Object detection is a critical technology of environmental perception for autonomous driving vehicle. The Convolutional Neural Network has gradually become a powerful tool in the field of vehicle detection because of its powerful ability of feature extraction. In aiming to reach the balance between speed and accuracy of detection in complex traffic scenarios, this paper proposes an improved lightweight and high-performance vehicle-pedestrian detection algorithm based on the YOLOv4. Firstly, the backbone network CSPDarknet53 is replaced by MobileNetv2 to reduce the number of parameters and raise the capability of feature extraction. Secondly, the method of multi-scale feature fusion is used to realize the information interaction among different feature layers. Finally, a coordinate attention mechanism is added to focus on the region of interest in the image by way of weight adjustment. The experimental results show that this improved model has a great performance in vehicle-pedestrian detection in traffic scenarios. Experimental results on PASCAL VOC datasets show that the improved model's is 85.79% and speed is 35FPS, which has an increase of 4.31% and 16.7% compared to YOLOv4. Furthermore, the improved YOLOv4 model maintains a great balance between detection accuracy and speed on different datasets, indicating that it can be applied to vehicle-pedestrian detection in traffic scenarios.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9654999 | PMC |
| http://dx.doi.org/10.3390/s22218480 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Evaluating the safety impact of mid-block pedestrian signals (MPS).
Accid Anal Prev
February 2025
Department of Civil, Environmental and Construction Engineering, University of Central Florida, Orlando, FL 32816, USA. Electronic address:
Article Synopsis
- * Using advanced computer vision and a specific statistical model, the study categorized vehicle-pedestrian interactions into conflict levels and found that MPS significantly reduced moderate and serious conflicts.
- * Factors like vehicle speed and land-use mix were found to increase the risk of serious conflicts, but the presence of MPS helped mitigate these risks, showing its potential to enhance safety at mid-block crossings.
Investigating streetscape environmental characteristics associated with road traffic crashes using street view imagery and computer vision.
Accid Anal Prev
February 2025
Center of GeoInformatics for Public Security, School of Geography and Remote Sensing, Guangzhou University, Guangzhou 510006, China. Electronic address:
Examining the relationship between streetscape features and road traffic crashes is vital for enhancing roadway safety. Traditional field surveys are often inefficient and lack comprehensive spatial coverage. Leveraging street view images (SVIs) and deep learning techniques provides a cost-effective alternative for extracting streetscape features.
View Article and Find Full Text PDFSynchronous End-to-End Vehicle Pedestrian Detection Algorithm Based on Improved YOLOv8 in Complex Scenarios.
Sensors (Basel)
September 2024
Computer Engineering Department, Batangas State University, Batangas City 4200, Philippines.
In modern urban traffic, vehicles and pedestrians are fundamental elements in the study of traffic dynamics. Vehicle and pedestrian detection have significant practical value in fields like autonomous driving, traffic management, and public security. However, traditional detection methods struggle in complex environments due to challenges such as varying scales, target occlusion, and high computational costs, leading to lower detection accuracy and slower performance.
View Article and Find Full Text PDFInvestigating the influence of streetscape environmental characteristics on pedestrian crashes at intersections using street view images and explainable machine learning.
Accid Anal Prev
September 2024
Center of GeoInformatics for Public Security, School of Geography and Remote Sensing, Guangzhou University, Guangzhou, 510006, China. Electronic address:
Examining the relationship between streetscape features and road traffic accidents is pivotal for enhancing roadway safety. While previous studies have primarily focused on the influence of street design characteristics, sociodemographic features, and land use features on crash occurrence, the impact of streetscape features on pedestrian crashes has not been thoroughly investigated. Furthermore, while machine learning models demonstrate high accuracy in prediction and are increasingly utilized in traffic safety research, understanding the prediction results poses challenges.
View Article and Find Full Text PDFRevisiting the hybrid approach of anomaly detection and extreme value theory for estimating pedestrian crashes using traffic conflicts obtained from artificial intelligence-based video analytics.
Accid Anal Prev
May 2024
Queensland University of Technology, School of Civil & Environment Engineering, Faculty of Engineering, Brisbane 4001, Australia. Electronic address:
Article Synopsis
- Pedestrians are at a higher risk of severe injuries in traffic, making it crucial to assess crash risks proactively.
- Recent studies using extreme value theory for crash risk assessment faced accuracy issues due to small sample sizes and poor selection of traffic conflict extremes.
- This study developed hybrid models using machine learning techniques to identify extreme vehicle-pedestrian conflicts, resulting in more accurate crash estimates compared to traditional models.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!