2010 Fiscal Year Final Research Report
Human Detection and Action Recognition by Feature Co-occurrence using TOF Camera
| Project/Area Number |
21700228
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Chubu University |
|---|
Principal Investigator |
FUJIYOSHI Hironobu Chubu University, 工学部, 教授 (20333172)
|
|---|
| Project Period (FY) |
2009 – 2010
|
| Keywords | 人検出 / 動作認識 / 距離情報 / Joint Boosting / Haar-likeフィルタ |
|---|
| Research Abstract |
We proposed a method for detecting humans that uses depth information obtained from a TOF camera. Our method calculates features derived from a depth histogram that represents the relationship between two local regions. Our method achieved a detection rate of 98.9% with a false positive rate of 5.0%. It also had a 4.9% higher performance than the conventional method, and our detection system can run in real-time (10 fps).
|
Research Products
(9 results)
