Aerial LiDAR Data Classification Using Weighted Support Vector Machines

This paper presents our research on classifying scattered 3D aerial LiDAR height data into ground,vegetable(trees) and man-made object(buildings) using improved Support Vector Machine algorithm.To this end,the most basic theory of SVM is first outlined and with the fact that features are differed in their contribution to identify certain class or classes simultaneously,Weighted Support Vector Machine(W-SVM) technique is developed for maximizing the "recognition" capacity of SVM features in classifying scattered 3D LiDAR height data.Second,we give a proof that the implement of W-SVM is equal to the features normalization multiplied by one weight that indicates feature's contribution to certain class or multi-class as a whole.The weight calculation for each feature is discussed as well.Third,Based on W-SVM technique,one 1AAA1 solution to multi-class classification is proposed by integration "one against one" and "one against all" solution together.Finally,the experiment of classifying LiDAR data with presented technique is presented and shows encouraging improvement classification accuracy,compared to tradition SVM technique.Valuable conclusions are given as well.