metric costs and choosing and performing the lowest cost of temporally matching the observed primitives to one or more transactions, deleting a primitive, or associating a primitive with a pseudo transaction marker. Accordingly, alerts are issued based on analysis of the transformation of primitives. | 04-19-2012 |
20120134527 | HAZARD DETECTION FOR ASSET MANAGEMENT - An approach that detects locations of hazardous conditions within an infrastructure is provided. This approach uses satellite imagery, GIS data, automatic image processing, and predictive modeling to determine the location of the hazards automatically, thus optimizing infrastructure management. Specifically, a hazard detection tool provides this capability. The hazard detection tool comprises a detection component configured to: receive visual media containing asset location data about a set of physical assets, and hazard location data about potential hazards within a vicinity of each of the set of physical assets. The detection component further receives graphical information system (GIS) data containing asset location data about each of the set of physical assets. The hazard detection tool further comprises an analysis component configured to: analyze the visual media to determine if a hazardous condition exists for each of the set of physical assets; and apply the GIS data to the visual media to determine a location of hazardous conditions within the infrastructure. | 05-31-2012 |
20120170805 | OBJECT DETECTION IN CROWDED SCENES - Methods and systems are provided for object detection. A method includes automatically collecting a set of training data images from a plurality of images. The method further includes generating occluded images. The method also includes storing in a memory the generated occluded images as part of the set of training data images, and training an object detector using the set of training data images stored in the memory. The method additionally includes detecting an object using the object detector, the object detector detecting the object based on the set of training data images stored in the memory. | 07-05-2012 |
20120233159 | HIERARCHICAL RANKING OF FACIAL ATTRIBUTES - In response to a query of discernible facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings by matching feature vectors in a bipartite graph to a base layer ranking sequence as a function of edge weights parameterized by an associated base layer parameter vector. Second-layer rankings define second-layer attribute vectors as bilinear combinations of the base-layer feature vectors and associated base layer parameter vectors for common attributes, which are matched in a bipartite graph to a second-layer ranking sequence as a function of edge weights parameterized by associated second-layer parameter vectors. The images are thus ranked for relevance to the query as a function of fusing the second-layer rankings. | 09-13-2012 |
20120237081 | ANOMALOUS PATTERN DISCOVERY - A trajectory of movement of an object is tracked in a video data image field that is partitioned into a plurality of different grids. Global image features from video data relative to the trajectory are extracted and compared to a learned trajectory model to generate a global anomaly detection confidence decision value as a function of fitting to the learned trajectory model. Local image features are also extracted for each of the image field grids that include object trajectory, which are compared to learned feature models for the grids to generate local anomaly detection confidence decisions for each grid as a function of fitting to the learned feature models for the grids. The global anomaly detection confidence decision value and the local anomaly detection confidence decision values for the grids are into a fused anomaly decision with respect to the tracked object. | 09-20-2012 |
20120242832 | VEHICLE HEADLIGHT MANAGEMENT - A method, data processing system, and computer program product for managing a headlight on a vehicle are presented. An image of an area in front of the vehicle is received. A first set of features is identified in the received image. The first set of features in the received image is compared with a number of sets of features from a plurality of previous images. Each image in the plurality of previous images is associated with a headlight setting. A second set of features from a previous image in the plurality of previous images matching the first set of features in the received image is identified. A determination is made whether to change a setting for the headlight on the vehicle based on the headlight setting associated with the previous image. | 09-27-2012 |
20120263346 | VIDEO-BASED DETECTION OF MULTIPLE OBJECT TYPES UNDER VARYING POSES - Training data object images are clustered as a function of motion direction attributes and resized from respective original into same aspect ratios. Motionlet detectors are learned for each of the sets from features extracted from the resized object blobs. A deformable sliding window is applied to detect an object blob in input by varying window size, shape or aspect ratio to conform to a shape of the detected input video object blob. A motion direction of an underlying image patch of the detected input video object blob is extracted and motionlet detectors selected and applied that have similar motion directions. An object is thus detected within the detected blob and semantic attributes of an underlying image patch extracted if a motionlet detectors fires, the extracted semantic attributes available for use for searching for the detected object. | 10-18-2012 |
