Research And Application Of Ship Detection System For Intelligrnt Shipping

Object detection is a critical research topic in computer vision,and its research results have been widely used in recent years.As an application scenario of object detection,ship detection has important research significance.Most ship detection research is based on SAR(Synthetic Aperture Radar)images in the existing research.However,the imaging method of SAR image is different from that of optical image,and it is impossible to transfer the research results of SAR image to optical image.Compared with SAR images,optical images have more image feature information,which can assist the algorithm to better learn ship features.In addition,the research of optical image ship detection has more important commercial value.Companies only need to equip a simple optical camera to complete the ship detection,without the need for a valuable device like radar.Optical image ship detection is also an important part of the obstacle avoidance module of unmanned ships.In this thesis,a ship detection system for intelligent shipping is designed.The optical image is captured by the code stream,and the ship in the channel is automatically detected,and the ship is positioned according to the position information on the image.The displacement of the image is measured for speed,and finally the detection and positioning speed measurement results are displayed on the map.The research carried out in this thesis is based on optical image ship detection,which is screened through comparative experiments,and the object detection performance of Faster R-CNN,SSD and YOLO v3 is comprehensively compared,and the YOLO v3 algorithm with the best performance is selected for target detection of waterway ships.The camera is calibrated,the internal parameters and distortion parameters of the camera are determined,and the mapping relationship between the image coordinate system and the real world coordinate system is established in combination with the external parameters of the camera to locate and measure the speed of the ship.This paper also integrates the attention mechanism in the backbone network of YOLO v3 to improve the residual block,and achieves better performance.At the same time,this paper optimizes the CIoU loss function whose performance is better than the regular loss function.On this basis,the AIoU loss function is proposed,and the regression performance is improved when the bounding boxes contain each other by adding the area penalty term.Compared with CIoU loss,AIoU loss further improves the detection performance,it is applied to ship detection in optical images,and compared with GIoU,DIoU,CIoU loss functions,it achieves better than GIoU,DIoU,CIoU loss functions in the bounding box regression task of ship detection.