Effect of Features and Angle on GLCM Feature Extraction on Accuracy for Object Classification

An autonomous car is a vehicle that can guide itself without human intervention. Various types of steeringless vehicles are being developed. The system of the future where computers take over the art of driving. The problem was before it became a concern in autonomous cars to get high safety. Autonomous cars need an early warning system to avoid accidents in front of the car, especially systems that can be used on highway locations. In this paper, we propose a vision-based vehicle detection system for vehicle detection in the form of cars. Our detection algorithm consists of two main components: Extraction of color features using GLCM values, and testing of 6 parameters of GLCM dissimilarity, correlation, homogeneity, contrast, ASM and energy. We use the SVM (Support Vector Machine) algorithm for the classification algorithm. The SVM (Support Vector Machine) classification in previous studies has had quite good results and has a fast computation time. Good accuracy results are found in the ASM feature and using an angle of 450