Research on Multi-Ship Target Detection and Tracking Method Based on Camera in Complex Scenes

Abstract

Aiming at the problem that multi-ship target detection and tracking based on cameras is difficult to meet the accuracy and speed requirements at the same time in some complex scenes, an improved YOLOv4 algorithm is proposed, which simplified the network of the feature extraction layer to obtain more shallow feature information and avoid the disappearance of small ship target features, and uses the residual network to replace the continuous convolution operation to solve the problems of network degradation and gradient disappearance. In addition, a nonlinear target tracking model based on the UKF method is constructed to solve the problem of low real-time performance and low precision in multi-ship target tracking. Multi-ship target detection and tracking experiments were carried out in many scenes with large differences in ship sizes, strong background interference, tilted images, backlight, insufficient illumination, and rain. Experimental results show that the average precision of the detection algorithm of this paper is 0.945, and the processing speed is about 34.5 frame per second, where the real-time performance is much better than other algorithms while maintaining high precision. Furthermore, the multiple object tracking accuracy (MOTA) and the multiple object tracking precision (MOTP) of this paper algorithm are 76.4 and 80.6, respectively, which are both better than other algorithms. The method proposed in this paper can realize the ship target detection and tracking well, with less missing detection and false detection, and also has good accuracy and real-time performance. The experimental results provide a valuable theoretical reference for the further practical application of the method.

Ship Detection Algorithm Based on YOLOv5 Network Improved with Lightweight Convolution and Attention Mechanism

“…Zhou the advantages of YOLOv3 and Retina-Net, which greatly reduces the number of parameters and computational complexity while ensuring detection accuracy [7]. Hong et al [8] used a residual network instead of continuous convolution operation in YOLOv4 to solve the problem of network degradation and gradient disappearance, and established a nonlinear target tracking model based on the UKF method, which improved the accuracy of ship detection. Wang et al [9] used SSD512, Faster-RCNN, and other methods to obtain a selfconstructed SAR image dataset with an 89.43% AP value; however, from the experimental results, some misdetections and omissions still occurred.…”

Particle Filter Based on Harris Hawks Optimization Algorithm for Underwater Visual Tracking

“…Faced with the complexity of the underwater environment, Wu et al [9] presented an improved Siamese network which introduced a lightweight network and hybrid excitation model to reduce the computational complexity and enhance the network's accuracy to achieve better underwater target tracking. Hong et al [10] proposed an improved YOLOv4 algorithm that simplifies the feature extraction layer network and uses a residual network instead of continuous convolution operation, thereby improving the poor real-time operation and low accuracy of multi-ship target tracking.…”

A Hybrid Excitation Model Based Lightweight Siamese Network for Underwater Vehicle Object Tracking Missions

“…The article [17,18] proposed an underwater cable visual tracking system, which integrates the information collected by optical vision and acoustic vision to locate and track the cable. The article [19,20] proposed improved algorithms based on YOLOv4 to detect and track underwater organisms and multi-ship targets. Ye et al [21] proposed a Bayesian-Transformer Neural Network to complete the ship target identification task using track information.…”