Road Traffic Flow Surveillance Robust for Poor Visibility Conditions Using Infrared Thermal Image Processing
| Project/Area Number |
23560631
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Civil engineering project/Traffic engineering
|
|---|
| Research Institution | Tokai University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2011-04-28 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2013: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2012: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2011: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | 車両検出 / 画像処理 / 道路交通流自動監視 / 赤外線サーモグラフィ / 視界不良環境 / パターン認識 / 赤外線エネルギー反射 / 温度画像 / 環境変動 / 交通流自動監視 / 交通流状態検知 |
|---|
| Outline of Final Research Achievements |
We have proposed two methods, method 1 and method 2, for detecting vehicle positions and their movements using thermal images taken with an infrared thermal camera. Method 1 detects vehicles robustly under four different environmental conditions which contain poor visibility conditions in snow and thick fog. Method 2 detects vehicles in thermal images for which the vehicle detection accuracies of method 1 are low. By combining these two methods, high vehicle detection accuracies are realized under various environmental conditions. We have proposed a traffic flow automatic surveillance method using traffic information obtained by the two methods, and have shown the effectiveness of our proposal. This surveillance method distinguishes uncongested flow and congested flow in each lane. The method also detects traffic problems such as vehicle accidents, broken down vehicles, and illegal parking.
|
Report
(5 results)
Research Products
(16 results)