20120274805 | Color Correction for Static Cameras - Methods and apparatus are provided for color correction of images. One or more colors in an image obtained from a static video camera are corrected by obtaining one or more historical background models from one or more prior images obtained from the static video camera; obtaining a live background model and a live foreground model from one or more current images obtained from the static video camera; generating a reference image from the one or more historical background models; and processing the reference image, the live background model, and the live foreground model to generate a set of color corrected foreground objects in the image. The set of color corrected foreground objects is optionally processed to classify a color of at least one of the foreground objects. | 11-01-2012 |
20120281873 | INCORPORATING VIDEO META-DATA IN 3D MODELS - A moving object detected and tracked within a field of view environment of a 2D data feed of a calibrated video camera is represented by a 3D model through localizing a centroid of the object and determining an intersection with a ground-plane within the field of view environment. An appropriate 3D mesh-based volumetric model for the object is initialized by using a back-projection of a corresponding 2D image as a function of the centroid and the determined ground-plane intersection. Nonlinear dynamics of a tracked motion path of the object are represented as a collection of different local linear models. A texture of the object is projected onto the 3D model, and 2D tracks of the object are upgraded to 3D motion to drive the 3D model by learning a weighted combination of the different local linear models that minimizes an image re-projection error of model movement. | 11-08-2012 |
20120284211 | IDENTIFYING ABNORMALITIES IN RESOURCE USAGE - A method, data processing system, and computer program product for identifying abnormalities in data. A model representing a plurality of modes for an activity generated from training data is retrieved. The training data includes a first plurality of measurements of a first performance of the activity over a period of time. Each of the plurality of modes is identified as one of normal and abnormal. Activity data including a second plurality of measurements of a second performance of the activity is received. A portion of the activity data is compared with the plurality of modes in the model. A notification of an abnormality in the second performance of the activity is generated in response to an identification that the portion of the activity data matches a mode in the plurality of modes identified as abnormal. Confirmation of the abnormality is requested via a user interface. | 11-08-2012 |
20120294511 | EFFICIENT RETRIEVAL OF ANOMALOUS EVENTS WITH PRIORITY LEARNING - Local models learned from anomaly detection are used to rank detected anomalies. The local models include image feature values extracted from an image field of video image data with respect to different predefined spatial and temporal local units, wherein anomaly results are determined by failures to fit to applied anomaly detection module local models. Image features values extracted from the image field local units associated with anomaly results are normalized, and image feature values extracted from the image field local units are clustered. Weights for anomaly results are learned as a function of the relations of the normalized extracted image feature values to the clustered image feature values. The normalized values are multiplied by the learned weights to generate ranking values to rank the anomalies. | 11-22-2012 |
20120308121 | IMAGE RANKING BASED ON ATTRIBUTE CORRELATION - Images are retrieved and ranked according to relevance to attributes of a multi-attribute query through training image attribute detectors for different attributes annotated in a training dataset. Pair-wise correlations are learned between pairs of the annotated attributes from the training dataset of images. Image datasets may then be searched via the trained attribute detectors for images comprising attributes in a multi-attribute query, wherein images are retrieved from the searching that each comprise one or more of the query attributes and also in response to information from the trained attribute detectors corresponding to attributes that are not a part of the query but are relevant to the query attributes as a function of the learned plurality of pair-wise correlations. The retrieved images are ranked as a function of respective total numbers of attributes within the query subset attributes. | 12-06-2012 |
20130016877 | MULTI-VIEW OBJECT DETECTION USING APPEARANCE MODEL TRANSFER FROM SIMILAR SCENESAANM Feris; Rogerio S.AACI White PlainsAAST NYAACO USAAGP Feris; Rogerio S. White Plains NY USAANM Pankanti; Sharathchandra U.AACI DarienAAST CTAACO USAAGP Pankanti; Sharathchandra U. Darien CT USAANM Siddiquie; BehjatAACI College ParkAAST MDAACO USAAGP Siddiquie; Behjat College Park MD US - View-specific object detectors are learned as a function of scene geometry and object motion patterns. Motion directions are determined for object images extracted from a training dataset and collected from different camera scene viewpoints. The object images are categorized into clusters as a function of similarities of their determined motion directions, the object images in each cluster are acquired from the same camera scene viewpoint. Zenith angles are estimated for object image poses in the clusters relative to a position of a horizon in the cluster camera scene viewpoint, and azimuth angles of the poses as a function of a relation of the determined motion directions of the clustered images to the cluster camera scene viewpoint. Detectors are thus built for recognizing objects in input video, one for each of the clusters, and associated with the estimated zenith angles and azimuth angles of the poses of the respective clusters. | 01-17-2013 |
