Image interpretation: exploiting multiple cues

Multiple cues play a crucial role in image interpretation. A vision system that combines shape, colour, motion, prior scene knowledge and object motion behaviour is described. The authors show that the use of interpretation strategies which depend on the image data, temporal context and visual goals significantly simplifies the complexity of the image interpretation problem and makes it computationally feasible.

[1]  J. Kittler,et al.  Colour texture analysis using colour histogram , 1994 .

[2]  W. Eric L. Grimson,et al.  An active visual attention system to play \Where''s Waldo , 1994, Computer Vision and Pattern Recognition.

[3]  Jiri Matas,et al.  Recognition of Cylindrical Objects Using Occluding Boundaries Obtained from Colour Based Segmentation , 1994, BMVC.

[4]  Miroslaw Zbigniew. Bober.  General motion estimation and segmentation from image sequences , 1994 .

[5]  James L. Crowley,et al.  Vision as Process , 1995 .

[6]  Josef Kittler,et al.  Supervised segmentation using a multiresolution data representation , 1993, Signal Process..

[7]  Mubarak Shah,et al.  Motion-based recognition a survey , 1995, Image Vis. Comput..

[8]  J. Kittler,et al.  Robust motion analysis , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Jiri Matas,et al.  Constraining visual expectations using a grammar of scene events , 1995 .

[10]  Jiri Matas,et al.  On representation and matching of multi-coloured objects , 1995, Proceedings of IEEE International Conference on Computer Vision.

[11]  Makoto Nagao,et al.  A Structural Analysis of Complex Aerial Photographs , 1980, Advanced Applications in Pattern Recognition.

[12]  J. Kittler,et al.  Recognition of polyhedral objects using triangle pair features , 1993 .

[13]  Jiri Matas,et al.  Control of Scene Interpretation , 1995 .

[14]  Josef Kittler,et al.  Estimating Angles And Curvature Features In Grey Scale Images , 1994, BMVC.