| Presentation | 2018-02-20 Detection of outdoor cables from point-cloud measured by MMS Hitoshi Niigaki, Ken Tsutsuguchi, Tetsuya Kinebuchi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Research results on detecting details of outdoor structures using point clouds measured by Mobile Map-ping Systems have been reported in recent years. The reports show that unvarying statistics about position andorientation, obtained by using normal information, have been used as effective feature quantities for identifying 3Dobjects. However, since many such structures have elongated (“swept”) shapes, it is often difficult to extract thenormal information stably. In urban areas, the scale for extracting features often increases due to the effects ofneighboring structures. In such cases, features extracted from point clouds of other structures get mixed together. This makes it difficult to obtain features effective for identification. We found in our work that the amount of statis-tics in the extrusion direction effectively enables swept shapes to be identified with high accuracy, even when thereare multiple adjacent objects. We also found that the identification accuracy improves by using feature quantitiesextracted explicitly from the region of interest and the surrounding regions. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | point-cloud / MMS / 3D feature / 3D object / cross section / clustering |
| Paper # | PRMU2017-159,CNR2017-37 |
| Date of Issue | 2018-02-12 (PRMU, CNR) |
| Conference Information | |
| Committee | PRMU / CNR |
|---|---|
| Conference Date | 2018/2/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Tetsuo Ono(Hokkaido Univ.) |
| Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Masayuki Kanbara(NAIST) / Kazunori Takashio(Keio Univ.) |
| Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Masayuki Kanbara(Hokkaido Univ.) / Kazunori Takashio(Panasonic) |
| Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Wataru Mito(SECOM) / Yuka Kobayashi(Toshiba) / Tatsuya Ishihara(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Cloud Network Robotics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Detection of outdoor cables from point-cloud measured by MMS |
| Sub Title (in English) | Classification method of elongated object using histogram feature based on multiple geometric directions(MGPFH) |
| Keyword(1) | point-cloud |
| Keyword(2) | MMS |
| Keyword(3) | 3D feature |
| Keyword(4) | 3D object |
| Keyword(5) | cross section |
| Keyword(6) | clustering |
| 1st Author's Name | Hitoshi Niigaki |
| 1st Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 2nd Author's Name | Ken Tsutsuguchi |
| 2nd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| 3rd Author's Name | Tetsuya Kinebuchi |
| 3rd Author's Affiliation | Nippon Telegraph and Telephone Corporation(NTT) |
| Date | 2018-02-20 |
| Paper # | PRMU2017-159,CNR2017-37 |
| Volume (vol) | vol.117 |
| Number (no) | PRMU-442,CNR-443 |
| Page | pp.pp.83-87(PRMU), pp.83-87(CNR), |
| #Pages | 5 |
| Date of Issue | 2018-02-12 (PRMU, CNR) |