The shipping industry is developing towards intelligence rapidly. An accurate and fast method for ship image/video detection and classification is of great significance for not only the port management, but also the safe driving of Unmanned Surface Vehicle (USV). Thus, this paper makes a self-built dataset for the ship image/video detection and classification, and its method based on an improved regressive deep convolutional neural network is presented. This method promotes the regressive convolutional neural network from four aspects. First, the feature extraction layer is lightweighted by referring to YOLOv2. Second, a new feature pyramid network layer is designed by improving its structure in YOLOv3. Third, a proper frame and scale suitable for ships are designed with a clustering algorithm to reduced 60% anchors. Last, the activation function is verified and optimized. Then, the detecting experiment on 7 types of ships shows that the proposed method has advantage compared with the YOLO series networks and other intelligent methods. This method can solve the problem of low recognition rate and real-time performance for ship image/video detection and classification with a small dataset. On the testing-set, the final mAP is 0.9209, the Recall is 0.9818, the AIOU is 0.7991, and the FPS is 78–80 in video detection. Thus, this method provides a highly accurate and real-time ship detection method for the intelligent port management and visual processing of the USV. In addition, the proposed regressive deep convolutional network also has a better comprehensive performance than that of YOLOv2/v3.
The Permanent Magnet Synchronous Motor (PMSM) is widely used in many fields. Aiming at nonlinearity, strong coupling and uncertainty of the PMSM, this paper proposes a nonlinear multi-input multi-output (MIMO) decoupling PMSM algorithm based on Active Disturbance Rejection Control (ADRC). A Lower-Upper matrix factorization approach is introduced to solve a general inverse of the measured time-varying matrix in real-time decoupling ADRC. This PMSM is based on the vector control. First, the PMSM model and vector control are simulated. Then, a first-order ADRC is introduced and used to replace the PID controller in the d and q axis of PMSM respectively. The simulation shows that the replaced system has a smaller fluctuation, faster response and better stability. Finally, the nonlinear MIMO decoupling ADRC and its inverse matrix method are deduced. Then, the decoupling PMSM control based on ADRC is verified. The simulation shows that this system has a better static and dynamic performance, and it conforms to the PMSM characteristics better. All this shows that the nonlinear MIMO decoupling ADRC is a better strategy for the PMSM. The presented algorithm also has advantage in method compared with some recent results of decoupling PMSM control.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.