Simultaneous active camera array focus plane estimation and occluded moving object imaging

a r t i c l e i n f o Automatically focusing and seeing occluded moving object in cluttered and complex scene is a significant challenging task for many computer vision applications. In this paper, we present a novel synthetic aperture imaging approach to solve this problem. The unique characteristics of this work include the following: (1) To the best of our knowledge, this work is the first to simultaneously solve camera array auto focusing and occluded moving object imaging problem. (2) A unified framework is designed to achieve seamless interaction between the focus-ing and imaging modules. (3) In the focusing module, a local and global constraint-based optimization algorithm is presented to dynamically estimate the focus plane of the moving object. (4) In the imaging module, a novel visibility analysis based active synthetic aperture imaging approach is proposed to remove the occluder and significantly improve the quality of occluded object imaging. An active camera array system has been set up and evaluated in challenging indoor and outdoor scenes. Extensive experimental results with qualitative and quantitative analyses demonstrate the superiority of the proposed approach compared with state-of-the-art approaches. Occluded moving object imaging is a challenging problem in the field of computer vision and pattern recognition. It plays an important role especially in surveillance, remote sensing and underwater filming. Since high level understanding of a scene relies heavily on accurate low level imaging of objects, developing a high performance occluded moving object imaging system has become a subject of great scientific and commercial interests. Although many algorithms and systems have been developed in the literature, to the best of our knowledge few works have been done in occluded moving object imaging possibly due to several challenges: (1) Visibility varies significantly over frames, ranging from occlusion-free to complete occlusion due to complex interaction among objects and surroundings. (2) The out of focus problem caused by the movements of the camera and the object adds huge uncertainty to the automatic focus plane estimation. To address the problems above, we present a novel active synthetic aperture imaging approach in this paper. Fig. 1 displays our camera array system and examples of auto-focusing and occluded object imaging results. Please note that the reason why the synthetic aperture images look dark is that image wrapping will then change the size of the image and the region where there is no mapping will be dark (Fig. 1, …