Object Detection Method Using Invariant Feature Based on Local Hue Histogram in Divided Area of an Object Area
Proceeding: The Fourth International Conference on Artificial Intelligence and Pattern Recognition (AIPR)Publication Date: 2017-09-18
Authors : Tomohiro Kanda; Kazuo Ikeshiro; Hiroki Imamura;
Page : 33-41
Keywords : Cognitive Robot; Hue Histogram; Peak And Trough; Divided Area;
Abstract
In recent years, human support robots have been receiving attention. Then, the robots are required to perform various tasks to support humans. Especially, an object detection task is important in case that people request the robot to transport and rearrange an object. However, the detection becomes difficult owing to difference of visual aspect in case of detecting with a target object from an equipped camera on a robot. We consider that there are seven necessary properties to detect in domestic environment as follows. 1. Robustness against the rotation change. 2. Robustness against the scale change. 3. Robustness against the illumination change. 4. Robustness against the distortion by perspective projection. 5. Robustness against the occlusion. 6. Detecting an object which has few textures. 7. Detecting different objects which have the same features of the hue histogram. As conventional method, there are Scale Invariant Feature Transform (SIFT), Color Indexing and the proposed method by Tanaka et al. These conventional methods do not satisfy all seven properties needed for the robots. Therefore, to satisfy the seven properties of detection, we propose the object detection method using invariant feature based on local hue histogram in a divided area of an object area.
Other Latest Articles
- A 3-Dimensional Object Recognition Method Using SHOT and Relationship of Distances and Angles in Feature Points
- A Neural Network Approach for Attribute Significance Estimation
- Multi-Sensor Fusion Method For Mobile System Localization
- Combined Neural Network Model for Real Estate Market Range Value Estimation
- Mapping of Relational Schema to Ontology Model
Last modified: 2017-10-02 23:39:34