On Kineopsis and Computation of Structure and Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion and Structure From Two Perspective Views: Algorithms, Error Analysis, and Error Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Trinocular Stereo Vision for Robotics
IEEE Transactions on Pattern Analysis and Machine Intelligence
The feasibility of motion and structure from noisy time-varying image velocity information
International Journal of Computer Vision
A Flexible New Technique for Camera Calibration
IEEE Transactions on Pattern Analysis and Machine Intelligence
Trinocular Active Range-Sensing
IEEE Transactions on Pattern Analysis and Machine Intelligence
3-D Translational Motion and Structure from Binocular Image Flows
IEEE Transactions on Pattern Analysis and Machine Intelligence
Modeling Insect Compound Eyes: Space-Variant Spherical Vision
BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Trinocular Divergent Stereo Vision
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Trinocular Stereo for Non-Parallel Configurations
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Trinocular Stereo Using Shortest Paths and the Ordering Constraint
SMBV '01 Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV'01)
Advances in Computational Stereo
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape and the Stereo Correspondence Problem
International Journal of Computer Vision
Recursive estimation of time-varying motion and structure parameters
Pattern Recognition
Hi-index | 0.00 |
This study develops a novel least-squares algorithm for recovering the translational motion parameters of a moving object using a parallel trinocular vision system. Although the proposed approach overcomes the matrix singularity problem inherent in binocular observers, its implementation is somewhat complex. Accordingly, a compact closed-form version of the algorithm is proposed to facilitate real-world visual imaging applications. The closed-form scheme not only resolves the matrix singularity problem, but also avoids the requirement for matrix manipulation and is therefore computationally efficient. The validity of the closed-form scheme is verified by comparing the known translation displacements of a target object with the estimated values. The results demonstrate that the proposed scheme accurately recovers the translational motion parameters provided that the movement of the target in the depth direction is of limited magnitude only. To verify the practical applicability of the proposed scheme, a servo tracking experiment is performed in which a parallel trinocular system mounted on a servo-driven positioning platform is used to track the motion of a target object as it is moved through a series of 3D displacements. The experimental results demonstrate that the closed-form scheme enables the parallel trinocular vision system to track the target effectively.