Search

Objective: The shallow underwater environment is complex, with problems of color shift, uneven illumination, blurring, and distortion in the imaging process. These scenes are very unfavorable for the reasoning of the detection network. Additionally, typical object identification algorithms struggle to maintain high resilience in underwater environments due to picture domain offset, making underwater object detection problematic. Methods: This paper proposes a single-stage detection method with the double enhancement of anchor boxes and features. The feature context relevance is improved by proposing a composite-connected backbone network. The receptive field enhancement module is introduced to enhance the multi-scale detection capability. Finally, a prediction refinement strategy is proposed, which refines the anchor frame and features through two regressions, solves the problem of feature anchor frame misalignment, and improves the detection performance of the single-stage underwater algorithm. Results: We achieved an effect of 80.2 mAP on the Labeled Fish in the Wild dataset, which saves some computational resources and time while still improving accuracy. On the original basis, UWNet can achieve 2.1 AP accuracy improvement due to the powerful feature extraction function and the critical role of multi-scale functional modules. At an input resolution of 300 × 300, UWNet can provide an accuracy of 32.4 AP. When choosing the number of prediction layers, the accuracy of the four and six prediction layer structures is compared. The experiments show that on the Labeled Fish in the Wild dataset, the six prediction layers are better than the four. Conclusion: The single-stage underwater detection model UWNet proposed in this research has a double anchor frame and feature optimization. By adding three functional modules, the underwater detection of the single-stage detector is enhanced to address the issue that it is simple to miss detection while detecting small underwater targets. [ABSTRACT FROM AUTHOR]

Purpose. In order to solve the problems of small face image samples, high size, low structure, no label, and difficulty in tracking and recapture in security videos, we propose a popular multiscale facial feature manifold (MSFFM) algorithm based on VGG16. Method. We first build the VGG16 architecture to obtain face features at different scales and construct a multiscale face feature manifold with face features at different scales as dimensions. At the same time, the recognition rate, accuracy rate, and running time are used to evaluate the performance of VGG16, LeNet-5, and DenseNet on the same database. Results. From the results of comparative experiments, it can be seen that the recognition rate and accuracy of VGG16 are the highest among the three networks. The recognition rate of VGG16 is 97.588%, and the accuracy is 95.889%. And the running time is only 3.5 seconds, which is 72.727% faster than LeNet-5 and 66.666% faster than DenseNet. Conclusion. The model proposed in this paper breaks through the key problem in the face detection and tracking problem in the public security field, predicts the position of the face target image in the time dimension manifold space, and improves the efficiency of face detection. [ABSTRACT FROM AUTHOR]

The trajectory optimization of automatic spraying robot is still a challenging problem, which is very important in the whole spraying work. Spray trajectory optimization consists of two parts: spray space path and end-effector moving speed. A large number of spraying experiments have proved that it is very important to find the best initial trajectory of spraying. This paper presents an automatic spray trajectory optimization that is based on the Bézier surface. Spray the workpiece for Bezier triangular surface modeling and find the best initial trajectory of the spraying robot, establish the appropriate spraying model, plan the appropriate space path, and finally plan the trajectory optimization along the specified painting path. The validity and practicability of the method presented in this paper are proved by an example. This method can also be extended to other applications. [ABSTRACT FROM AUTHOR]

When the autonomous underwater vehicle (AUV) traces the trajectory under complex hydrological conditions, the real-time performance of system is slow and the accuracy of tracking is poor. To solve this problem, an adaptive predictive control method based on Laguerre function is designed in this paper. This method contains two parts: one is the adaptive MPC module which is used to track the trajectory accurately; the other is the Laguerre function module which is applied to reduce computations significantly. In the adaptive MPC module, the recursive least squares algorithm is introduced to identify the model parameters of the system to improve the accuracy and the robustness. However, this method may cause a great increase in computation when AUV works in the complex environment. Therefore, in Laguerre function, one reconstruction of the controller input variables is introduced to reduce the matrix order of the objective function. The simulation results show that the designed method has a good performance in the respects of the dynamic, the anti-interference and the robustness when AUV tracks the trajectory with the less amount of calculation. • It proposed a five-degree-of-freedom linear model for AUV. And the adaptive MPC strategy is established based on this model. • It solves the problem of parameter adaptation in traditional MPC and the problem of the error in linearization process. • The internal matrix of controller is reconstructed with Laguerre function to improve the response speed of the controller. [ABSTRACT FROM AUTHOR]