The Consistent Labelling of Image Features using an ATMS
R. Bodington, G. D. Sullivan, K. D. Baker · 1988
Labelling sets of 2-D image features as model features is a constraint satisfaction problem that occurs in modelbased vision. The labelling must be consistent with constraints that describe how image features originating from the modelled object would appear in the image. This paper discusses how an assumption-based truth maintenance system, ATMS, can be used to solve such a constraint satisfaction problem. The ATMS is used to limit the number of constraints applied, and to represent the multiple sets of consistent labels that are possible. The effectiveness of the ATMS in limiting the constraints is analysed. This paper concerns the use of model-based vision techniques for the identification of vehicles in complex outdoor scenes 1. Figure 1 shows a typical scene. There