Details

Autor(en) / Beteiligte

• Ding, Cheng
• Bao, Jianmin
• Mi, Guanyu
• Kuai, Xiao
• Kang, YiNing

Titel

Research on Vehicle Distance Estimation Model based on Deep Learning

Ist Teil von

• 2022 41st Chinese Control Conference (CCC), 2022, p.7169-7173

Ort / Verlag

Technical Committee on Control Theory, Chinese Association of Automation

Erscheinungsjahr

2022

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• With the continuous development of artificial intelligence technology, intelligent vehicle technology in driverless scenarios has become an important direction for a new round of technological change. As an important part of the driverless car, the vehicle distance estimation module is of great significance for improving the intelligent car in the driverless environment, and the reliability and safety of the system are of great significance. However, in the field of unmanned driving, traditional vehicle distance estimation algorithms have the problems of poor real-time performance and insufficient accuracy, and cannot achieve end-to-end distance estimation tasks. Aiming at the above problems, this paper proposes a deep learning-based vehicle distance estimation model. The distance estimation module is added to the traditional mainstream deep learning network so that the distance estimation task and the original classification and detection task can achieve feature fusion, and multi-task joint learning is performed to realize the end-to-end distance estimation task. The simulation results show that the model proposed in this paper can effectively make up for the lack of real-time performance of traditional distance estimation methods based on machine learning, and achieve higher distance estimation accuracy and better real-time performance.