| Presentation | 2022-12-05 Improvement of Visual Odometry Based on Suitable and Restricted Feature Point Extraction Junfeng Xue, Miho Adachi, Ryusuke Miyamoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Accurate localization is indispensable for autonomous moving. When a camera is an external sensor, visual odometry can be used for this purpose. The accuracy can be improved if IMU is available: VINS-Mono is a famous scheme. In actual scenes, the accuracy of visual odometry may become worse according to translational or rotational motions of a robot and outliers of feature point matching caused by dynamic objects in the view. This paper attempts to improve the accuracy of visual odometry by more suitable feature extraction schemes for feature points and outlier elimination based on semantic information. Experimental results obtained at actual environment showed that other schemes for feature extraction is effective and outlier elimination also work well only when many dynamic objects exist in the view. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Semantic segmentation / visual odometry / feature point matching |
| Paper # | SIS2022-33 |
| Date of Issue | 2022-11-28 (SIS) |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2022/12/5(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) |
| Vice Chair | Naoto Sasaoka(Tottori Univ.) / Hakaru Tamukoh(Kyushu Inst. of Tech.) |
| Secretary | Naoto Sasaoka(NTT) / Hakaru Tamukoh(Kansai Univ.) |
| Assistant | Yoshiaki Makabe(Kanagawa Inst. of Tech.) / Yosuke Sugiura(Saitama Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Improvement of Visual Odometry Based on Suitable and Restricted Feature Point Extraction |
| Sub Title (in English) | |
| Keyword(1) | Semantic segmentation |
| Keyword(2) | visual odometry |
| Keyword(3) | feature point matching |
| 1st Author's Name | Junfeng Xue |
| 1st Author's Affiliation | Meiji University(Meiji Univ.) |
| 2nd Author's Name | Miho Adachi |
| 2nd Author's Affiliation | Meiji University(Meiji Univ.) |
| 3rd Author's Name | Ryusuke Miyamoto |
| 3rd Author's Affiliation | Meiji University(Meiji Univ.) |
| Date | 2022-12-05 |
| Paper # | SIS2022-33 |
| Volume (vol) | vol.122 |
| Number (no) | SIS-293 |
| Page | pp.pp.56-61(SIS), |
| #Pages | 6 |
| Date of Issue | 2022-11-28 (SIS) |