BROWSE
Detail
Conference Paper
Object Pose Estimation by Contour Segment Matching
Cited - time in 
Share 
Share
- Authors
- Seohyun Jeon, Sangseung Kang, Kyekyung Kim, Jaemin Cho
- Issue Date
- 2019-02
- Citation
- International Workshop on Frontiers of Computer Vision (IW-FCV) 2019, pp.1-3
- Language
- English
- Type
- Conference Paper
- Abstract
- Estimating the pose of the target object from the obtained image is an important procedure for the robot grasping task which enables extracting exact grasping points. We assumed a manufacturing application, where assembly parts are fed randomly on the moving conveyor belt. The camera recognizes the object’s coordinate and sends the coordinate to the robot controller for grasping. Machine learning is generally used to estimate the pose of the object from the image. To operate machine learning, the user has to collect many images for training database. However, in real factory application, the target object is changed frequently, and it is difficult to acquire many image data, every time the target is changed. Therefore, a flexible and fast adapting method is required. This paper proposes a pose estimation method that applicable to flexible work environment by matching contour shape of the image.
- KSP Keywords
- Assumed A, Image data, Object Pose Estimation, Robot Controller, Robot Grasping, Training database, conveyor belt, estimation method, machine Learning, target object, work environment