Surveillance Video Parsing with Single Frame Supervision

Liu, Si; Wang, Changhu; Qian, Ruihe; Han, Yu; Bao, Renda

doi:10.48550/arxiv.1611.09587

Cited by 5 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic segmentation. Semantic segmentation [18,19,20] aims to cluster image pixels of the same object class with assigned labels. Numerous recent methods use semantic segmentation to resolve ambiguities in road signs detection [21], 3D reconstruction [10], and optical flow estimation by using different motion models at different object regions [28].…”

Section: Related Workmentioning

confidence: 99%

Video Deblurring via Semantic Segmentation and Pixel-Wise Non-linear Kernel

Ren

Pan

Cao

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Video deblurring is a challenging problem as the blur is complex and usually caused by the combination of camera shakes, object motions, and depth variations. Optical flow can be used for kernel estimation since it predicts motion trajectories. However, the estimates are often inaccurate in complex scenes at object boundaries, which are crucial in kernel estimation. In this paper, we exploit semantic segmentation in each blurry frame to understand the scene contents and use different motion models for image regions to guide optical flow estimation. While existing pixel-wise blur models assume that the blur kernel is the same as optical flow during the exposure time, this assumption does not hold when the motion blur trajectory at a pixel is different from the estimated linear optical flow. We analyze the relationship between motion blur trajectory and optical flow, and present a novel pixel-wise non-linear kernel model to account for motion blur. The proposed blur model is based on the non-linear optical flow, which describes complex motion blur more effectively. Extensive experiments on challenging blurry videos demonstrate the proposed algorithm performs favorably against the state-of-the-art methods.

show abstract