People Counting In Classroom Based On Video Surveillance

Currently, the switches of the lights and other electronic devices in the classroom are mainly relied on manual control, as a result, many lights are on while no one or only few people in the classroom. It is important to change the current situation and control the electronic devices intelligently according to the number and the distribution of the students in the classroom, so as to reduce the considerable waste of electronic resources. This paper studies the problem of people counting in classroom based on video surveillance. With the development of social economy, more and more video surveillance system is used in all kinds of public places widely. Currently, how to extract the useful information in the video monitoring data is one of the research hotspots and difficulties in the field. According to the relative position about the camera and the target object, there are three kinds of common scenario about the number statistics:camera is located above the diagonal the target object, which can obtain the target object shape contour information. Camera is located on the in and out port, which can get the head shape contour information of target objects. And the camera is located in the highly probably flush with the target object, which means it can get the facial feature. These three scenarios are using the three different characteristics respectively to achieve counting, such as using the body’s shape features, outline of man’s head and facial features.As the camera in the classroom can not get the full shape contour information of bodies and the clear features information of faces, the following work has been done in this paper.1. In this paper the feature-based methods are used in the number of classroom scenes detection, using different feature extraction methods and classification methods characteristics of different combinations to achieve statistics. And these methods are verified and comparative analysis through the experiments.2. A new kind of dual background updating model based on sparse and low-rank matrix decomposition is proposed in this paper, according to the fact that most of the students in the classroom are almost in stationary state and there are body movement occasionally. Firstly, combining the frame difference with the sparse and low-rank matrix decomposition to predict the moving areas, and updating the background model with different parameters according to the positional relationship between the pixels of current video frame and the predicted motion regions. Secondly, the regions of moving objects are determined based on the updated background using the background subtraction method. Finally, some operations including binarization, median filtering and morphology processing, connected component detection, etc. are performed on the regions acquired by the background subtraction, in order to induce the effects of the noise and obtain the number of people in the classroom.The experimental results show that the proposed improved method has certain improvement in the classroom number statistics. Finally, this paper analyzes the shortcomings in the course of the research process, and the work plan for the next step are made in this paper.