Continuously tracking and see-through occlusion based on a new hybrid synthetic aperture imaging model

Abstract

Robust detection and tracking of multiple people in cluttered and crowded scenes with severe occlusion is a significant challenging task for many computer vision applications. In this paper, we present a novel hybrid synthetic aperture imaging model to solve this problem. The main characteristics of this approach include: (1) To the best of our knowledge, this algorithm is the first time to solve the occluded people imaging and tracking problem in a joint multiple camera synthetic aperture imaging domain. (2) A multiple model framework is designed to achieve seamless interaction among the detection, imaging and tracking modules. (3)In the object detection module, a multiple constraints based approach is presented for people localizing and ghost objects removal in a 3D foreground silhouette synthetic aperture imaging volume. (4) In the synthetic imaging module, a novel occluder removal based synthetic imaging approach is proposed to continuously obtain object clear image even under severe occlusion. (5) In the object tracking module, a camera array is used for robust people tracking in color synthetic aperture images. A network camera based hybrid synthetic aperture imaging system has been set up, and experimental results with qualitative and quantitative analysis demonstrate that the method can reliably locate and see people in challenge scene.