Deep-Learning-Based Detection of Obstacles in Transit on Trams
Deep-Learning-Based Detection of Obstacles in Transit on Trams
- New search for: Li, Yiming
- New search for: Cai, Guoqiang
- New search for: Wang, Wuhong
- New search for: Baumann, Martin
- New search for: Jiang, Xiaobei
- New search for: Li, Yiming
- New search for: Cai, Guoqiang
Due to the pervasive employment of trams, the measurements to keep the transit of trams safe are necessary and emergent. In this sense, we put forward a Neural Network based on Convolutional Neural Network, in which we made some modifications to make it more flexible. Such as passthrough layer to ensure some small objects detectable, anchor boxes to ensure a high-speed detection, and batch-normalization layers to make the network be malleable for objects with different distributions. With this network, we can efficiently detect possible obstacles, such as pedestrians, cars and some other objections that may endanger the trams. We test the network among several databases with 5000 samples, and the average accuracy rate is 94.12%, the average detecting speed is 30 FPS, the smallest detectable object’s size is 20 × 20 pixels, these all show remarkable result.
Document information
Deep-Learning-Based Detection of Obstacles in Transit on Trams
Lect. Notes Electrical Eng.
2020-03-24
13 pages
Article/Chapter (Book)
Electronic Resource
English
Similar titles
Deep-Learning-Based Detection of Obstacles in Transit on Trams
| British Library Conference Proceedings | 2020
Deep-Learning-Based Detection of Obstacles in Transit on Trams
| TIBKAT | 2020
| Online Contents | 1996
Analysis of personal rapid transit mixed with buses and trams
| Automotive engineering | 1994