A Method for Improving Accuracy of Object Recognition and Pose Estimation by Using Kinect sensor

• DOI: 10.7746/jkros.2015.10.1.016
• Publication Date: 2015-03-11T00:39:00Z
• Authors: Anna Kim; Gun Kyu Yee; Gitae Kang; Yong Bum Kim; Hyouk Ryeol Choi
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

This paper presents a method of improving the pose recognition accuracy objects by using Kinect sensor. First, SURF algorithm, which is one most widely used local features point algorithms, we modify inner parameters algorithm for efficient object recognition. The proposed adjusting distance between box filter, modifying Hessian matrix, and eliminating improper key points. In second, orientation estimated based on homography. Finally novel approach Auto-scaling to improve estimation. experimentally tested with in plane its effectiveness validated.