1 University College London
2 Disney Research
We investigate the advantages of a stereo, multi-spectral acquisition system for material classification in ground-level landscape images. Our novel system allows us to acquire high-resolution, multi-spectral stereo pairs using commodity photographic equipment. Given additional spectral information we obtain better classification of vegetation classes than the standard RGB case. We test the system in two modes: splitting the visible spectrum into six bands; and extending the recorded spectrum to near infra-red. Our six-band design is more practical than standard multi-spectral techniques and foliage classification using acquired images compares favourably to using a standard camera.
Gwyneth A. Bradbury, Kenny Mitchell, Tim Weyrich.
Lecture Notes in Computer Science (Proc. Conf. on Computer Analysis of Images and Patterns, CAIP), 8048, pp. 209–216, August 2013.Gwyneth Bradbury, Kenny Mitchell, and Tim Weyrich. Multi-spectral material classification in landscape scenes using commodity hardware. 8048:209–216, August 2013.Bradbury, G., Mitchell, K., and Weyrich, T. 2013. Multi-spectral material classification in landscape scenes using commodity hardware. 209–216.G. Bradbury, K. Mitchell, and T. Weyrich, “Multi-spectral material classification in landscape scenes using commodity hardware,” vol. 8048, pp. 209–216, Aug. 2013.
This work was supported by the UCL EngD VEIV Centre for Doctoral Training.