20130044942 | EVENT DETECTION THROUGH PATTERN DISCOVERY - Events are classified through string pattern recognition. Text labels are assigned to image primitives in a time-ordered set of training images and to related time-ordered transactions in an associated training transaction log in a combined time-ordered training string of text labels as a function of image types. Transactions are labeled in a training transaction log with a transaction label, a training primitive image of a start of a transaction with a start image text label, a training primitive of an entry of a transaction into the log with an entry image text label, and a training primitive of a conclusion of a transaction with an ending image text label. Positive subset string patterns are discovered representing true events from the combined time-ordered training string of text labels, and negative subset string patterns defined by removing single transaction primitive labels from the positive subset string patterns. | 02-21-2013 |
20130050517 | VISUAL CONTENT-AWARE AUTOMATIC CAMERA ADJUSTMENT - Visual content in images captured from a scene by a camera in each of a plurality of different pose settings are analyzed to determine predicted occurrences of a transaction associated with the visual content in each pose, which are compared with actual transaction occurrence data to generate performance values for each pose as a function difference between the predicted and actual transactions. Optimized poses are chosen having the best performance value, wherein a camera controller may place the camera in the optimum pose for use in monitoring the scene and generating the primitives of interest associated with the transactions. | 02-28-2013 |
20130051613 | MODELING OF TEMPORARILY STATIC OBJECTS IN SURVEILLANCE VIDEO DATA - A foreground object blob having a bounding box detected in frame image data is classified by a finite state machine as a background, moving foreground, or temporally static object, namely as the temporally static object when the detected bounding box is distinguished from a background model of a scene image of the video data input and remains static in the scene image for a threshold period. The bounding box is tracked through matching masks in subsequent frame data of the video data input, and the object sub-classified within a visible sub-state, an occluded sub-state, or another sub-state that is not visible and not occluded as a function of a static value ratio. The ratio is a number of pixels determined to be static by tracking in a foreground region of the background model corresponding to the tracked object bounding box over a total number of pixels of the foreground region. | 02-28-2013 |
20130124514 | HIERARCHICAL RANKING OF FACIAL ATTRIBUTES - In response to a query of discernable facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings by matching feature vectors to a base layer ranking sequence as a function of edge weights. Second-layer rankings define second-layer attribute vectors as combinations of the base-layer feature vectors and associated base layer parameter vectors for common attributes, which are matched to a second-layer ranking sequence as a function of edge weights. The images are thus ranked for relevance to the query as a function of the second-layer rankings. | 05-16-2013 |
20130241928 | INCORPORATING VIDEO META-DATA IN 3D MODELS - A moving object detected and tracked within a field of view environment of a two-dimensional data feed of a calibrated video camera is represented by a three-dimensional model through localizing a centroid of the object and determining an intersection with a ground-plane within the field of view environment. An appropriate three-dimensional mesh-based volumetric model for the object is initialized by using a back-projection of a corresponding two-dimensional image as a function of the centroid and the determined ground-plane intersection. A texture of the object is projected onto the three-dimensional model, and two-dimensional tracks of the object are upgraded to three-dimensional motion to drive a three-dimensional model. | 09-19-2013 |
20130250115 | SYSTEMS AND METHODS FOR FALSE ALARM REDUCTION DURING EVENT DETECTION - Embodiments of the present invention provide a system, method, and program product to determine whether a product has been successfully purchased by identifying in a video record when a movement of a product adjacent to a scanner occurs, and whether the scanner did not record a purchase transaction at that time; measuring a difference in time between the time of the movement of the product and a time of another movement of a product, and determining by a trained support vector machine a likelihood that the product was successfully purchased. Alternately, the difference in time can be measured between the time of the movement of the product and a time of a transaction record, or between the time of the movement of the product and a boundary time. The support vector machine can use a radial basis function kernel and can generate a decision value and a confidence score. | 09-26-2013 |
