First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Spatiotemporal Agent Detection 2024

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Tengfei, Zhang, Heng, Li, Ruyang, Deng, Qi, Zhao, Yaqian, Li, Rengang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910678440214528
author Zhang, Tengfei
Zhang, Heng
Li, Ruyang
Deng, Qi
Zhao, Yaqian
Li, Rengang
author_facet Zhang, Tengfei
Zhang, Heng
Li, Ruyang
Deng, Qi
Zhao, Yaqian
Li, Rengang
contents This report presents our team's solutions for the Track 1 of the 2024 ECCV ROAD++ Challenge. The task of Track 1 is spatiotemporal agent detection, which aims to construct an "agent tube" for road agents in consecutive video frames. Our solutions focus on the challenges in this task, including extreme-size objects, low-light scenarios, class imbalance, and fine-grained classification. Firstly, the extreme-size object detection heads are introduced to improve the detection performance of large and small objects. Secondly, we design a dual-stream detection model with a low-light enhancement stream to improve the performance of spatiotemporal agent detection in low-light scenes, and the feature fusion module to integrate features from different branches. Subsequently, we develop a multi-branch detection framework to mitigate the issues of class imbalance and fine-grained classification, and we design a pre-training and fine-tuning approach to optimize the above multi-branch framework. Besides, we employ some common data augmentation techniques, and improve the loss function and upsampling operation. We rank first in the test set of Track 1 for the ROAD++ Challenge 2024, and achieve 30.82% average video-mAP.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23077
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Spatiotemporal Agent Detection 2024
Zhang, Tengfei
Zhang, Heng
Li, Ruyang
Deng, Qi
Zhao, Yaqian
Li, Rengang
Computer Vision and Pattern Recognition
This report presents our team's solutions for the Track 1 of the 2024 ECCV ROAD++ Challenge. The task of Track 1 is spatiotemporal agent detection, which aims to construct an "agent tube" for road agents in consecutive video frames. Our solutions focus on the challenges in this task, including extreme-size objects, low-light scenarios, class imbalance, and fine-grained classification. Firstly, the extreme-size object detection heads are introduced to improve the detection performance of large and small objects. Secondly, we design a dual-stream detection model with a low-light enhancement stream to improve the performance of spatiotemporal agent detection in low-light scenes, and the feature fusion module to integrate features from different branches. Subsequently, we develop a multi-branch detection framework to mitigate the issues of class imbalance and fine-grained classification, and we design a pre-training and fine-tuning approach to optimize the above multi-branch framework. Besides, we employ some common data augmentation techniques, and improve the loss function and upsampling operation. We rank first in the test set of Track 1 for the ROAD++ Challenge 2024, and achieve 30.82% average video-mAP.
title First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Spatiotemporal Agent Detection 2024
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.23077