Multi-spectral Material Classification in Landscape Scenes Using Commodity Hardware

Abstract

Abstract. 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, multispectral 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 simply using a standard camera.

Image recognition in UAV videos using convolutional neural networks

“…Its main applications have been in the areas of pattern recognition, natural language processing, and computational learning [2]. Some of the most common problems in this area are the recognition of personal characteristics [3, 4], the detection of faces [5, 6, 7], the recognition of landscape types [8], the recognition of handwritten digits [9, 10], digital forensic analysis [11], recognition of traffic signals [12, 13], sentiment analysis [14], among others.…”