3D shape recovery by superquadrics model using object Silhouettes and stereo disparity

Effendi, Sutono; Jarvis, Ray; Li, Wai Ho

doi:10.1109/iccis.2010.5518577

Cited by 1 publication

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 9. The three views of objects on the table are used to obtain shape from silhouette and stereo disparity are implemented using method described in [3]. Each view was deliberately chosen to be separated with a large rotational angle in order to show the efficacy of our method.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Camera Ego-Motion Estimation Using Phase Correlation under Planar Motion Constraint

Effendi

Jarvis

2010

2010 International Conference on Digital Image Computing: Techniques and Applications

Self Cite

View full text Add to dashboard Cite

An intelligent robotic living assistive system has become a popular research in the last decade. One of the important topics in that research area is 3D object reconstruction from multiple views. This process may depend on motion estimation using vision. However, often a domestic robot on an electric wheel chair has to move in a steep rotational angle that causes motion estimation from vision to become inaccurate. In addition, an oblique viewing angle creates a perspective distortion to the captured images, which further worsens the estimation result. Hence, in this paper, we propose a new approach by altering the motion estimation problem into a 2D image registration problem. Our method's accuracy is very close to that of the Scale Invariant Feature Transform (SIFT) features tracker, whereas the Kanade-Lucas-Tomasi (KLT) tracker's drops as soon as the rotational angle reaches about 40 ∘ . Although our method is 2.7 times slower than the KLT tracker, it is 19 times faster than the SIFT tracker.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The execution time using the KLT and the SIFT feature tracker (Rob Hess implementation) including homographies of two views in our scheme are tabulated in Table. 1. Finally, we implement our method for a 3D reconstruction from multiple views [3] for a box and cylinder which were placed at known locations on the table. Fig.…”

Section: Performance Evaluationmentioning

confidence: 99%