Raytheon Company

Hrl Laboratories, LLC

Cynthia E Daniell

Narayan Srinivasa

Qin Jiang

David B Shu

The present invention relates to a motion recognition system for distinguishing motion between two different entity forms, such as distinguishing human motion from animal motion. The motion recognition system comprises a moving object detection component, a motion feature extraction component, and a motion feature classification component. The moving object detection component is configured to detect an object within a video sequence and generate a moving object signal. The motion feature extraction component is configured to receive the moving object signal and to extract features representing the detected object within the object signal. The motion feature classification component is configured to classify the features extracted from the detected object as either human motion or animal motion, thereby generating an identification signal. Through detecting, extracting and classifying the objection, a user can determine if the object is a human or an animal.

Motion recognition system

A method for classification of a target object having a periphery comprises the steps of: selecting a plurality of random first chords Dacross the periphery of the target object; For each of the pairs, the second chords are orthogonal to the first chords, and the second chords share a point with the first chords and the periphery.

Recognition algorithm for the unknown target rejection based on shape statistics obtained from orthogonal distance function

A plurality of image chips () (over 100), each of the chips containing the same, known target of interest, such as, for example an M109 tank are presented to the system for training. Each image chip of the known target is slightly different than the next, showing the known target at different aspect angles and rotation with respect to the moving platform acquiring the image chip. The system extract multiple features of the known target from the plurality of image chips () presented for storage and analysis, or training. These features distinguish a known target of interest from the nearest similar target to the M109 tank, for example a Caterpillar D7 bulldozer. These features are stored for use during unknown target identification. When an unknown target chip is presented, the recognition algorithm relies on the features stored during training to attempt to identify the target. The tools used for extracting features of the known target of interest as well as the unknown target presented for identification are the same and include the Haar Transform (), and entropy measurements () generating coefficient locations. Using the Karhunen-Loeve (KL) transform, eigenvectors are computed. A Gaussian mixture model (GMM) () is used to compare the extracted coefficients and eigenfeatures from the known target chips with that of the unknown target chips. Thus the system is trained initially by presenting to it known target chips for classification. Subsequently, the system uses the training in the form of stored eigenfeatures and entropy coefficients fused with multiscale features to identify unknown targets.

Growing community of inventors

Pasadena, CA, United States of America

Cynthia E Daniell