A computational theory of human stereo vision

Marr, David; Poggio, Tomaso

doi:10.1016/b978-1-4832-1446-7.50046-7

Cited by 130 publications

(171 citation statements)

References 47 publications

Supporting

Mentioning

170

Contrasting

Order By: Relevance

“…In stereo snakes, the stereo match actually affects the detection and localization of the features on which the match is based. This differs importantly, for example, from the Marr-Poggio stereo theory [12] in which the basic stereo matching primitive zero-crossings always remain unchanged by the matching process. Figure 7 shows an example of a 3D surface reconstructed from disparities measured along a Fig.…”

Section: Stereomentioning

confidence: 71%

Snakes: Active contour models

Kass

Witkin

Terzopoulos

1988

Int J Comput Vision

14,412

8,516

View full text Add to dashboard Cite

A snake is an energy-minimizing spline guided by external constraint forces and influenced by image forces that pull it toward features such as lines and edges. Snakes are active contour models: they lock onto nearby edges, localizing them accurately. Scale-space continuation can be used to enlarge the capture region surrounding a feature. Snakes provide a unified account of a number of visual problems, including detection of edges, lines, and subjective contours; motion tracking; and stereo matching. We have used snakes successfully for interactive interpretation, in which user-imposed constraint forces guide the snake near features of interest.

show abstract

Section: Stereomentioning

confidence: 71%

Snakes: Active contour models

Kass

Witkin

Terzopoulos

1988

Int J Comput Vision

14,412

8,516

View full text Add to dashboard Cite

show abstract

“…The reason for using the above search window about the point P~,i (described above) is as follows. Grimson (1981,1985) conducted experiments based upon the Marr-Poggio theory (Marr & Poggio 1979) of stereopsis with random dot stereograms whose edge points were extracted using the V2G operator. Marr and Poggio proposed that if the expected disparity for a certain binocular match is known and if an edge point is located within +to/2 of the expected disparity position, then a 95% probability exists that it is a correct match.…”

Section: Binocular and Trinocular Matchingmentioning

confidence: 99%

“…In the local matching stage, for every feature point in the base image, an attempt is made to find a set of candidate match-points in a second image which have similar local properties and which satisfy the epipolar constraint. In the global matching stage, a scheme for imposing a global consistency among the local matches, like coarse-to-fine (Grimson 1985;Marr & Poggio 1979), disparity gradient limit (Pollard et al 1981), neighborhood relationships (Ayache & Faverjon 1987;Medioni & Nevatia 1980), or relaxation labeling (Barnard & Thompson 1980;Kim & Aggarwal 1987), is used to disambiguate multiple local match-point candidates.…”

Section: Introductionmentioning

confidence: 99%

“…In case of ambiguity due to multiple match-point triplets, the 3D position of the ambiguous point is decided after determining the depth of all the surrounding points. A disparity smoothness constraint similar to that proposed by Marr and Poggio (1979) for imposing consistency among binocular matches in a neighborhood is used to decide the best match. Ito and Ishii (1986) use a similar trinocular imaging geometry and trinocular epipolar constraint for local matching.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A cost-benefit analysis of a third camera for stereo correspondence

Dhond

Aggarwal

1991

Int J Comput Vision

View full text Add to dashboard Cite

This paper looks at the twin issues of the gain in accuracy of stereo correspondence and the accompanying increase in computational cost due to the use of a third camera for stereo analysis. Trinocular stereo algorithms differ from binocular algorithms essentially in the epipolar constraint used in the local matching stage. The current literature does not provide any insight into the relative merits of binocular and trinocular stereo matching with the matching accuracy being verified against the ground truth. Experiments for evaluating the relative performance of binocular and trinocular stereo algorithms were conducted. The stereo images used for the performance evaluation were generated by applying a Lambertian reflectance model to real Digital Elevation Maps (DEMs) available from the U.S. Geological Survey. The matching accuracy of the stereo algorithms was evaluated by comparing the observed stereo disparity against the ground truth derived from the DEMs. It was observed that trinocular local matching reduced the percentage of mismatches having large disparity errors by more than half when compared to binocular matching. On the other hand, trinocular stereopsis increased the computational cost of local matching over binocular by only about one-fourth. We also present a quantization-error analysis of the depth reconstruction process for the nonparallel stereo-imaging geometry used in our experiments. I IntroductionWe present a quantitative analysis of the contribution of a third camera in improving the accuracy of local stereo matches, and its computational overhead in the stereo correspondence process. In the recent past, trinocular matching (Ayache & Lustman 1987;Ito & Ishii 1986;Peitikainen & Harwood 1986;Yachida et al. 1986) has been proposed as a new technique for achieving local matching in stereo analysis. Contemporary literature does not contain an in-depth analysis of the advantages gained in the local matching performance as a result of using trinocular instead of binocular stereo. Understanding the trade-off between the contribution of a third camera and the extra computations required for trinocular local matching is of significant interest for those involved in the design of stereo-based vision systems. We also present a quantization error analysis for the nonparallel stereo imaging geometry used in our experiments.Stereo analysis has been recognized as an important passive mechanism to extract 3D world information from intensity images. Earlier, Barnard and Fischler (1982) presented a detailed survey describing the major stages involved in stereo analysis and the different computational approaches developed starting from the mid70s up to 1981. The three main stages of computational stereopsis are preprocessing, establishing a correspondence, and computing the 3D depth (from the stereo disparity). Dhond and Aggarwal (1989) provide a comprehensive review of the major stereo algorithms developed in the recent past . Traditionally, only binocular (two view) images have been used in stereo analysis to...

show abstract

“…Color features is the most widely used in image recognition visual features, has the high stability. The shape of the image features, also known as contour, commonly used are longer than wide, area, perimeter, eccentricity, methods and so on [3] . Image topological properties are adjacent and connected, distance, euler number, etc.…”

Section: Image Feature Extraction and Analysismentioning

confidence: 99%

Theoretical Research on Image Recognition and Processing Method of Construction Engineering

Hou¹,

Zhao²,

Wang³

2017

dtssehs

View full text Add to dashboard Cite

Abstract. In the construction, project schedule management is a necessary part of the construction process. However in the huge construction, the traditional way that rely on human scene recording and monitoring has some difficulties in face of such a complex project. Based on this kind of situation, this paper proposes a vision: Using image recognition and processing technology to judge the construction schedule. This paper will discuss this idea from the type of image, image recognition and image processing in turn. InstructionWith the development of modern society, many major projects have completed and put into use. As we all know, a construction project usually need a lot of manpower, material resources, financial resources and time. In this environment, construction progress control is particularly important. The traditional way is that supervisor supervise the construction process and record the actual project progress on site, but the complexity of modern construction process is not qualified to human. So, this paper propose an idea: using related equipment to obtain the original image, then putting the image into computer, classifying the image recognition by a certain technology and convert it into computer signals, finally, comparing with computer database to determine whether the image reflects the present situation of the construction to achieve the intended target.

show abstract

A computational theory of human stereo vision

Cited by 130 publications

References 47 publications

Snakes: Active contour models

Snakes: Active contour models

A cost-benefit analysis of a third camera for stereo correspondence

Theoretical Research on Image Recognition and Processing Method of Construction Engineering

Contact Info

Product

Resources

About