A Lightweight Fine-Grained VRU Detection Model for Roadside Units

Sie sind hier: Homepage > Suche

A Lightweight Fine-Grained VRU Detection Model for Roadside Units

Shi, Jian / Sun, Dongxian / Zhang, Haodong / Tan, Haiqiu / Hu, Yaoguang / Wang, Wuhong

Object detection of vulnerable road users (VRU) under low computing resources of roadside units is one of the key technologies to achieve vehicle-infrastructure cooperative perception. In this paper, a lightweight fine-grained VRU detection model is proposed. Analyzing the existing complex traffic environment, the traditional definition of VRU is no longer applicable. Our work includes two parts: One is to redefine the fine-grained VRU and construct a new dataset. This task makes the perceptual information obtained by detection more comprehensive and accurate. Another is to optimize YOLOv4 by using the channel pruning method in model compression. The optimized model is 60% lighter than the original model. Under the limitation of low computing resources at the roadside units, the real-time detection of VRU is realized while ensuring a certain detection accuracy.

Zugriff

Zugriff prüfen

Verfügbarkeit in meiner Bibliothek prüfen

Bestellung bei Subito €

Exportieren, teilen und zitieren

Dokumentinformationen

Titel :

A Lightweight Fine-Grained VRU Detection Model for Roadside Units

Weitere Titelangaben:

Lect. Notes Electrical Eng.

Beteiligte:

Wang, Wuhong (Herausgeber:in) / Wu, Jianping (Herausgeber:in) / Jiang, Xiaobei (Herausgeber:in) / Li, Ruimin (Herausgeber:in) / Zhang, Haodong (Herausgeber:in) / Shi, Jian (Autor:in) / Sun, Dongxian (Autor:in) / Zhang, Haodong (Autor:in) / Tan, Haiqiu (Autor:in) / Hu, Yaoguang (Autor:in)

Kongress:

International Conference on Green Intelligent Transportation System and Safety ; 2021 November 19, 2021 - November 21, 2021

Erschienen in:

Green Transportation and Low Carbon Mobility Safety ; Kapitel : 21 ; 301-309

Lecture Notes in Electrical Engineering ; 944

Erscheinungsdatum :

2022-10-28

Format / Umfang :

9 pages

ISBN :

978-981-19-5615-7 , 978-981-19-5614-0

ISSN :