20130266227 | HUMAN ACTIVITY DETERMINATION FROM VIDEO - Automated analysis of video data for determination of human behavior includes segmenting a video stream into a plurality of discrete individual frame image primitives which are combined into a visual event that may encompass an activity of concern as a function of a hypothesis. The visual event is optimized by setting a binary variable to true or false as a function of one or more constraints. The visual event is processed in view of associated non-video transaction data and the binary variable by associating the visual event with a logged transaction if associable, issuing an alert if the binary variable is true and the visual event is not associable with the logged transaction, and dropping the visual event if the binary variable is false and the visual event is not associable. | 10-10-2013 |
20130272573 | MULTI-VIEW OBJECT DETECTION USING APPEARANCE MODEL TRANSFER FROM SIMILAR SCENES - View-specific object detectors are learned as a function of scene geometry and object motion patterns. Motion directions are determined for object images extracted from a training dataset and collected from different camera scene viewpoints. The object images are categorized into clusters as a function of similarities of their determined motion directions, the object images in each cluster are acquired from the same camera scene viewpoint. Zenith angles are estimated for object image poses in the clusters relative to a position of a horizon in the cluster camera scene viewpoint, and azimuth angles of the poses as a function of a relation of the determined motion directions of the clustered images to the cluster camera scene viewpoint. Detectors are thus built for recognizing objects in input video, one for each of the clusters, and associated with the estimated zenith angles and azimuth angles of the poses of the respective clusters. | 10-17-2013 |
20130279743 | ANOMALOUS RAILWAY COMPONENT DETECTION - A method and system for inspecting railway components. The method includes receiving a stream of images containing railway components, detecting a railway component in each image, generating a plurality of feature vectors for each railway component image, measuring the dissimilarity between the railway component and a set of railway components detected in preceding images, in a sliding window, based on the feature vectors. | 10-24-2013 |
20130329049 | MULTISENSOR EVIDENCE INTEGRATION AND OPTIMIZATION IN OBJECT INSPECTION - Video image data is acquired from synchronized cameras having overlapping views of objects moving past the cameras through a scene image in a linear array and with a determined speed. Processing units generate one or more object detections associated with confidence scores within frames of the camera video stream data. The confidence scores are modified as a function of constraint contexts including a cross-frame constraint that is defined by other confidence scores of other object detection decisions from the video data that are acquired by the same camera at different times; a cross-view constraint defined by other confidence scores of other object detections in the video data from another camera with an overlapping field-of-view; and a cross-object constraint defined by a sequential context of a linear array of the objects, spatial attributes of the objects and the determined speed of the movement of the objects relative to the cameras. | 12-12-2013 |
20130336531 | SEQUENTIAL EVENT DETECTION FROM VIDEO - Human behavior is determined by sequential event detection by constructing a temporal-event graph with vertices representing primitive images of images of a video stream, and also of idle states associated with the respective primitive images. A human activity event is determined as a function of a shortest distance path of the temporal-event graph vertices. | 12-19-2013 |
20130336581 | MULTI-CUE OBJECT DETECTION AND ANALYSIS - Foreground objects of interest are distinguished from a background model by dividing a region of interest of a video data image into a grid array of individual cells that are each smaller than that a foreground object of interest. More particularly, image data of the foreground object of interest spans a contiguous plurality of the cells. Each of the cells are labeled as foreground if accumulated edge energy within the cell meets an edge energy threshold, if color intensities for different colors within each cell differ by a color intensity differential threshold, or as a function of combinations of said determinations in view of one or more combination rules. | 12-19-2013 |
20140003708 | OBJECT RETRIEVAL IN VIDEO DATA USING COMPLEMENTARY DETECTORS | 01-02-2014 |
20140055609 | DETERMINING FOREGROUNDNESS OF AN OBJECT IN SURVEILLANCE VIDEO DATA - A computer identifies a proto-object in a digital image using a background subtraction method, the proto-object being associated with a lighting artifact in the surveillance region. The background subtraction method preserves boundary details and interior texture details of proto-objects associated with lighting artifacts. A plurality of characteristics of the proto-object digital data are determined, the characteristics, individually or in combination, distinguish a proto-object related to a lighting artifact from its background. A learning machine, trained with the plurality of characteristics of proto-objects classified as either foreground or not foreground, determines a likelihood that the plurality of characteristics is associated with a foreground object. | 02-27-2014 |
