Two-stream convolution network (2SCN) is a classical method of action recognition. It is capable of extracting action information from two dimensions: spatial and temporal streams. However, the method of extracting motion features from a spatial stream is single-frame recognition, and there is still room for improvement in the perception ability of appearance coherence features. The classical two-stream convolution network structure is modified in this paper by utilizing the strong mining capabilities of the bidirectional gated recurrent unit (BiGRU) to allow the neural network to extract the appearance coherence features of actions. In addition, this paper introduces an attention mechanism (SimAM) based on neuroscience theory, which improves the accuracy and stability of neural networks. Experiments show that the method proposed in this paper (BS-2SCN, BiGRU-SimAM Two-stream convolution network) has high accuracy. The accuracy is improved by 2.6% on the UCF101 data set and 11.7% on the HMDB51 data set.

https://www.mdpi.com/2076-3417/12/12/5784/pdf?version=1654762588

Human Action Recognition Based on Improved Two-Stream Convolution Network

Membrane fouling diagnosis of membrane components based on multi-feature information fusion

In order to make it easier to extract fault features, reduce model complexity and improve the accuracy of membrane fouling diagnosis on membrane modules, a membrane module fault diagnosis method based on attention mechanism and convolutional neural network (ECA-CNN) is proposed in this study. First, the convolution kernel is used to extract the image features of the input layer. At the same time, a rectified linear unit (ReLU) is connected after each convolution layer, and a batch normalization layer (BN) is added to solve the problem of internal co variate shift, so as improving the expression ability of nonlinear models. Secondly, in batches after the first layer, add the attention mechanism module (ECA), extract the important features and connect to the pooling layer, reduce the network calculation complexity, and improve the accuracy and efficiency of the network. Finally, the membrane module operating data is used as the research object to conduct fault diagnosis experiments as verification. This method can improve the diagnosis accuracy to a large extent, in which the highly difficult fault classification and localization can be accomplished. Besides, the effluent quality from the membrane water treatment system may be improved with this method with less energy consumption, paving the theoretical foundation for actual production. 

Research on the membrane fouling diagnosis of MBR membrane module based on ECA-CNN

Data-attention-YOLO (DAY): A comprehensive framework for mesoscale eddy identification

Intelligent detection of marine organism plays an important part in the marine economy, and it is significant to detect marine organisms quickly and accurately in a complex marine environment for the intelligence of marine equipment. The existing object detection models do not work well underwater. This paper improves the structure of EfficientDet detector and proposes the EfficientDet-Revised (EDR), which is a new marine organism object detection model. Specifically, the MBConvBlock is reconstructed by adding the Channel Shuffle module to enable the exchange of information between the channels of the feature layer. The fully connected layer of the attention module is removed and convolution is used to cut down the amount of network parameters. The Enhanced Feature Extraction module is constructed for multi-scale feature fusion to enhance the feature extraction ability of the network to different objects. The results of experiments demonstrate that the mean average precision (mAP) of the proposed method reaches 91.67% and 92.81% on the URPC dataset and the Kaggle dataset, respectively, which is better than other object detection models. At the same time, the processing speed reaches 37.5 frame per second (FPS) on the URPC dataset, which can meet the real-time requirements. It can provide a useful reference for underwater robots to perform tasks such as intelligent grasping.

/pdf/underwater-object-detection-based-on-improved-efficientdet-2t7bblm7.pdf

Underwater Object Detection Based on Improved EfficientDet

Marine target detection technology plays an important role in sea surface monitoring, sea area management, ship collision avoidance, and other fields. Traditional marine target detection algorithms cannot meet the requirements of accuracy and speed. This article uses the advantages of deep learning in big data feature learning to propose the YOLOv4 marine target detection method fused with a convolutional attention module. Marine target detection datasets were collected and produced and marine targets were divided into ten categories, including speedboat, warship, passenger ship, cargo ship, sailboat, tugboat, and kayak. Aiming at the problem of insufficient detection accuracy of YOLOv4’s self-built marine target dataset, a convolutional attention module is added to the YOLOv4 network to increase the weight of useful features while suppressing the weight of invalid features to improve detection accuracy. The experimental results show that the improved YOLOv4 has higher detection accuracy than the original YOLOv4, and has better detection results for small targets, multiple targets, and overlapping targets. The detection speed meets the real-time requirements, verifying the effectiveness of the improved algorithm.

https://www.mdpi.com/2073-8994/13/4/623/pdf

Yuchao Wang

Papers

Improved YOLOv4 Marine Target Detection Combined with CBAM