Research and development of plateau portable landslide detection equipment based on Jetson Nano

Authors

  • Jianyu Xu
  • Siwei Cheng
  • Libin Su
  • Yonggang Guo

DOI:

https://doi.org/10.62051/eqrtb452

Keywords:

Machine Learning; Convenience Devices; Jetson Nano; Landslide Detection.

Abstract

In response to the problems that landslides occur in remote locations, are difficult to monitor and landslide target detection is not easily deployed at the embedded end, a landslide detection device based on the Jetson nano edge device is developed. The technology detects information of landslide feature objects through YOLOV5m technology, and is able to output landslide area information as well as geographic location information while accurately detecting landslide targets. A dataset of 25,000 landslide images is used to build the data set, and the training and validation sets are divided 9:1. A deep learning network is used to extract landslide features and build a landslide target detection model. After that, the train.py file is placed on the cloud server for training, and the best.pt file is migrated to Jetson Nano and tested on the embedded platform. The experimental results show that the average running time of single frame of YOLOV5m model in the embedded device is 100ms, and the detection accuracy can be maintained above 80%, which can achieve accurate detection and information acquisition of landslide target on Jetson Nano device, and lay the foundation for the development of edge device module for landslide detection later.

Downloads

Download data is not yet available.

References

Han Shunshun. Evaluation of geological disaster susceptibility in southeast Tibet [J]. Journal of Mountain Studies, 2021,39 (05): 700.

Li Hongfei, Hu Manhong. Research on real-time intelligent obstacle avoidance system of picking robot- -based on embedded ARM [J]. Agricultural Mechanization Research, 2021,43 (04): 107-111

Sun Deliang. Research on landslide prone zoning and rainfall-induced landslide [D]. East China Normal University, 2019.

Lin Bo Kun, Li Denghua, Ding Yong, Li Yuanmeng. Research on nighttime uninterrupted monitoring technology of landslide body based on machine vision [J]. Laser magazine: 1-6.

Wang Qingguo, Zhao Hai, Li Jianping. Landslide monitoring by combining ground laser point cloud and aerial image [J]. Surveying and mapping Bulletin, 2019 (04): 99-102.

REN S, HE K GIRSHICKR, et al.Faster R-CNN:towards real time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017, 39(6):1137-1149

lenn Jocher.YOLOv5:The Leader in Realtime Object Detection[EB/OL].ar Xiv:1804.02767vl.2018

Zhang Guolong, Wang Tonghe, Ji Siyuan. Application of three-dimensional laser scanning measurement technology in the overall monitoring of landslide [J]. Engineering Survey, 2017,45 (07): 54-58.

Long Shike, Jiang Qihang, Bao Yunan, Wang Jianqi. Design based on the Jetson Nano vision application platform [J]. Sensors and Microsystems, 2022,41 (09): 99-101 + 108.

Lian Xiaofeng, Dou Lihua, Chen Jie. Research on the calibration method of omni-directional camera [J]. Optical Technology, 2008 (01): 75-78.

Tang Yi, Chen Xi, Liu Xianglei. Application of OpenCV's camera calibration in high-speed cameras [J]. Beijing Surveying and Mapping, 2018,32 (05): 578-582

Huang Jilan, Lou Xinyuan. Testing practice of monocular camera calibration based on OpenCV [J]. Railway computer application, 2009,18 (04): 47-49.

Wang Tan, Wang Leilei, Zhang Weiguo, Duan Xiaotao, Wang Wanli. Infrared target system based on Zhang Zhengyou's calibration method [J]. Optical Precision Engineering, 2019,27 (08): 1828-1835.

Zhang Z Y.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 1:201-207.

HRUSNA C S, VEENA M B, KESHINHA R G D.OpenCV Implementation of Grid-based Vertical Safe Landing for UAV using YOLOv5[J].International Journal of Advanced Coter Science and Applications (IJACSA), 2022, 13(9):325-334.

XiangYong, Wang Zhangrui, Xu Fanghua, Zhang Linxin. GPS navigation data extraction and coordinate transformation [J]. Instrumentation User, 2009,16 (04): 70-71.

Zhen Ran, Liu Ying, Meng Fanhua, Zhu Jintai. Lightweight target detection algorithm based on YOLOv5 [J / OL]. Radio engineering: 1-9 [2023-04-04].

DENG S, ZHAO H, FANG W, et al.Edge intelligence: the confluence of edge computing and artificial intelligence[J]. IEEE Internet of Things Journal, 2020, 7( 8) : 7457-7469.

Downloads

Published

20-06-2024

How to Cite

“Research and development of plateau portable landslide detection equipment based on Jetson Nano” (2024) Transactions on Computer Science and Intelligent Systems Research, 4, pp. 162–171. doi:10.62051/eqrtb452.

Similar Articles

1-10 of 39

You may also start an advanced similarity search for this article.