| Presentation | 2021-03-03 Study of Environment Recognition and 3D Map Generation Using SegNet for Night Forest Monitoring Using an Environmental Monitoring Robot Takeo Kaneko, Junji Yamato, Hiroyuki Ishii, Jun Ohya, Atuo Takanishi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Towards the actualization of autonomous robots that monitor forests, around which various kinds of damages caused by wild animals frequently occur, this paper proposes a method for obtaining 3D maps based on labeled image segmentation results at night. The cameras mounted on the monitoring robot acquires IR (infrared) images and depth images. To the acquired images, CNN (Convolutional Neural Network) is performed so that the segmentation result of the IR image is obtained. Then, by registering the 3D point cloud obtained from the depth image to the segmentation result, a labeled 3D map is obtained. Experiments that evaluate the proposed method using IR images and depth images acquired in forests at night were conducted. It turns out that accurate segmentation results and labeled 3D maps are obtained. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep Learning / SegNet / Point Cloud / 3D Map / IR image / SLAM / OctoMap |
| Paper # | IMQ2020-29,IE2020-69,MVE2020-61 |
| Date of Issue | 2021-02-22 (IMQ, IE, MVE) |
| Conference Information | |
| Committee | MVE / IMQ / IE / CQ |
|---|---|
| Conference Date | 2021/3/1(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Masayuki Ihara(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Hideaki Kimata(NTT) / Hideyuki Shimonishi(NEC) |
| Vice Chair | Kiyoshi Kiyokawa(NAIST) / Mitsuru Maeda(Canon) / Kenya Uomori(Osaka Univ.) / Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.) |
| Secretary | Kiyoshi Kiyokawa(Oosaka Inst. of Tech.) / Mitsuru Maeda(NTT) / Kenya Uomori(Univ. of ToKyo) / Kazuya Kodama(Shizuoka Univ.) / Keita Takahashi(Sony Semiconductor Solutions) / Jun Okamoto(KDDI Research) / Takefumi Hiraguri(Nagoya Inst. of Tech.) |
| Assistant | Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Hiroaki Kudo(Nagoya Univ.) / Masaru Tsuchida(NTT) / Keita Hirai(Chiba Univ.) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) / Ryoichi Kataoka(KDDI Research) |
| Paper Information | |
| Registration To | Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Communication Quality |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Study of Environment Recognition and 3D Map Generation Using SegNet for Night Forest Monitoring Using an Environmental Monitoring Robot |
| Sub Title (in English) | |
| Keyword(1) | Deep Learning |
| Keyword(2) | SegNet |
| Keyword(3) | Point Cloud |
| Keyword(4) | 3D Map |
| Keyword(5) | IR image |
| Keyword(6) | SLAM |
| Keyword(7) | OctoMap |
| 1st Author's Name | Takeo Kaneko |
| 1st Author's Affiliation | Waseda University(WASEDA Univ.) |
| 2nd Author's Name | Junji Yamato |
| 2nd Author's Affiliation | Kogakuin University(Kogakuin Univ.) |
| 3rd Author's Name | Hiroyuki Ishii |
| 3rd Author's Affiliation | Waseda University(WASEDA Univ.) |
| 4th Author's Name | Jun Ohya |
| 4th Author's Affiliation | Waseda University(WASEDA Univ.) |
| 5th Author's Name | Atuo Takanishi |
| 5th Author's Affiliation | Waseda University(WASEDA Univ.) |
| Date | 2021-03-03 |
| Paper # | IMQ2020-29,IE2020-69,MVE2020-61 |
| Volume (vol) | vol.120 |
| Number (no) | IMQ-389,IE-390,MVE-391 |
| Page | pp.pp.91-96(IMQ), pp.91-96(IE), pp.91-96(MVE), |
| #Pages | 6 |
| Date of Issue | 2021-02-22 (IMQ, IE, MVE) |