Abstract：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 algorithmwhich aims to detect the phenomenon of seat occupation in university librariesprovide accurate positioning for libra Library Automation and Consulting ServiceThis model can automatically detect library seat occupancyhelping librarians manage seating resources more effectivelyThis automated detection method not only provides real-time seat usage status but also reduces the workload of librariansallowing them to focus more on other servicesAdditionallythis technology can be used in consultation services to provide real-time information when readers need to find available seatsThis article proposes a dual-channel detection model based on the Faster-RCNN object detection algorithm and the object classification algorithmThe model aims to detect seat occupancy in university librariesproviding librarians with accurate positioning and improving seat utilizationIn the detection processan object detection algorithm first determines if there is a person in the seatthenan object classification algorithm classifies and identifies images with no people to determine if the seat is occupiedThe study uses deep learning methods to solve the seat occupancy problem in library seat systemseffectively improving the detection accuracy of seat occupancy recognition and significantly enhancing the management efficiency of library seats