| Presentation | 2018-09-21 Deployment Friendly Crack Detection via Convolutional Neural Network Yuki Inoue, Shunsuke Ota, Hiroto Nagayoshi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Damage inspection, the first step in structural maintenance, is predominantly done manually today. Thus the cost of structural maintenance will be reduced greatly if this process is automated. In this paper, we propose a model that automatically detects surface cracks at a pixel level. Unlike in previous literatures, we heavily focused on the field deployability, such as reducing the dataset annotation cost and shortening the inference time. Experimental results show that the proposed model surpasses the state of the art in terms of accuracy. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | crack detection / convolutional neural network / multiple instance learning / deep learning |
| Paper # | PRMU2018-64,IBISML2018-41 |
| Date of Issue | 2018-09-13 (PRMU, IBISML) |
| Conference Information | |
| Committee | PRMU / IBISML / IPSJ-CVIM |
|---|---|
| Conference Date | 2018/9/20(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Hisashi Kashima(Kyoto Univ.) |
| Vice Chair | Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) / Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST) |
| Assistant | Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Deployment Friendly Crack Detection via Convolutional Neural Network |
| Sub Title (in English) | |
| Keyword(1) | crack detection |
| Keyword(2) | convolutional neural network |
| Keyword(3) | multiple instance learning |
| Keyword(4) | deep learning |
| 1st Author's Name | Yuki Inoue |
| 1st Author's Affiliation | Hitachi Ltd.(Hitachi) |
| 2nd Author's Name | Shunsuke Ota |
| 2nd Author's Affiliation | Hitachi Ltd.(Hitachi) |
| 3rd Author's Name | Hiroto Nagayoshi |
| 3rd Author's Affiliation | Hitachi Ltd.(Hitachi) |
| Date | 2018-09-21 |
| Paper # | PRMU2018-64,IBISML2018-41 |
| Volume (vol) | vol.118 |
| Number (no) | PRMU-219,IBISML-220 |
| Page | pp.pp.201-206(PRMU), pp.201-206(IBISML), |
| #Pages | 6 |
| Date of Issue | 2018-09-13 (PRMU, IBISML) |