| Project/Area Number |
17K00446
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Web informatics, Service informatics
|
|---|
| Research Institution | Advanced Telecommunications Research Institute International |
|---|
Principal Investigator |
Tamai Morihiko 株式会社国際電気通信基礎技術研究所, 適応コミュニケーション研究所, 主任研究員 (90523077)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
|
|---|
| Keywords | 車両センシング / DTN / 機械学習 / 走行環境認識 / 分散コンピューティング |
|---|
| Outline of Final Research Achievements |
In this research, we explore the system that collects driving videos from a large number of sensing vehicles, where collected videos are used to continuously update machine learning-based models for driving environments recognition. In order to deploy such a system, it is important to minimize the load on the cellular network as much as possible. We propose a method that detects duplicates of the videos recorded at the same driving environments by multiple sensing vehicles, to reduce the total upload data volume and to collect videos from the various driving environments.
|
| Academic Significance and Societal Importance of the Research Achievements |
機械学習に基づく走行環境認識を行うシステムにおいて，走行環境の多様性に応じてモデルを継続的に更新するためには，多数の車両から走行中に撮影されたビデオを収集しモデルの更新に役立てることが有効である．本研究では，複数の車両により同一の走行環境上で撮影されたビデオの重複を削減する方式を提案し，このような動画収集システムを運用する上で消費されるセルラ通信網への負荷の軽減を実現する．
|
