Showing papers on "3D single-object recognition published in 1981"
Proceedings Article•
24 Aug 1981
TL;DR: This paper describes an approach to the recognition of stacked objects with planar and curved surfaces by a combination of data-driven and model-driven search processes.
Abstract: This paper describes an approach to the recognition of stacked objects with planar and curved surfaces. The range data of a scene are obtained by a range finder. The system works In two phases. In a learning phase, a scene containing a single object Is described In terms of properties of regions and relations between them. This description Is stored as an object model. In a recognition phase, an unknown scene Is described In the same way as In the learning phase. And then the description is matched to the object models so that stacked objects are recognized one by one. Efficient matching is achieved by a combination of data-driven and model-driven search process. Experimental results for blocks and machine parts are shown.
282 citations
TL;DR: A hardwired videoprocessor linked to a 16‐bit microprocessor enables the recognition of plane objects to be achieved within 30 milliseconds.
Abstract: Recognition of plane objects can be achieved by calculating the area and first and second moments of the object. In the work described a hardwired videoprocessor linked to a 16‐bit microprocessor enables the recognition to be achieved within 30 milliseconds.
8 citations
TL;DR: An algorithm is described for recognizing two-dimensional objects that first checks the boundary lines against the object models and then performs a model-directed search for other details of the object.
7 citations
TL;DR: A decentralised computing system based on the data-flow model of computation is applied, in conjunction with a laser range-finder, to the task of recognising a number of simple objects in a work-space.
2 citations
[...]
TL;DR: This essay overviews the algorithms of medium level vision, i.e. those algorithms which perform intermediate steps of image recognition, and surveys several proposed algorithms and introduces some ideas which hold promise to develop into an underlying theory.
Abstract: This essay overviews the algorithms of medium level vision, i.e. those algorithms which perform intermediate steps of image recognition. The reason for this choice is the great diversity of methods proposed for medium level vision and the lack of an underlying theory about how to design appropriate intermediate structures and algorithms for a given image recognition task. The paper surveys several proposed algorithms and introduces some ideas which hold promise to develop into an underlying theory. Two specific image recognition systems are also described which incorporate medium level vision algorithms together with low and high level vision methods, providing possible logical sequences to constitute complete recognition systems.
2 citations