A novel texture feature based multiple classifier technique for roadside vegetation classification

•Proposed technique use LBP based GLCM feature vector and multiple classifiers.•We achieve over 92% accuracy for vegetation classification.•Extensive experiments use 5-fold cross validation.•The experiments were conducted on dense and sparse grasses.•In future, extension will be done by introducing large dataset of grasses.

This paper presents a novel texture feature based multiple classifier technique and applies it to roadside vegetation classification. It is well-known that automation of roadside vegetation classification is one of the important issues emerging strongly in improving the fire risk and road safety. Hence, the application presented in this paper is significantly important for identifying fire risks and road safety. The images collected from outdoor environments such as roadside, are affected for a high variability of illumination conditions because of different weather conditions. This paper proposes a novel texture feature based robust expert system for vegetation identification. It consists of five steps, namely image pre-processing, feature extraction, training with multiple classifiers, classification, validation and statistical analysis. In the initial stage, Co-occurrence of Binary Pattern (CBP) technique is applied in order to obtain the texture feature relevant to vegetation in the roadside images. In the training and classification stages, three classifiers have been fused to combine the multiple decisions. The first classifier is based on Support Vector Machine, the second classifier is based on feed forward back-propagation neural network (FF-BPNN) and the third classifier is based on -Nearest Neighbor (k-NN). The proposed technique has been applied and evaluated on two types of vegetation images i.e. dense and sparse grasses. The classification accuracy with a success of 92.72% has been obtained using 5-fold cross validation approach. An (Analysis of Variance) test has also been conducted to show the statistical significance of results.