Three-dimensional object recognition from single two-dimensional images
Artificial Intelligence
Computation of Surface Orientation and Structure of Objects Using Grid Coding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Surface Orientation from a Projected Grid
IEEE Transactions on Pattern Analysis and Machine Intelligence
3-D Surface Solution Using Structured Light and Constraint Propagation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual learning and recognition of 3-D objects from appearance
International Journal of Computer Vision
A robust-coded pattern projection for dynamic 3D scene measurement
Pattern Recognition Letters
Registration of Cad-Models to Images by Iterative Inverse Perspective Matching
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Vision guided bin picking and mounting in a flexible assembly cell
IEA/AIE '00 Proceedings of the 13th international conference on Industrial and engineering applications of artificial intelligence and expert systems: Intelligent problem solving: methodologies and approaches
A New Contour-Based Approach to Object Recognition for Assembly Line Robots
Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
| Hi-index | 0.00 |
The development of a flexible assembly unit is one of the demanding tasks in industrial manufacturing. A higher degree of flexibility is mostly payed by an increasing complexity of the involved hardware. In this paper we present a three-step concept for a vision driven automatic assembly unit. These three steps are robust bin-picking to isolate objects from a pile of unorganized parts, exact pose determination to enable industrial mounting and visual inspection of the final assembling. For robust bin-picking we present a new structured light approach. Experiments show the robust and accurate behavior of the proposed algorithm and motivate the implementation in an industrial system. For exact pose determination, the second step, a pose estimation based on a modified view based approach, followed by a model based refinement is proposed. Initial experiments promise a fast and exact pose determination.