当前位置: X-MOL 学术Int. J. Circ. Theory Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Vehicle video surveillance system based on image fusion and parallel computing
International Journal of Circuit Theory and Applications ( IF 2.3 ) Pub Date : 2020-12-02 , DOI: 10.1002/cta.2907
Shan Liu 1 , Chengang Lyu 1 , Haotian Gong 1
Affiliation  

Autonomous driving has gradually moved towards practical applications in recent years. It is particularly critical to provide reliable real‐time environmental information for autonomous driving systems. At present, vehicle video surveillance systems based on multi‐source video and target detection algorithms can effectively solve these problems. However, the previous vehicle video surveillance systems are often unable to balance the surveillance effect and the surveillance frame rate. Therefore, we will introduce a vehicle video surveillance system based on parallel computing and computer vision in this article. First, multiple fisheye cameras are used to collect surround‐view environmental information. Second, we will use a low‐light camera, infrared thermal imager, and millimeter‐wave radar to provide forward‐view environmental information at night. Correspondingly, we designed the surround‐view image fusion algorithm and the forward‐view image fusion algorithm based on parallel computing. At last, a monocular camera and detection algorithms are used to provide forward‐view detection results. In a word, this vehicle video surveillance system will benefit the practical application of autonomous driving.

中文翻译:

基于图像融合和并行计算的车辆视频监控系统

近年来,自动驾驶已逐渐走向实际应用。为自动驾驶系统提供可靠的实时环境信息尤为重要。目前,基于多源视频和目标检测算法的车辆视频监控系统可以有效地解决这些问题。然而,先前的车辆视频监视系统通常不能平衡监视效果和监视帧率。因此,本文将介绍基于并行计算和计算机视觉的车辆视频监控系统。首先,使用多个鱼眼摄像机收集环视环境信息。其次,我们将使用低照度相机,红外热像仪,和毫米波雷达在夜间提供前瞻性的环境信息。相应地,我们基于并行计算设计了环视图像融合算法和前视图像融合算法。最后,使用单眼相机和检测算法来提供前视检测结果。总之,该车载视频监控系统将有利于自动驾驶的实际应用。
更新日期:2020-12-02
down
wechat
bug