Research by Xiao-jun Tan, Jun Li & Chunlu Liu: Link to Research ArticleIn this research, they propose a new two-level real-time vehicle detection method in order to meet the robustness and efficiency requirements of real world applications. At the high level, pixels of the background image are classified into three categories according to the characteristics of Red, Green, and Blue (RGB) curves. The robustness of the classification is further enhanced by using line detection and pattern connectivity. At the lower level, an exponential forgetting algorithm with adaptive parameters for different categories is utilised to calculate the background and reduce the distortion by the small motion of video cameras.Traffic Scene Analysis and Classification Pixels in the traffic scene are classified into three categories according to the RGB curves, namely road surface, lane line and others. They found two common properties from RGB curves of a road surface pixel (figure a) and lane line (figure b). The differences of three primary colours (Red, Green and Blue) are not significant.The range of the oscillations is small.  However, pixels in different categories have different average values. It is found that the road surface pixel has an average value smaller than 150 while the lane line pixel has an average value greater than 180.By using equations, they have shown that a pixel can be classified into 3 categories.A pixel is on the road surfaceA pixel is on the lane lineThe pixels are neither on the road surface nor on the lane lineAfter the classification, a procedure is added to enhance the robustness of the classification, which is based on the observations of the geometric characteristics of the highway.Line Detection: With the results of the classifier, the candidates of a lane line form a straight line, which can be detected using a Hough Transformation. Only those near the line can be confirmed as lane lines. The detected line is in colour blue. Two white areas due to plastic bags are excluded. If the lane line is another curve than a straight line, then other techniques can be adopted.Pattern Connectivity: A growing algorithm, similar to that from Tremeau and Borel, is utilised to check the candidates of the road surface. The result is shown in green in figure below. In figure below, the green pixels are the connected patterns of road surfaces. Those pixels that cannot be classified either as road surface or as a lane line are labelled with their original colour.Background Learning based on Classification The background learning algorithm is similar to the exponential forgetting algorithm that has been mentioned in the research article previously. But in here they have changed the forgetting factor to a function rather than a constant. When compared with the simple forgetting algorithm, the modified forgetting factor considers the motion happening at the current pixel so that only the relatively stable pixels are chosen to perform background learning. This approach can significantly reduce the effects caused by small motion of video cameras, which is very important for outdoor environments. If the pixel belongs to the other class, then background learning will not be performed because this kind of pixel has nothing to do with the motion detection of the current frame. To further reduce the computation time, the background classification and background learning are not updated synchronously. As shown in the figure below, background learning is performed for almost every frame, but the classification will only be carried out after a certain period. Vehicle Detection Vehicle detection has almost the same meaning of motion segmentation, which judges whether there is a motion at a certain pixel. In the proposed method, the area to detect vehicles is not the whole image, but rather due to understanding given at the higher level. If the pixel belongs to the other class and is in the lane line or near the lane line, then detection will not be performed. This can help to avoid false detection due to small motions of the camera. Figure below shows each area with a possible vehicle, while other areas are ignored. An algorithm named Minimum Boundary Rectangles (MBRs) is then utilised in order to divide those areas that belong to different vehicles. The rectangles indicating the moving vehicles are outlined.