Abstract: A method for performing crowd segmentation includes receiving video image data (S21). Background differencing is performed on the received video image data to identify a foreground silhouette shape (S22). Approximate number and position of human subjects within the received video image data are determined by matching the foreground silhouette shape against a set of predetermined foreground silhouette shapes, for each of which a number and position of human subjects is known (S28). The estimated number and position of the human subjects is refined to determine a final number and position of the human subjects (S27).

Abstract: A system for use by a user and with a plurality of stored images. A retrieval facility for accessing said plurality of stored images; a display facility for displaying images from said plurality to said user; a response facility for permitting interaction between the user and the system; a selection facility for determining an image that is of interest to said user based on said interaction between said user and said system; and a comparison facility for carrying out a similarity analysis between the image determined to be of interest and each of at least a subset of said plurality of stored images, the similarity analysis involving a calculation based on one or more of a measurement of color similarity, texture similarity and shape similarity. The retrieval, display and response facility can be defined by a web browser.

Abstract: A tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking is provided. The solution to the tracking problem is articulated into a method that encodes the spatial configuration of features along with their density and yet retains robustness to spatial deformations and feature density variations. The method of encoding of spatial configuration is provided using a set of kernels whose parameters can be optimized for a given class of objects off-line. The method enables the use of mean-shift iterations and runs in real-time. Better tracking results by the novel tracking method as compared to the original mean-shift tracker are demonstrated.

Abstract: A method for object detection from a visual image of a scene. The method includes: using a first order predicate logic formalism to specify a set of logical rules to encode contextual knowledge regarding the object to be detected; inserting the specified logical rules into a knowledge base; obtaining the visual image of the scene; applying specific object feature detectors to some or all pixels in the visual image of the scene to obtain responses at those locations; using the obtained responses to generate logical facts indicative of whether specific features or parts of the object are present or absent at that location in the visual image; inserting the generated logical facts into the knowledge base; and combining the logical facts with the set of logical rules to whether the object is present or absent at a particular location in the scene.

Abstract: A method and system for video-based encroachment detection are provided, the method including receiving first and second images, modeling a background from the first image, subtracting the background from the second image to provide a detection map, calibrating the size of an object from the pixel level, integrating a projection of the object with the detection map using dynamic programming, and detecting the object in a region if the projection matches that region of the detection map; and the system including a processor, a background modeling unit coupled with the processor for modeling a background from the first image and subtracting the background from the second image to provide a detection map, and a dynamic programming unit coupled with the processor for calibrating the size of an object from the pixel level, integrating a projection of the object with the detection map, and detecting the object in a region if the projection matches that region of the detection map.

Abstract: A method for detecting events in a video sequence includes providing a video sequence, sampling the video sequence at regular intervals to form a series of snapshots of the sequence, measuring a similarity of each snapshot, measuring a similarity change between successive pairs of snapshots, wherein if a similarity change magnitude is greater than a predetermined threshold, a change event has been detected, verifying the change event to exclude a false positive, and completing the processing of the snapshot incorporating the verified change event.

Abstract: A system and method for illumination invariant change detection are provided, the system including a processor, an energy ranking unit in signal communication with the processor for extracting block coefficients for the first and second images and computing an energy difference responsive to the coefficients for a frequency energy between the first and second images, and a change detection unit in signal communication with the processor for analyzing the energy difference and detecting a scene change if the energy difference is indicative of change; and the method including receiving first and second images, extracting block coefficients corresponding to frequency energies for the first and second images, computing an energy difference for at least one of the frequency energies between the first and second images, analyzing the at least one energy difference, and detecting a scene change if the energy difference is indicative of change.

Abstract: A method for performing crowd segmentation includes receiving video image data (S21). Background differencing is performed on the received video image data to identify a foreground silhouette shape (S22). Approximate number and position of human subjects within the received video image data are determined by matching the foreground silhouette shape against a set of predetermined foreground silhouette shapes, for each of which a number and position of human subjects is known (S28). The estimated number and position of the human subjects is refined to determine a final number and position of the human subjects (S27).

Abstract: A method and system for background maintenance of a vision system by fusing a plurality of detection methods and applying a 1D analysis to verify an absence of a static vehicle is provided. Methods for analyzing spatial temporal images in vehicle detection systems are provided. A method for processing a 1-dimensional profile is provided to detect a static vehicle in a traffic lane. When no vehicles are detected, a background image may be updated. A method for processing a 1-dimensional profile is also provided to detect occlusions of a traffic lane by a vehicle in a neighboring traffic lane. A method to reduce false alarm in wrong way driver detection applies the method for occlusion detection. A method to detect a slow moving vehicle in a traffic lane from a spatial-temporal image is also disclosed. A system applying the methods for processing 1-dimensional profiles is also provided.

Abstract: A tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking is provided. The solution to the tracking problem is articulated into a method that encodes the spatial configuration of features along with their density and yet retains robustness to spatial deformations and feature density variations. The method of encoding of spatial configuration is provided using a set of kernels whose parameters can be optimized for a given class of objects off-line. The method enables the use of mean-shift iterations and runs in real-time. Better tracking results by the novel tracking method as compared to the original mean-shift tracker are demonstrated.

Abstract: A method and system for video-based encroachment detection are provided, the method including receiving first and second images, modeling a background from the first image, subtracting the background from the second image to provide a detection map, calibrating the size of an object from the pixel level, integrating a projection of the object with the detection map using dynamic programming, and detecting the object in a region if the projection matches that region of the detection map; and the system including a processor, a background modeling unit coupled with the processor for modeling a background from the first image and subtracting the background from the second image to provide a detection map, and a dynamic programming unit coupled with the processor for calibrating the size of an object from the pixel level, integrating a projection of the object with the detection map, and detecting the object in a region if the projection matches that region of the detection map.

Abstract: A system and method for illumination invariant change detection are provided, the system including a processor, an energy ranking unit in signal communication with the processor for extracting block coefficients for the first and second images and computing an energy difference responsive to the coefficients for a frequency energy between the first and second images, and a change detection unit in signal communication with the processor for analyzing the energy difference and detecting a scene change if the energy difference is indicative of change; and the method including receiving first and second images, extracting block coefficients corresponding to frequency energies for the first and second images, computing an energy difference for at least one of the frequency energies between the first and second images, analyzing the at least one energy difference, and detecting a scene change if the energy difference is indicative of change.

Abstract: A method for detecting events in a video sequence includes providing a video sequence, sampling the video sequence at regular intervals to form a series of snapshots of the sequence, measuring a similarity of each snapshot, measuring a similarity change between successive pairs of snapshots, wherein if a similarity change magnitude is greater than a predetermined threshold, a change event has been detected, verifying the change event to exclude a false positive, and completing the processing of the snapshot incorporating the verified change event.