Road Pedestrian Detection Based on Deep Learning

Siyu Jia

doi:10.47297/taposatWSP2633-456904.20230402

PDF
导出
分享
收藏
专辑

Road Pedestrian Detection Based on Deep Learning

4卷第2期

浏览量: 0 Downloads: 0

Road Pedestrian Detection Based on Deep Learning
Road Pedestrian Detection Based on Deep Learning
School of Information and Intelligent Engineering, Tianjin Ren'ai University,Tianjin,P. R. China,301636
2023年4卷第2期页码：24-30
纸质出版日期： 2023 ，
DOI：10.47297/taposatWSP2633-456904.20230402

Full txt

(2023). Road Pedestrian Detection Based on Deep Learning. 科技理论与实践（英文版）, 4(2), 24-30.

Siyu Jia. (2023). Road Pedestrian Detection Based on Deep Learning. Theory and Practice of Science and Technology, 4(2), 24-30.
(2023). Road Pedestrian Detection Based on Deep Learning. 科技理论与实践（英文版）, 4(2), 24-30. DOI： 10.47297/taposatWSP2633-456904.20230402.

Siyu Jia. (2023). Road Pedestrian Detection Based on Deep Learning. Theory and Practice of Science and Technology, 4(2), 24-30. DOI： 10.47297/taposatWSP2633-456904.20230402.

摘要

Abstract

Aiming at the problem that deep learning-based road pedestrian detection algorithms are difficult to be deployed in low-performance devices

this paper utilizes the deep learning-based target detection algorithm YOLO V5s

optimizes and updates the network model

changes the preprocessing method of the input side

and adjusts the model structure of the YOLO V5 algorithm

and proposes an improved lightweight pedestrian detection model algorithm

YOLO V5s-LW. The final results show that the YOLO V5s-LW model has a mAP of 95.1%

which is 2.3% lower than that of the YOLO V5s model

but it can reduce the difficulty of deploying devices for pedestrian detection in road environments while maintaining a good detection rate.

关键词

Keywords

Target detectionPedestrian DetectionDeep learningYOLO model

references

Cheng Wang, Yuan-sheng Liu, Fei-xiang Chang & Ming Lu (2022) Pedestrian detection based on YOLOv3 multimodal data fusion, Systems Science & Control Engineering, 10, pp. 832-45.[2] Liu Lisang,Ke Chengyang,Lin He & Xu Hui.(2022).Research on Pedestrian Detection Algorithm Based on MobileNet-YoLo. Computational Intelligence and Neuroscience. Volume 2022 , pp. 12.[3] Zhang Xue & Chang Li.(2022).Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism. American Journal of Electrical and Computer Engineering(1). Volume 6, Issue 1, pp. 47-53.[4] Panigrahi Sweta & Raju U. S. N..(2022).InceptionDepth-wiseYOLOv2: improved implementation of YOLO framework for pedestrian detection. International Journal of Multimedia Information Retrieval(3). Int J Multimed Info Retr 11, pp. 409–30.[5] Ke Xiao,Lin Xinru & Qin Liyun.(2021).Lightweight convolutional neural network-based pedestrian detection and re-identification in multiple scenarios. Machine Vision and Applications (2). Machine Vision and Applications 32, pp. 46.

文章被引用时，请邮件提醒。

Submit

Stock Price Forecasting Based on the MDT-CNN-CBAM-GRU Model: An Empirical Study

A Review of Medical Imaging in Breast Cancer Detection

Empirical Advancements in Convolutional Neural Networks for Image Recognition: A Comparative Analysis

Diagnosis of Flower Diseases Based on Deep-learning

A Novel DL Approach to PE Malware Detection: Exploring Glove Vectorization, MCC_RCNN and Feature Fusion

Related Author

No data

Related Institution

Business School, University of New South Wales

Xi’an Tieyi Lugang High School