Abstract: Described is a system and method for the classification of agents based on agent movement patterns. In operation, the system receives position data of a moving agent from a camera or sensor. Motion data of the moving agent is then extracted and used to generate a predicted future motion of the moving agent using a set of pre-calculated Echo State Networks (ESN). Each ESN represents an agent classification and generates a predicted future motion. A prediction error is generated for each ESN by comparing the predicted future motion for each ESN with actual motion data. Finally, the agent is classified based on the ESN having the smallest prediction error.

Abstract: A method includes receiving image data at a first tracking system. The image data represents a region in an image of a sequence of images. The method also includes generating a first tracking fingerprint based on the image data. The method further includes comparing the first tracking fingerprint and a second tracking fingerprint. The method also includes providing an output from the first tracking system to a second tracking system based on a result of the comparison of the first tracking fingerprint and the second tracking fingerprint. The output includes an instruction associated with an object model stored at the second tracking system.

Abstract: Described is a system and method for the classification of agents based on agent movement patterns. In operation, the system receives position data of a moving agent from a camera or sensor. Motion data of the moving agent is then extracted and used to generate a predicted future motion of the moving agent using a set of pre-calculated Echo State Networks (ESN). Each ESN represents an agent classification and generates a predicted future motion. A prediction error is generated for each ESN by comparing the predicted future motion for each ESN with actual motion data. Finally, the agent is classified based on the ESN having the smallest prediction error.

Abstract: A method includes receiving image data at a first tracking system. The image data represents a region in an image of a sequence of images. The method also includes generating a first tracking fingerprint based on the image data. The method further includes comparing the first tracking fingerprint and a second tracking fingerprint. The method also includes providing an output from the first tracking system to a second tracking system based on a result of the comparison of the first tracking fingerprint and the second tracking fingerprint. The output includes an instruction associated with an object model stored at the second tracking system.

Abstract: Described is a training system for training a vision-based object detector. The system is configured to run an object detector on an image of a cleared scene to detect objects in the cleared scene. The object detector includes a support vector machine (SVM) or similar classifier with a feature model to generate an SVM score for object features and a spatial bias threshold to generate augmented object scores. The system designated detected objects in the cleared scene as false detections and, based on that, updates at least one of the feature model and spatial bias threshold to designate the false detections as background. The updated feature model or updated spatial bias threshold are then stored for use in object detection.

Abstract: A method includes receiving image data at a first tracking system. The image data may represent a region in an image of a sequence of images. The method includes generating a first tracking fingerprint based on the image data. The method includes comparing the first tracking fingerprint and a second tracking fingerprint. The method further includes providing an output from the first tracking system to a second tracking system based on a result of the comparison of the first tracking fingerprint and the second tracking fingerprint.

Abstract: A method of classification and segmentation of an image using modules on a computer system includes receiving a plurality of models having features suitable for classifying each pixel of the image into a respective one of a plurality of categories, using a classifier to provide a score for each pixel in the image for each category and using a segmenter to segment the image into image segments, wherein each image segment is a contiguous set of pixels having at least one common feature. For each image segment a set of average probabilities for each category is determined, and for each image segment, a most likely category to which the image segment belongs is determined by the maximum average probability resulting in a labeled segment image, which is used to identify any empty areas as incorrect holes. Then any empty areas that are identified as incorrect holes are filled.

Abstract: The present invention relates to a system for detecting an object of interest in a scene. The system operates by receiving an image frame of a scene and extracting features from the image frame, the features being descriptors. The descriptors are quantized to generate PHOW features. A sliding window protocol is implemented to slide a window over the image and analyze the PHOW features that fall inside the window. Finally, the system determines if the PHOW features represent the object of interest and, if so, then designates the window as a location in the image with a detected object of interest.

Abstract: A method includes receiving image data at a first tracking system. The image data may represent a region in an image of a sequence of images. The method includes generating a first tracking fingerprint based on the image data. The method includes comparing the first tracking fingerprint and a second tracking fingerprint. The method further includes providing an output from the first tracking system to a second tracking system based on a result of the comparison of the first tracking fingerprint and the second tracking fingerprint.

Abstract: A method of classification and segmentation of an image using modules on a computer system includes receiving a plurality of models having features suitable for classifying each pixel of the image into a respective one of a plurality of categories, using a classifier to provide a score for each pixel in the image for each category and using a segmenter to segment the image into image segments, wherein each image segment is a contiguous set of pixels having at least one common feature. For each image segment a set of average probabilities for each category is determined, and for each image segment, a most likely category to which the image segment belongs is determined by the maximum average probability resulting in a labeled segment image, which is used to identify any empty areas as incorrect holes. Then any empty areas that are identified as incorrect holes are filled.

Abstract: Described is a system for scene change detection. The system receives an input image (current frame) from a video stream. The input image is color conditioned to generate a color conditioned image. A sliding window is used to segment the input image into a plurality boxes. Descriptors are extracted from each box of the color conditioned image. Thereafter, differences in the descriptors are identified between a current frame and past frames. The differences are attenuated to generate a descriptor attenuation factor ?i. Initial scores are generated for each box based on the descriptor attenuation factor ?i. The initial scores are filtered to generate a set of conspicuity scores for each box, the set of conspicuity scores being reflective of the conspicuity of each box in the image. Finally, the conspicuity scores are presented to the user or provided to other systems for further processing.

Abstract: The present invention relates to a system for identifying regions of interest in visual imagery. The system is configured to receive a series of consecutive frames representing a scene as captured from N sensors. The frames include at least a current frame and a previous frame. A surprise map can be generated based on features found in the current frame and the previous frame. The surprise map having a plurality of values corresponding to spatial locations within the scene. Based on the values, a surprise in the scene can be identified if a value in the surprise map exceeds a predetermined threshold.