| Presentation | 2019-12-19 Efficient Object Detection for Railway Crossing Combining Image Classification and Object Detection Kaisei Shimura, Yoichi Tomioka, Qiangfu Zhao, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this research, we aim to develop a system to support drivers to prevent accidents when driving an mobility scooter. As the first step of driving support, in this paper, we proposes a method for efficiently detecting an object which exists close to a railway crossing normally. In this method, an image classification is performed before object detection to detect railway crossing scene. By applying object detection only to a crossing scene, the workload and false detection for object detection are reduced.In the experiments, the precision and F-score for each class was improved by at most 0.224 and 0.234, respectively. Moreover, we achieved 1.7 to 2.0 times faster execution for scenes in which a railway crossing does not exist on desktop PC, Raspberry Pi 3 model B equipped with Neural Compute Stick 2. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | railway crossing / deep learning / image classification / object detection |
| Paper # | PRMU2019-52 |
| Date of Issue | 2019-12-12 (PRMU) |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2019/12/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Yoichi Sato(Univ. of Tokyo) |
| Vice Chair | Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT) |
| Secretary | Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX) |
| Assistant | Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Efficient Object Detection for Railway Crossing Combining Image Classification and Object Detection |
| Sub Title (in English) | |
| Keyword(1) | railway crossing |
| Keyword(2) | deep learning |
| Keyword(3) | image classification |
| Keyword(4) | object detection |
| 1st Author's Name | Kaisei Shimura |
| 1st Author's Affiliation | University of Aizu(UoA) |
| 2nd Author's Name | Yoichi Tomioka |
| 2nd Author's Affiliation | University of Aizu(UoA) |
| 3rd Author's Name | Qiangfu Zhao |
| 3rd Author's Affiliation | University of Aizu(UoA) |
| Date | 2019-12-19 |
| Paper # | PRMU2019-52 |
| Volume (vol) | vol.119 |
| Number (no) | PRMU-347 |
| Page | pp.pp.35-39(PRMU), |
| #Pages | 5 |
| Date of Issue | 2019-12-12 (PRMU) |