Library occupancy warning system based on dual-channel detection

This paper proposes a dual-channel detection model based on Faster-RCNN object detection algorithm and objects classification algorithm, which aims to detect the phenomenon of seat occupation in university libraries, provide accurate positioning for librarians, and improve the utilization rate of seats. The data set is constructed by combining network acquisition with UE5 virtual reality construction. The dual-channel detection comprises the following two steps. In first step, a target detection algorithm is used to judge whether a person is on the seat. Next, the objects classification algorithm is used to classify and identify the pictures without people to judge whether the person is suspected of occupying the seat. The research uses deep learning method to solve the problem of seat occupation in library seat system, effectively improves the detection accuracy of seat occupation recognition, and greatly improves the management efficiency of library seats.