CVSep 25, 2021

Vehicle Detection and Tracking From Surveillance Cameras in Urban Scenes

arXiv:2109.12414v17 citations
Originality Incremental advance
AI Analysis

This work addresses vehicle detection and tracking for traffic safety applications, but it is incremental as it builds on existing tracking-by-detection methods with added features.

The paper tackled challenges in multi-object tracking (MOT) for vehicles in urban scenes, such as long-term occlusions and fast motion, by extending an IOU-based tracker with re-identification features, resulting in outperforming the baseline on the UA-DETRAC benchmark while maintaining suitable processing speed for online use.

Detecting and tracking vehicles in urban scenes is a crucial step in many traffic-related applications as it helps to improve road user safety among other benefits. Various challenges remain unresolved in multi-object tracking (MOT) including target information description, long-term occlusions and fast motion. We propose a multi-vehicle detection and tracking system following the tracking-by-detection paradigm that tackles the previously mentioned challenges. Our MOT method extends an Intersection-over-Union (IOU)-based tracker with vehicle re-identification features. This allows us to utilize appearance information to better match objects after long occlusion phases and/or when object location is significantly shifted due to fast motion. We outperform our baseline MOT method on the UA-DETRAC benchmark while maintaining a total processing speed suitable for online use cases.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes