WINDOW GROUPING AND TRACKING FOR FAST OBJECT DETECTION

摘要

Disclosed examples include image processing methods and systems to process image data, including computing a plurality of scaled images according to input image data for a current image frame, computing feature vectors for locations of the individual scaled images, classifying the feature vectors to determine sets of detection windows, and grouping detection windows to identify objects in the current frame, where the grouping includes determining first clusters of the detection windows using non-maxima suppression grouping processing, determining positions and scores of second clusters using mean shift clustering according to the first clusters, and determining final clusters representing identified objects in the current image frame using non-maxima suppression grouping of the second clusters. Disclosed examples also include methods and systems to track identified objects from one frame to another using feature vectors and overlap of identified objects between frames to minimize computation intensive operations involving feature vectors.

主权项

1. A method to process image data, the method comprising:
computing a plurality of scaled images according to image data for a current input image frame; computing feature vectors for pixel locations or groups of pixel locations of the individual scaled images; classifying the feature vectors to determine sets of detection windows; grouping the detection windows to identify objects in the current image frame, including:
determining first clusters of the detection windows using non-maxima suppression grouping processing,determining positions of second clusters and scores of the second clusters using a mean shift clustering process according to the first clusters, anddetermining final clusters representing identified objects in the current image frame using non-maxima suppression grouping processing of the second clusters.