Depth Camera-Based Human Detection Using Yolov5

DOI

10.2991/978-94-6463-620-8_12How to use a DOI?

Keywords

Deep learning; YOLOv5n; Mean average precision (MAP); Human Detection

Abstract

This research develops a depth camera-based human detection system using the YOLOv5n algorithm. The system is designed to address the challenges of object detection in various environmental and lighting conditions, as well as in real-time applications with hardware constraints. Testing results show the system achieves high accuracy in detecting distances and angles during the day, maintaining a combined error rate of approximately 2.439%. However, the system’s performance declined at night with the combined error rate increasing to about 10.042%, indicating vulnerability to low lighting. Evaluation using the mean Average Precision (mAP) metric showed the model achieved a mAP value of 0.99 at an IoU threshold of 0.5 and an average mAP value of 0.9 at various thresholds from 0.5 to 0.95, indicating a high level of accuracy in object detection and classification. The integration of depth information from the RealSense camera and the real-time detection capability of YOLOv5n proves to be highly effective in human detection.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Wati P. S. Simanjuntak
AU  - Anugerah Wibisana
PY  - 2024
DA  - 2024/12/25
TI  - Depth Camera-Based Human Detection Using Yolov5
BT  - Proceedings of the  7th International Conference on Applied Engineering (ICAE 2024)
PB  - Atlantis Press
SP  - 150
EP  - 162
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-620-8_12
DO  - 10.2991/978-94-6463-620-8_12
ID  - Simanjuntak2024
ER  -