Scholarlink

Traffic monitoring can be supported by stationary or dynamic camera systems. Whereas the analysis of stationary camera data has a long tradition, the analysis of dynamic sensors (recorded by Unmanned Aerial Systems (UAS) or dashcams in cars or trucks) has gained interest in the recent past. This paper proposes a labeling enhancement of a dashcam video repository and the evaluation of several recent deep learning algorithm (LSTM, Inception V3, VGG16, MobileNet V2, etc.) for classifying traffic accidents in dynamic camera systems. Based on fine-tuning methods and data preprocessing steps optimized results for the individual deep learning approaches could be achieved and an overall analysis is presented.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluation of Deep Learning Approaches for Prediction of Traffic Accidents in Dashcam Videos

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Nilesh Jayantibhai Solanki,
  • Mario Döller

摘要

Traffic monitoring can be supported by stationary or dynamic camera systems. Whereas the analysis of stationary camera data has a long tradition, the analysis of dynamic sensors (recorded by Unmanned Aerial Systems (UAS) or dashcams in cars or trucks) has gained interest in the recent past. This paper proposes a labeling enhancement of a dashcam video repository and the evaluation of several recent deep learning algorithm (LSTM, Inception V3, VGG16, MobileNet V2, etc.) for classifying traffic accidents in dynamic camera systems. Based on fine-tuning methods and data preprocessing steps optimized results for the individual deep learning approaches could be achieved and an overall analysis is presented.