Browse Publications Technical Papers 2022-01-7027

Data Fusion-Based Obstacle Detection for Rail Transit Scenarios 2022-01-7027

In order to solve the problem of obstacle detection for rail transit scenarios, a recognition method of obstacle based on data fusion is proposed. First, the image data, which is obtained through a telephoto camera and a wide-angle camera, is synchronized. Then, the artificial intelligence model for objects detection is applied to image data processing, where the distance measuring module is added to transform the recognition results into three-dimensional output with object distance. Finally, the output of the model is processed by data fusion and visualized. Taking tram as experimental background, the experimental results show that the method in this paper can effectively recognize objects in the front of tram, and can be used as a part of the rail transit automatic sensing system to ensure the safety of driving.


Subscribers can view annotate, and download all of SAE's content. Learn More »


Members save up to 16% off list price.
Login to see discount.
Special Offer: Download multiple Technical Papers each year? TechSelect is a cost-effective subscription option to select and download 12-100 full-text Technical Papers per year. Find more information here.