TY  - JOUR
PY  - 2024//
TI  - A Siamese neural network-based method to recognize the abnormal driving behaviors for autonomous vehicles
JO  - Lecture notes in electrical engineering
A1  - Zhang, Xinya
A1  - He, Shanglu
A1  - Fan, Zhengwen
A1  - Liu, Yingshun
A1  - Qi, Yong
A1  - Qu, Yi
A1  - Gu, Mancang
A1  - Niu, Yifeng
A1  - Fu, Wenxing
SP  - 267
EP  - 276
VL  - 1177
IS  - 
N2  - Proceedings of 3rd 2023 International Conference on Autonomous Unmanned Systems (3rd ICAUS 2023)    It is such a challenge to ensure a safety driving when the self-driving vehicles are in a mixed traffic environment with human-driven vehicles. There are some abnormal driving behaviors, which could lead to accidents, financial losses, and even casualties. Therefore, the identification of abnormal driving behaviors is vital for the safety of autonomous vehicles, which could help to avoid the potential dangers. Considering that the abnormal behaviors take a small part of driving data, this paper proposed a Siamese neural network recognition model, which could be built up with small datasets. In detail, the vehicle trajectory data were preprocessed and used to train and validate the proposed method. Experimental results indicated that the Siamese neural network-based method could effectively identify abnormal driving behaviors with an accuracy rate of 88.0%. To some extent, the proposed method could assist the autonomous vehicles to recognize the abnormal driving behaviors successfully with a small sample size of driving data.<p />  <p>Language: en</p>
LA  - en
SN  - 1876-1100
UR  - http://dx.doi.org/10.1007/978-981-97-1103-1_24
ID  - ref1
ER  -