27 February 2007 Landmarks recognition for autonomous aerial navigation by neural networks and Gabor transform
Author Affiliations +
Template matching in real-time is a fundamental issue in many applications in computer vision such as tracking, stereo vision and autonomous navigation. The goal of this paper is present a system for automatic landmarks recognition in video frames over a georeferenced high resolution satellite image, for autonomous aerial navigation research. The video frames employed were obtained from a camera fixed to a helicopter in a low level flight, simulating the vision system of an unmanned aerial vehicle (UAV). The landmarks descriptors used in recognition task were texture features extracted by a Gabor Wavelet filters bank. The recognition system consists on a supervised neural network trained to recognize the satellite image landmarks texture features. In activation phase, each video frame has its texture feature extracted and the neural network has to classify it as a predefined landmark. The video frames are also preprocessed to reduce their difference of scale and rotation from the satellite image before the texture feature extraction, so the UAV altitude and heading for each frame are considered as known. The neural network techniques present the advantage of low computational cost, been appropriate to real-time applications. Promising results were obtained, mainly during flight over urban areas.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Elcio Hideiti Shiguemori, Elcio Hideiti Shiguemori, Maurício Pozzobon Martins, Maurício Pozzobon Martins, Marcus Vinícius T. Monteiro, Marcus Vinícius T. Monteiro, } "Landmarks recognition for autonomous aerial navigation by neural networks and Gabor transform", Proc. SPIE 6497, Image Processing: Algorithms and Systems V, 64970R (27 February 2007); doi: 10.1117/12.705138; https://doi.org/10.1117/12.705138

Back to Top