Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Generating De Bruijn Sequences: An Efficient Implementation
IEEE Transactions on Computers
The watershed transform: definitions, algorithms and parallelization strategies
Fundamenta Informaticae - Special issue on mathematical morphology
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Range Sensing by Projecting Multiple Slits with Random Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Toward optimal structured light patterns
NRC '97 Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling
Space-variant computer vision: a graph-theoretic approach
Space-variant computer vision: a graph-theoretic approach
Spacetime Stereo: A Unifying Framework for Depth from Triangulation
IEEE Transactions on Pattern Analysis and Machine Intelligence
An improved watershed algorithm based on efficient computation of shortest paths
Pattern Recognition
A High-Resolution and High Accuracy Real-Time 3D Sensor Based on Structured Light
3DPVT '06 Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)
Optimised De Bruijn patterns for one-shot shape acquisition
Image and Vision Computing
A method for constructing decodable de Bruijn sequences
IEEE Transactions on Information Theory
The minimum description length principle in coding and modeling
IEEE Transactions on Information Theory
Aperiodic and semi-periodic perfect maps
IEEE Transactions on Information Theory
Hi-index | 0.00 |
We present a new technique for decoding color stripe or color checkerboard patterns as often used for single-shot 3d range data acquisition with structured light. The key idea is to segment the camera image into superpixels with a watershed transform. We then describe a new algorithm that constructs a regions adjacency graph and uses it to solve the correspondence problem. This is an improvement over existing scanline based evaluation methods as the spatial coherence assumption can be relaxed. It allows to measure non-smooth objects that have so far posed problems for single-shot acquisition. The algorithm works in near real time even in uncontrolled environments. Experimental results are given.