20140056476 | INCORPORATING VIDEO META-DATA IN 3D MODELS - A moving object tracked within a field of view environment of a two-dimensional data feed of a calibrated video camera is represented by a three-dimensional model. An appropriate three-dimensional mesh-based volumetric model for the object is initialized by using a back-projection of a corresponding two-dimensional image. A texture of the object is projected onto the three-dimensional model, and two-dimensional tracks of the object are upgraded to three-dimensional motion to drive a three-dimensional model. | 02-27-2014 |
20140098221 | APPEARANCE MODELING FOR OBJECT RE-IDENTIFICATION USING WEIGHTED BRIGHTNESS TRANSFER FUNCTIONS - An approach for re-identifying an object in a first test image is presented. Brightness transfer functions (BTFs) between respective pairs of training images are determined. Respective similarity measures are determined between the first test image and each of the training images captured by the first camera (first training images). A weighted brightness transfer function (WBTF) is determined by combining the BTFs weighted by weights of the first training images. The weights are based on the similarity measures. The first test image is transformed by the WBTF to better match one of the training images captured by the second camera. Another test image, captured by the second camera, is identified because it is closer in appearance to the transformed test image than other test images captured by the second camera. An object in the identified test image is a re-identification of the object in the first test image. | 04-10-2014 |
20140098989 | MULTI-CUE OBJECT ASSOCIATION - Multiple discrete objects within a scene image captured by a single camera track are distinguished as un-labeled from a background model within a first frame of a video data input. Object position and object appearance and/or object size attributes are determined for each of the blobs, and costs determined to assign to existing blobs of existing object tracks as a function of the determined attributes and combined to generate respective combination costs. The un-labeled object blob that has a lowest combined cost of association with any of the existing object tracks is labeled with the label of that track having the lowest combined cost, said track is removed from consideration for labeling remaining un-labeled object blobs, and the process iteratively repeated until each of the track labels have been used to label one of the un-labeled blobs. | 04-10-2014 |
20140122470 | HIERARCHICAL RANKING OF FACIAL ATTRIBUTES - In response to a query of discernable facial attributes, the locations of distinct and different facial regions are estimated from face image data, each relevant to different attributes. Different features are extracted from the estimated facial regions from database facial images, which are ranked in base layer rankings as a function of relevance of extracted features to attributes relevant to the estimated regions, and in second-layer rankings as a function of combinations of the base layer rankings and relevance of the extracted features to common ones of the attributes relevant to the estimated regions. The images are ranked in relevance to the query as a function of the second-layer rankings. | 05-01-2014 |
20140147041 | IMAGE COLOR CORRECTION - Color-correcting a digital image comprising P pixels (P≧4) is presented. Each of the P pixels has a respective color. Color strengths of the P pixels are determined based at least on respective intensities, respective saturations, or both respective intensities and respective saturations of the P pixels. A subset of the P pixels less than all of the P pixels is determined. The pixels in the subset have respective color strengths in a range of respective color strength. All other pixels of the P pixels have respective color strengths outside of the range of respective color strengths. Color correction is determined for the P pixels based in part on the colors of the respective pixels in the subset which are the only pixels of the P pixels used for determining the color correction. The colors of the P pixels are corrected based on the color correction. | 05-29-2014 |
20140164306 | PATHWAY MANAGEMENT USING MODEL ANALYSIS AND FORCASTING - A computer generates a three dimensional map of a pathway area using a plurality of overhead images. The computer determines a forecasted weather pattern to occur in the pathway area. The computer analyzes the three dimensional map and the forecasted weather pattern to predict one or more violations of the pathway. The computer generates a priority for the one or more predicted violations of the pathway. The computer generates a plan for pathway management of the pathway area. | 06-12-2014 |
20140185925 | BOOSTING OBJECT DETECTION PERFORMANCE IN VIDEOS - A method and system for training a special object detector to distinguish a foreground object appearing in a sequence of frames for a target domain. The sequence of frames depicts motion of the foreground object in a non-uniform background. The foreground object is detected in a high-confidence subwindow of an initial frame of the sequence, which includes computing a measure of confidence that the high-confidence subwindow includes the foreground object and determining that the measure of confidence exceeds a specified confidence threshold. The foreground object is tracked in respective positive subwindows of subsequent frames appearing after the initial frame. The subsequent frames are within a specified short period of time. The positive subwindows are used to train the special object detector to detect the foreground object in the target domain. The positive subwindows include the subwindow of the initial frame and the respective subwindows of the subsequent frames. | 07-03-2014 |
