| Project/Area Number |
12555151
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 展開研究 |
|---|
| Research Field |
交通工学・国土計画
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
SHIMIZU Eihan Graduate School of Engineering, Professor, 大学院・工学系研究科, 教授 (50196507)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
FUSE Takashi Japan Society for the Promotion of Science, Reserch Fellow, 特別研究員(PD)
TSUTSUML Morito Graduate School of Engineering, Assistant Professor, 大学院・工学系研究科, 講師 (70292886)
MORICHI Shigeru Graduate School of Engineering, Professor, 大学院・工学系研究科, 教授 (40016473)
|
|---|
| Project Period (FY) |
2000 – 2002
|
| Project Status |
Completed (Fiscal Year 2002)
|
| Budget Amount *help |
¥7,000,000 (Direct Cost: ¥7,000,000)
Fiscal Year 2002: ¥1,000,000 (Direct Cost: ¥1,000,000)
Fiscal Year 2001: ¥1,600,000 (Direct Cost: ¥1,600,000)
Fiscal Year 2000: ¥4,400,000 (Direct Cost: ¥4,400,000)
|
|---|
| Keywords | Optical Flow / Vehicle Maneuver / Moving Object Recognition / Sequential Image Analysis / Traffic Engineering / 実3次元空間計測 / 交通事故分析 / 挙動解析 / 光学勾配法 / 正則化 |
|---|
| Research Abstract |
1. Review of optical flow estimation methods
Optical flow estimation methods in all pixels are divided into gradient-based approach and area-based approach. The basic methods of the gradient-based approach are increase in the number of observation equations and imposition of a condition. The area-based approach has cross correlation, sequential similarity detection, eigen window.
2. Comparison of their performance empirically from the point of view of application to vehicle motion analysis
The reviewed methods were applied to sequential images from fixed video cameras and high altitude video cameras. The result showed the difficulty of estimation of precise and dense optical flow by ordinary gradient-based approaches. On the other hand, the results by SSDA were better than gradient-based approach.
3. Development of vehicle recognition method
With features, that are value of background subtraction and optical flow, all pixels in a spatio-temporal image are clustered. The spatio-temporal clustering means unifying pixels which meet homogeneous property.
4. Application to real sequential images
The proposed method was applied to 10cm and 1/30sec sequential images. In this experiment 77 vehicles in all, whose movements include direct advances, left and right-hand turns, lane changes and stoppage, could be recognized.
|
