Drivable path detection based on image fusion for unmanned ground vehicles

Autonomous vehicles are used for a range of tasks, such as automated highway driving, transporting work, etc. These vehicles are used both in structured and unstructured environments. This work presents an effective method for path detection using statistical texture features extracted from fused LIDAR sensor and visual camera images. An edge-based feature detection approach is adopted for image registration. The Grey Level Co-occurrence Matrix (GLCM)-based texture features are extracted from the fused image. Classification performance of K-NN and Support Vector Machine (SVM) classifiers are analysed in this work. For experimentation, the data available in Ford Campus Vision data set are used. The results of this new approach are very promising for path detection problem of unmanned ground vehicles.