| Project/Area Number |
17K12713
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Kanazawa University |
|---|
Principal Investigator |
Yoneda Keisuke 金沢大学, 新学術創成研究機構, 助教 (80643957)
|
|---|
| Project Period (FY) |
2017-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2017: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | 自動運転自動車 / 周辺環境認識 / 画像処理 / ITS / 機械学習 / 自動運転 / 高度道路交通システム（ITS） |
|---|
| Outline of Final Research Achievements |
Environmental perception using onboard sensor is an important role in urban automated driving. This study develops a traffic light detection system using a camera and a digital map. On urban roads where many traffic lights are placed, it is sometimes difficult to identify the specific traffic light in the image because multiple traffic lights are observed. Therefore, accurate correspondence with the traffic light on the digital map was realized by modeling the existence probability of the traffic light position observed in the image. Furthermore, an object tracking method was implemented for traffic lights in order to achieve stable recognition against changes in lighting conditions. The developed system was installed on the automated vehicle to verify the validity of the recognition ability in urban driving.
|
| Academic Significance and Societal Importance of the Research Achievements |
信号機の認識は状態が時間変化する道路特徴であるため，対象物を適切に特定しながらその状態変化を考慮して認識することが重要となる．本研究の取り組みにより，地図上の信号機を画像中に存在する信号機間の対応付けが実現され，自動運転車が次に通過する交差点の信号機など特定の信号機を抽出しやすくなる．現在の交通死亡事故において，交差点周辺の十分な安全確認により防げる事故が多いと報告されている．自動車の交差点走行における状況判断が改善されることで，安全な走行環境の確保に貢献可能である．
|