20140211988 | ATTRIBUTE-BASED ALERT RANKING FOR ALERT ADJUDICATION - Alerts to object behaviors are prioritized for adjudication as a function of relative values of abandonment, foregroundness and staticness attributes. The attributes are determined from feature data extracted from video frame image data. The abandonment attribute indicates a level of likelihood of abandonment of an object. The foregroundness attribute quantifies a level of separation of foreground image data of the object from a background model of the image scene. The staticness attribute quantifies a level of stability of dimensions of a bounding box of the object over time. Alerts are also prioritized according to an importance or relevance value that is learned and generated from the relative abandonment, foregroundness and staticness attribute strengths. | 07-31-2014 |
20140241583 | SECURE SELF-CHECKOUT - Various embodiments allow scanning by a shopper using a barcode reader (e.g., a scanner) attached to or positioned near the shopping receptacle. As items are scanned, they are identified based on their barcode and added to an item list. Item verification can then performed at checkout using imaging technology. For example, the shopping cart or shopping basket can be brought into the field of view of a computer-connected camera. The camera and computer can, working from the customer's item list developed when the items are scanned, observe each product in the receptacle and ring it up. If all products can be accounted for, the customer is free to leave; otherwise the customer is denied egress, informed of the problem, etc. A store employee can also be signaled to investigate. | 08-28-2014 |
20140247994 | HUMAN ACTIVITY DETERMINATION FROM VIDEO - Automated analysis of video data for determination of human behavior includes segmenting a video stream into a plurality of discrete individual frame image primitives which are combined into a visual event that may encompass an activity of concern as a function of a hypothesis. The visual event is optimized by setting a binary variable to true or false as a function of one or more constraints. The visual event is processed in view of associated non-video transaction data and the binary variable by associating the visual event with a logged transaction if associable, issuing an alert if the binary variable is true and the visual event is not associable with the logged transaction, and dropping the visual event if the binary variable is false and the visual event is not associable. | 09-04-2014 |
20140253732 | TOPOLOGY DETERMINATION FOR NON-OVERLAPPING CAMERA NETWORK - Image-matching tracks the movements of the objects from initial camera scenes to ending camera scenes in non-overlapping cameras. Paths are defined through scenes for pairings of initial and ending cameras by different respective scene entry and exit points. For each of said camera pairings a combination path having a highest total number of tracked movements relative to all other combinations of one path through the initial and ending camera scene is chosen, and the scene exit point of the selected path through the initial camera and the scene entry point of the selected path into the ending camera define a path connection of the initial camera scene to the ending camera scene. | 09-11-2014 |
20140293043 | DETERMINING CAMERA HEIGHT USING DISTRIBUTIONS OF OBJECT HEIGHTS AND OBJECT IMAGE HEIGHTS - A camera at a fixed vertical height positioned above a reference plane, with an axis of a camera lens at an acute angle with respect to a perpendicular of the reference plane. One or more processors receive images of different people. The vertical measurement values of the images of different people are determined. The one or more processors determine a first statistical measure associated with a statistical distribution of the vertical measurement values. The known heights of people from a known statistical distribution of heights of people are transformed to normalized measurements, based in part on a focal length of the camera lens, the angle of the camera, and a division operator in an objective function of differences between the normalized measurements and the vertical measurement values. The fixed vertical height of the camera is determined, based at least on minimizing the objective function. | 10-02-2014 |
20140294231 | AUTOMATICALLY DETERMINING FIELD OF VIEW OVERLAP AMONG MULTIPLE CAMERAS - Field of view overlap among multiple cameras is automatically determined as a function of the temporal overlap of object tracks determined within their fields-of-view. Object tracks with the highest similarity value are assigned into pairs, and portions of the assigned object track pairs having a temporally overlapping period of time are determined. Scene entry points are determined from object locations on the tracks at a beginning of the temporally overlapping period of time, and scene exit points from object locations at an ending of the temporally overlapping period of time. Boundary lines for the overlapping fields-of-view portions within the corresponding camera fields-of-view are defined as a function of the determined entry and exit points in their respective fields-of-view. | 10-02-2014 |
