3-D translational motion and structure from binocular image flows

Li, L.; Duncan, James H.

doi:10.1109/34.221167

Cited by 30 publications

(16 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the motion parameters are to be obtained using just two image patterns, an additional constraint must be introduced. Li and Duncan [20] proposed that a suitable additional constraint could be obtained simply by multiplying one of the two optical equations by the y-coordinate value in order to generate the following 3x3 image matrix:…”

Section: Limitations Of Binocular Stereo Image Visioning Systemsmentioning

confidence: 99%

“…However, the authors neither addressed the behavior of translational motion nor explored the potential sources of navigational error. Li and Duncan [20] used the image flow fields captured by two parallel stereo cameras to determine the 3D translational motion parameters with respect to various objects in the viewing area and to establish the correspondence between equivalent features in the left and right images. However, since the disparity between the left and right images in a binocular system is insufficient to fully determine the translational motion, the authors were obliged to introduce an additional geometrical constraint, namely multiplying one of the two optical equations by the y-coordinate value.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Acquisition of translational motion by the parallel trinocular

Cheng

Lin

2008

Information Sciences

View full text Add to dashboard Cite

Section: Limitations Of Binocular Stereo Image Visioning Systemsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Acquisition of translational motion by the parallel trinocular

Cheng

Lin

2008

Information Sciences

View full text Add to dashboard Cite

“…In the earlier works of motion-stereo integration, no matter it is the mere juxtaposition of the results from independent processing of the motion and stereo information (Ayache and Faugeras, 1989;Grosso et al, 1989;Kriegman et al, 1989), where the final estimates of structure were based on some combination of the outputs of these separate processes (coupled loosely together sensus (Clark and Yuille, 1994)), or the tightly coupled approach where the processing of one type of visual information may depend on the presence of another (Balasubramanyam and Snyder, 1991;Li and Duncan, 1993;Shi et al, 1994;Waxman and Duncan, 1993;Zhang and Negahdaripour, 2008), the all but universal assumption is that the overlap in the visual field is used for computing binocular disparity. This assumption remains true in the later approaches with the advent of more sophisticated techniques such as PDE (Strecha and Gool, 2002), variational approach (Huguet and Devernay, 2007;Pons et al, 2007;Williams et al, 2005)and factorization (Ho and Chung, 2000).…”

Section: Literature Reviewmentioning

confidence: 99%

Quasi-Parallax for Nearly Parallel Frontal Eyes

Cheong

Gao

2012

Int J Comput Vis

View full text Add to dashboard Cite

In this paper, we explore how a visual system equipped with a pair of frontally-placed eyes/cameras can rapidly estimate egomotion and depths for the task of locomotion by exploiting the eye topography. We eschew the traditional approach of motion-stereo integration, as finding stereo correspondence is a computationally expensive operation. Instead, we propose a quasi-parallax scheme by pairing appropriate visual rays together, thus obviating the need for stereo correspondence and yet being able to leverage on the redundant information present in the binocular overlap. Our model covers realistic visual systems where the two eyes might deviate from the strictly frontal-parallel configuration, and yet the results show that the advantages of the parallax-based approach are retained. In particular, it offers better disambiguation of translation and rotation over conventional two-frame structure from motion approaches, despite not having views covering diametrically opposing directions like that of spherical eyes or laterally-placed eyes. The rapid processing that such scheme entails seems to offer a more realizable and useful alternative for depth recovery during locomotion.

show abstract

“…In general, it is possible to make a distinction between the approaches where the results of stereo and motion analysis are considered separately and the rather different approach based upon more integrated relations. Within this group falls the work reported in [18], [19] where the temporal derivative of disparity is exploited, and the dynamic stereo approach [20], [21] considered in this paper.…”

Section: Introductionmentioning

confidence: 99%

Active/dynamic stereo vision

Grosso

Tistarelli

1995

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

Abstract-Visual navigation is a challenging issue in automated robot control. In many robot applications, like object manipulation in hazardous environments or autonomous locomotion, it is necessary to automatically detect and avoid obstacles while planning a safe trajectory. In this context the detection of corridors of free space along the robot trajectory is a very important capability which requires nontrivial visual processing. In m t cases it is possible to take advantage of the active control of the cameras.In this paper we propose a cooperative schema in which motion and stereo vision are used to infer scene structure and determine free space areas. Binocular disparity, computed on several stereo images over time, is combined with optical flow from the same sequence to obtain a relative-depth map of the scene. Both the time-to-impact and depth scaled by the distance of the camera from the fixation point in space are considered as good, relative measurements which are based on the viewer, but centered on the environment.The need for calibrated parameters is considerably reduced by using an active control strategy. The cameras track a point in space independently of the robot motion and the full rotation of the head, which includes the unknown robot motion, is derived from binocular image data.The feasibility of the approach in real robotic applications is demonstrated by several experiments performed on real image data acquired from an autonomous vehicle and a prototype camera head.

show abstract

3-D translational motion and structure from binocular image flows

Cited by 30 publications

References 8 publications

Acquisition of translational motion by the parallel trinocular

Acquisition of translational motion by the parallel trinocular

Quasi-Parallax for Nearly Parallel Frontal Eyes

Active/dynamic stereo vision

Contact Info

Product

Resources

About