4.2 Article

A Real-Time Object Detector for Autonomous Vehicles Based on YOLOv4

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Review Engineering, Electrical & Electronic

Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques

Mazin Hnewa et al.

Summary: Advanced automotive active safety systems, especially autonomous vehicles, heavily rely on visual data for object classification and localization to ensure safe maneuvering. However, the performance of object detection methods can significantly degrade in challenging weather conditions, such as rainy weather, which has been an understudied area, particularly in the context of autonomous driving.

IEEE SIGNAL PROCESSING MAGAZINE (2021)

Article Engineering, Electrical & Electronic

YOLOv4-5D: An Effective and Efficient Object Detector for Autonomous Driving

Yingfeng Cai et al.

Summary: This article proposes a one-stage object detection framework based on YOLOv4, using CSPDarknet53 as the backbone network, to improve the accuracy and real-time performance of object detection through techniques such as deformable convolutions and feature fusion. Additionally, an optimized network pruning algorithm is introduced to address limited computational resources, resulting in a 31.3% increase in inference speed.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2021)