Research and Implementation of Anti-occlusion Algorithm for Vehicle Detection in Video Data
Lists
Only you see this
Abstract
Object detection is an important branch of image processing and computer vision, which has become a hot research issue in recent years. Accurate target detection in a video is the foundation of intelligent surveillance system. Since the background scenario is dynamic and even especially complicated when vehicles occlude, the target detection accuracy is declined. Therefore, based on the bounding box regression algorithm, this paper constructs adjacent punishment mechanism to make the bounding box clear off other objects. The proposal weak confidence suppression is leveraged for the robustness of the detector when occlusion happens. Experiments show that the proposed method outperforms traditional methods on three different datasets.
BibTeX
@inproceedings{wu2019research,
author = {Yongqi Wu and Zhichao Zhou and Lan Yao and Minghe Yu and Yongming Yan},
title = {{Research and Implementation of Anti-occlusion Algorithm for Vehicle Detection in Video Data}},
booktitle = {Wisa},
year = {2019},
doi = {10.1007/978-3-030-30952-7\_26},
}Loading related content...