CenterLoc3D: Monocular 3D Vehicle Localization Network for Roadside Surveillance Cameras
Tang Xinyao, Wang Wei, Song Huansheng, Zhao Chunhui

TL;DR
CenterLoc3D is a novel monocular 3D vehicle localization network for roadside cameras that directly predicts vehicle positions and dimensions, improving accuracy and efficiency without relying on 2D detectors.
Contribution
This paper introduces the first 3D vehicle localization method for roadside monocular cameras, with a new network, a weighted-fusion module, and a dedicated benchmark dataset.
Findings
Achieves high accuracy in 3D vehicle localization
Operates in real-time for practical deployment
Provides a new benchmark dataset and evaluation tools
Abstract
Monocular 3D vehicle localization is an important task in Intelligent Transportation System (ITS) and Cooperative Vehicle Infrastructure System (CVIS), which is usually achieved by monocular 3D vehicle detection. However, depth information cannot be obtained directly by monocular cameras due to the inherent imaging mechanism, resulting in more challenging monocular 3D tasks. Most of the current monocular 3D vehicle detection methods leverage 2D detectors and additional geometric modules, which reduces the efficiency. In this paper, we propose a 3D vehicle localization network CenterLoc3D for roadside monocular cameras, which directly predicts centroid and eight vertexes in image space, and the dimension of 3D bounding boxes without 2D detectors. To improve the precision of 3D vehicle localization, we propose a weighted-fusion module and a loss with spatial constraints embedded in…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Video Surveillance and Tracking Methods · Vehicle License Plate Recognition