20140314277 | INCORPORATING VIDEO META-DATA IN 3D MODELS - A moving object tracked within a field of view environment of a two-dimensional data feed of a calibrated video camera is represented by a three-dimensional model. An appropriate three-dimensional mesh-based volumetric model for the object is initialized by using a back-projection of a corresponding two-dimensional image. A texture of the object is projected onto the three-dimensional model, and two-dimensional tracks of the object are upgraded to three-dimensional motion to drive a three-dimensional model. | 10-23-2014 |
20140353372 | SMART SCANNING SYSTEM - The present invention provides a smart scanning system comprising an integrated scanning and image capture system in which one or more image capture device(s) (e.g., still camera, video camera, etc.) and a barcode scanner are positioned within a common enclosure that is a component of a checkout station. The barcode of item is scanned and an image of the item is recorded. The identity of the item as determined based on the barcode is compared to its appearance as determined based on its image. If the identity is inconsistent with its appearance, a discrepancy is registered. It is then determined whether the discrepancy is due to fraud (e.g., theft) or device error. In the case of the latter, the system can be updated to prevent a repeat of the error. | 12-04-2014 |
20150015606 | HAZARD DETECTION FOR ASSET MANAGEMENT - An approach that detects locations of hazardous conditions within an infrastructure is provided. This approach uses satellite imagery, GIS data, automatic image processing, and predictive modeling to determine the location of the hazards automatically, thus optimizing infrastructure management. Specifically, a hazard detection tool provides this capability. The hazard detection tool comprises a detection component configured to: receive visual media containing asset location data about a set of physical assets, and hazard location data about potential hazards within a vicinity of each of the set of physical assets. The detection component further receives graphical information system (GIS) data containing asset location data about each of the set of physical assets. The hazard detection tool further comprises an analysis component configured to: analyze the visual media to determine if a hazardous condition exists for each of the set of physical assets; and apply the GIS data to the visual media to determine a location of hazardous conditions within the infrastructure. | 01-15-2015 |
20150023560 | MULTI-CUE OBJECT ASSOCIATION - Multiple discrete objects within a scene image captured by a single camera track are distinguished as un-labeled from a background model within a first frame of a video data input. Object position, object appearance and/or object size attributes are determined for each of the blobs, and costs determined to assign to existing blobs of existing object tracks as a function of the determined attributes. The un-labeled object blob that has a lowest cost of association with any of the existing object tracks is labeled with the label of that track having the lowest cost, said track is removed from consideration for labeling remaining un-labeled object blobs, and the process iteratively repeated until each of the track labels have been used to label one of the un-labeled blobs. | 01-22-2015 |
20150039542 | IMAGE RANKING BASED ON ATTRIBUTE CORRELATION - Images are retrieved and ranked according to relevance to attributes of a multi-attribute query through training image attribute detectors for different attributes annotated in a training dataset. Pair-wise correlations are learned between pairs of the annotated attributes from the training dataset of images. Image datasets may are searched via the trained attribute detectors for images comprising attributes in a multi-attribute query. The retrieved images are ranked as a function of comprising attributes that are not within the query subset plurality of attributes but are paired to one of the query subset plurality of attributes by the pair-wise correlations, wherein the ranking is an order of likelihood that the different ones of the attributes will appear in an image with the paired one of the query subset plurality of attributes. | 02-05-2015 |
20150055830 | AUTOMATICALLY DETERMINING FIELD OF VIEW OVERLAP AMONG MULTIPLE CAMERAS - Field of view overlap among multiple cameras are automatically determined as a function of the temporal overlap of object tracks determined within their fields-of-view. Object tracks with the highest similarity value are assigned into pairs, and portions of the assigned object track pairs having a temporally overlapping period of time are determined. Scene entry points are determined from object locations on the tracks at a beginning of the temporally overlapping period of time, and scene exit points from object locations at an ending of the temporally overlapping period of time. Boundary lines for the overlapping fields-of-view portions within the corresponding camera fields-of-view are defined as a function of the determined entry and exit points in their respective fields-of-view. | 02-26-2015 |
20150063689 | MULTI-CUE OBJECT DETECTION AND ANALYSIS - Foreground objects of interest are distinguished from a background model by dividing a region of interest of a video data image into a grid array of individual cells. Each of the cells are labeled as foreground if accumulated edge energy within the cell meets an edge energy threshold, or if color intensities for different colors within each cell differ by a color intensity differential threshold, or as a function of combinations of said determinations. | 03-05-2015 |