Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2022, 5(4); doi: 10.25236/AJCIS.2022.050401.

Intelligent detection system of community electric vehicle based on visual deep learning


Changle Wang1, Pei Yu1, Guochen Zhang1

Corresponding Author:
Pei Yu

1China Fire and Rescue Institute, Beijing, 102202, China


At present, the number of electric bicycles in China is still increasing rapidly, with the risk of fire still exceeding 300 million. This paper designs an electric vehicle monitoring system based on deep learning. The system uses the image real-time transmission system and deep learning platform to identify and detect the relevant behaviors of electric vehicles in real time. Infrared cameras are set in the areas with high fire risk such as the centralized parking point and charging point of electric vehicles. The captured infrared image is based on the smoke removal processing method of histogram equalization to improve the contrast of the image. It is convenient for the upper computer to identify the high-temperature point, find the fire point in time, and nip the danger in the bud.


electric vehicle, graphics processing, deep learning

Cite This Paper

Changle Wang, Pei Yu, Guochen Zhang. Intelligent detection system of community electric vehicle based on visual deep learning. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 4: 1-3. https://doi.org/10.25236/AJCIS.2022.050401.


[1] Meng Huilei. Research on pedestrian and electric motorcycle target detection [D]. Chang'an University, 2019.

[2] Xie Yongkang. Deep learning development platform and application [J]. Artificial intelligence, 2020 (03): 43-53 DOI:10.16453/j.cnki. issn 2096-5036.2020.03.005.

[3] Huang Qiong, Si Ying, Wang Haoyu, Ding Zhaoyun Research on high temperature point location and tracking algorithm based on infrared image [J]. Fire science and technology, 2021,40 (09): 1276-1280

[4] Li Yang, Chen Zhihua, Sheng bin Image joint segmentation algorithm based on central consistency sensitive histogram [J]. Computer science, 2018,45 (08): 28-35

[5] Cao Yongmei. Research on image defogging and enhancement algorithm based on Retinex theory [D]. Jiangsu University of Science and Technology, 2014