☆ 4.6 Article

Vehicle target detection method based on improved YOLO V3 network model

PEERJ COMPUTER SCIENCE (2023)

Real-time vehicle target detection in inclement weather conditions based on YOLOv4

Rui Wang et al.

Summary: This study investigated the You Only Look Once (YOLO) algorithm and proposed an enhanced YOLOv4 for real-time target detection in inclement weather conditions. The algorithm uses the Anchor-free approach to tackle the problem of YOLO preset anchor frame and poor fit. It better adapts to the detected target size, making it suitable for multi-scale target identification. The experimental results showed that the proposed method achieved a higher mean average precision and enhanced inference speed compared to the original YOLOv4, indicating its practical implications in inclement weather conditions.

FRONTIERS IN NEUROROBOTICS (2023)

添加到收藏夹

Article Environmental Sciences

Street mapping, object detection and traffic load assessment from SVIs and field data using YOLOv3, machine learning and GIS

Hasan Raja Naqvi et al.

Summary: Street View Imageries (SVIs) provide street mapping, extraction, and examination from a human perspective to aid navigation and understanding of real-time loads on streets. This study used Google Street View Application (GSVA) to map 82 streets in an unplanned residential area in New Delhi and achieved accurate object detection and classification using the YOLOv3 model. The analysis showed a satisfactory association between humans, motorcycles, cars/auto rickshaws, and street width during the afternoon.

GEOCARTO INTERNATIONAL (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence