Fundamentals of digital image processing
Fundamentals of digital image processing
Bayesian Estimation of Motion Vector Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine vision
Multiple Constraints to Compute Optical Flow
IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time quantized optimal flow
Real-Time Imaging - Special issue on computer vision motion analysis
Self-organizing maps
Detecting Salient Motion by Accumulating Directionally-Consistent Flow
IEEE Transactions on Pattern Analysis and Machine Intelligence
Model-Based Brightness Constraints: On Direct Estimation of Structure and Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robot Vision
Computer Vision: Three-Dimensional Data from Images
Computer Vision: Three-Dimensional Data from Images
Theory of Reconstruction from Image Motion
Theory of Reconstruction from Image Motion
Computer and Robot Vision
| Hi-index | 0.00 |
To increase the robustness of optical flow computation in the context of mobile robotics, we introduce an image filtering process based on the codebook computed by Vector Quantization (VQ) algorithms, which usually are used for compression and codification purposes. The Self Organizing Map is used to compute adaptively the vector quantizers of color imaged sequences. The codebook computed for each image in the sequence is then used as a smoothing filter, the VQ Bayesian Filter (VQ-BF), for preprocessing images in the sequence. The filtered images are the basis for the computation of the optical flow via pixel and region correlation algorithms. The pixel correlation gives a good estimation of the optical flow at the image edges, whereas the region correlation gives a robust and dense estimation of the optical flow.