CVGIP: Image Understanding
An Experimental Comparison of Range Image Segmentation Algorithms
IEEE Transactions on Pattern Analysis and Machine Intelligence
Edge detection in range images based on scan line approximation
Computer Vision and Image Understanding
Shape Detection in Computer Vision Using the Hough Transform
Shape Detection in Computer Vision Using the Hough Transform
Nonparametric Segmentation of Curves into Various Representations
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
In many branches of industry, piled box-like objects have to be recognized, grasped and transferred. Unfortunately, existing systems only deal with the most simple configurations (i.e. neatly placed boxes) effectively. It is known that the detection of 3D-vertices is a crucial step towards the solution of the problem, since they reveal essential information about the location of the boxes in space. In this paper we present a technique based on edge detection and robust line fitting, which efficiently detects 3D-vertices. Combining this technique with the advantages of a time of flight laser sensor for data acquisition, we obtain a fast system which can operate in adverse environments independently of lighting conditions.