This paper presents the learned techniques during the Video Analysis Module of the Master in Computer Vision from the Universitat Aut\`onoma de Barcelona, used to solve the third track of the AI-City Challenge. This challenge aims to track vehicles across multiple cameras placed in multiple intersections spread out over a city. The methodology followed focuses first in solving multi-tracking in a single camera and then extending it to multiple cameras. The qualitative results of the implemented techniques are presented using standard metrics for video analysis such as mAP for object detection and IDF1 for tracking. The source code is publicly available at: https://github.com/mcv-m6-video/mcv-m6-2021-team4.
翻译:本文介绍了巴塞罗那Aut ⁇ onoma大学计算机视觉硕士视频分析单元期间的学习技术,该单元用于解决AI-City挑战的第三个轨道,旨在跟踪放置在一个城市多个交叉点的多摄像头中的车辆,其方法首先侧重于用单一相机解决多轨问题,然后推广到多个相机,所应用技术的质量结果采用用于视频分析的标准衡量标准,例如用于物体探测的MAP和用于跟踪的UNFD1,来源代码公布在https://github.com/mcv-m6-vical/mcv-m6-2021-team4上。