—We present in this paper an integrated solution to rapidly recognizing dynamic objects in surveillance videos by exploring various contextual information. This solution consists...
Xiaobai Liu, Liang Lin, Shuicheng Yan, Hai Jin, We...
We propose a reduced algebraic cost based on pairwise epipolar constraints for the iterative refinement of a multiple view 3D reconstruction. The aim is to accelerate the intermedi...
The aim of this paper is to achieve seamless image stitching for eliminating obvious visual artifact caused by severe intensity discrepancy, image distortion and structure misalig...
In the perspective of a sustainable urban planning, it is necessary to investigate cities in a holistic way and to accept surprises in the response of urban environments to a part...
Multi-camera tracking systems often must maintain consistent identity labels of the targets across views to recover 3D trajectories and fully take advantage of the additional info...