Improving safety and reducing accidents are the most goals of Advanced Driver Assistance Systems (ADAS). For their low cost and capability of providing information about driving environments, Vision-based driver assistance systems are the most important systems in recent years. In these systems, robust and precise vehicle detection is a critical step, and the detected cars can be used for various applications. This paper presents an algorithm for vehicle detection in an urban environment which is very important for driver assistance systems and autonomous driving. To succeed the detection of a vehicle, we propose the histogram of oriented gradients features descriptor (HOG) and linear support vector machine (SVM) for the classification. Our experimental results illustrate the robustness and precision of our algorithm for different scenes.