In this article we propose a fusion model at data-level based on a linear combination of kernels. These kernels functions will be evaluated on disjoint entries, on the signature acquired from visible respective infrared spectrum. Therefore, we have to choose the proper numeric signature for the visible and for the infrared images. In order to retain just the best suited features, different feature extraction and feature selection algorithms have been investigated. In this way, important information can be achieved in a small number of coefficients, implying thus a significant reduction of the computation time. Our purpose is to develop the obstacle recognition module and to examine if a visible-infrared fusion is efficient for this task.
Applications of wavelet analysis are widespread and cover many fields of scientific research including image processing, classification and recognition. In addition, the mathematical concept of moments has been used for many years in pattern recognition and image processing. We present a new discovered family of splines, named fractional B-splines which we used as mother wavelet functions. The resulted fractional B-spline wavelets constitute a part of the features vector used in our ruttier obstacle classification system. We compared different recognition rates obtained by the use of different mother wavelet functions, but in order to improve the recognition rates, we added first order statistics features and the seven moments of Hu. The artificial vision systems was developed having as model the human system, and therefore the objects recognition task is reduced to a classification using features extracted from images. In our case, the features vector is formed by wavelet transform of fractional B-splines and seven statistics features, followed by the seven moments of Hu.