Alvey MMI-007 Vehicle Exemplar: Evaluation and Verification of Model Instances

Brisdon, Kay

doi:10.5244/c.1.5

Cited by 10 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The processes of evidental reasoning (Morton, 1987) and model matching (Brisdon, 1987) require inputs from the bottom-up processes; for the former as a factual description of the segmentation results in a suitable form; for the latter as hypotheses of good search areas, prioritised and constrained where possible. The rule-learning algorithm of Hutber and Sims (1987) also uses an attribute description of the segmented image, from which object recognition rules are derived.…”

Section: Discussionmentioning

confidence: 99%

Alvey MMI-007 Vehicle Exemplar: Image Segmentation and Attribute Generation

Godden¹,

Fullwood²,

Hyde³

1987

Procedings of the Alvey Vision Conference 1987

View full text Add to dashboard Cite

The MMI-007 project uses both bottom-up and top-down strategies to deal with the difficult problem of object recognition in outdoor scenes. Within this scheme, bottom-up methods fulfil the requirements of providing a concise image description suitable for symbolic reasoning and of providing an initial set of hypotheses to 'bootstrap' the top-down processes. The nature of the imagery does not lend itself easily to the derivation of precise 3-D structural information by optical-flow or stereo techniques. This leads us to call upon a range of static segmentation techniques, each individually capable of capturing some aspect of the diffuse information present in our images. For example, surface, texture and colour homogenity, and boundary smoothness and continuity.

show abstract

Section: Discussionmentioning

confidence: 99%

Alvey MMI-007 Vehicle Exemplar: Image Segmentation and Attribute Generation

Godden¹,

Fullwood²,

Hyde³

1987

Procedings of the Alvey Vision Conference 1987

View full text Add to dashboard Cite

show abstract

“…On instantiation the model is translated and rotated to the appropriate position in the world coordinate frame and finally all lines which are visible from the given camera position are projected onto the image. Each visible line is evaluated using methods similar to the one that was originally reported [6] [7] [8]. The scores from the individual lines are aggregated to give an overall goodness-of-fit score for the model in the given position.…”

Section: Evaluation Of the "Goodness-of-fit"mentioning

confidence: 99%

Advances in Model-Based Traffic Vision

Worrall¹,

Sullivan²,

Baker³

1993

Procedings of the British Machine Vision Conference 1993

View full text Add to dashboard Cite

Model based vision allows use of prior knowledge of the shape and appearance of specific objects to be used in the interpretation of a visual scene; it provides a powerful and natural way to enforce the view consistency constraint [I]. A model based vision system has been developed within ESPRIT VIEWS: P2152 which is able to classify and track moving objects (cars and other vehicles) in complex, cluttered traffic scenes. The fundamental basis of the method has been previously reported [2]. This paper presents recent developments which have extended the scope of the system to include (i) multiple cameras, (ii) variable camera geometry, and (Hi) articulated objects. All three enhancements have easily been accommodated within the original model-based approach.

show abstract

“…A more sophisticated iconic matching procedure has been described previously 6 . Viewpoint dependent predictions were made about the two-dimensional features in the image, hypothesised from a three-dimensional model.…”

Section: Iconic Model-matchingmentioning

confidence: 99%

Feature Aggregation in Iconic Model Evaluation

Brisdon¹,

Sullivan²,

Baker³

1988

Procedings of the Alvey Vision Conference 1988

Self Cite

View full text Add to dashboard Cite

This paper describes a method of model-matching, applicable as a verification procedure within a knowledge-based vision systems containing threedimensional geometric models. Most approaches to object verification in model-based vision merely extend the initial model instantiation process which uses a symbolic edge description, and thereby refine the initial hypothesis until a solution is reached. Symbolic edge descriptions are always inaccurate since it is difficult to translate real world scenes in to a set of discrete entities 1 . The iconic approach returns to the original image and can thus make use of information missed by the low-level processes.If a three-dimensional object is to be represented as a geometric model the model description should be analogical, to reflect the spatial isomorphism between the two entities. Geometric models used in vision systems are usually converted into an entirely symbolic form, for example graph structures 2 , or bit strings 3 , to facilitate matching with a symbolic image segmentation. A preferable approach is to use the spatial isomorphism present in the model and match it to an iconic representation of the image. Thus instead of simply applying global operations to the image to produce a fixed set of data structures, which can only be used uniformly, computational procedures of arbitrary complexity may be devised to manipulate the information in the image. Reliance for the final classification on the output of region or edge segmentations then becomes unnecessary. ICONIC MODEL-MATCHINGThere are a number of methods available with which iconic model-matching to an image can be performed. One example is image rendering, which was discussed in particular by Besl and Jain 4 . They believed that a common fault of vision systems is that "high-level results are not projected back into a low-level form for final error checking" and said that "more research is needed in this area". Their proposed solution to the problem was to use computer graphics techniques in conjunction with the object models to predict the sensor data. This prediction could then be tested for its correspondence with the pixels in the image. On a sequential machine this is a very slow process and excessively sensitive to minor detail. In any real image, and particularly in natural scene analysis, it is impossible to predict the conditions in the image.Another similar iconic/iconic process, namely normalised correlation, suffers from the same problems. In this technique template functions are produced which specify the expected binary or grey-level distribution of the image. The image is convolved with these masks and a metric used to measure the "best" or "sufficiently good" matches in the image. Correlation is more flexible than image rendering, as it is less dependent on local properties, and in addition deformations of the image are allowed. It still however relies on specifying what a portion of the image will look like and performing a quantative match. This is very difficult, and requires a much deeper ...

show abstract

Alvey MMI-007 Vehicle Exemplar: Evaluation and Verification of Model Instances

Cited by 10 publications

References 3 publications

Alvey MMI-007 Vehicle Exemplar: Image Segmentation and Attribute Generation

Alvey MMI-007 Vehicle Exemplar: Image Segmentation and Attribute Generation

Advances in Model-Based Traffic Vision

Feature Aggregation in Iconic Model Evaluation

Contact Info

Product

Resources

About