Surendra

Abstract: To detect the motion of objects under monitored circumstances,a motion detection algorithm based on Surendra background updating and background subtraction is proposed.The visual images are grayed and the noise is eliminated. Then a reliable model of Surendra background updating is developed.The motion information is detected by adopting background subtraction method.The images are segmented.In an attempt to minimize the negative influences of noise and background disturbance,morphologic filtering and connected region area measurement are introduced.The experimental results show that the algorithm based on Surendra is practically valuable.

Abstract: Moving object detection plays an important role in intelligent transportation system. Combined with dynamic segmentation threshold and the counter, this paper proposes an improved Surendra algorithm based on background subtraction method. Image sequence is firstly preprocessed by median filtering, followed by background model updating on basis of dynamic background subtraction. Counter is incorporated to offset the effects of stagnation of moving vehicles and camera vibration. Mathematical morphology operations including connectivity components analysis and iterative dilating are applied to remove noises and fill holes. Experimental results show that the proposed method is efficient and can perform in real time.

Abstract: Recently, due to the gradual mature of the development of computer vision, video-based monitoring and control system has become a classic practice in the field of computer vision. Traffic detection and tracking technology in intelligent video surveillance system is one of the branches of computer vision, which has gradually become a hot and new research field. Through analysis and summary of the existing detection and tracking technology, this study draws a set of target detection and tracking program at the perspective of taking photos with a single fixed camera on the road. The target in the program is the vehicle on the road. The key point of the program is to detect the target, and another is tracking. The main purpose of this study is to detect and track the moving vehicles on the road in the condition of a single fixed camera. This detection program uses the improved surendra algorithm, which is a more advanced algorithm in the algorithms of moving target detection. In all the algorithms, such as background subtraction method and the adjacent frame difference method, the improved surendra algorithm is more excellent than them. The algorithm is based on the mixed Gaussian model method and the improved adjacent frame difference. Experiment shows that the algorithm is able to track and detect the target vehicle accurately indeed. And the complexity, real-time and robustness of the algorithm are very consistent with the system design requirements of the study, so the adoption of the algorithm and the implementation of the detection system design of this study can track and detect the target vehicle well.