Mural Anomaly Region Detection Algorithm Based on Hyperspectral Multiscale Residual Attention Network

Mural paintings hold significant historical information and possess substantial artistic and cultural value.However,murals are inevitably damaged by natural environmental factors such as wind and sunlight,as well as by human activities.For this reason,the study of damaged areas is crucial for mural restoration.These damaged regions differ significantly from undamaged areas and can be considered abnormal targets.Traditional manual visual processing lacks strong characterization capabilities and is prone to omissions and false detections.Hyperspectral imaging can reflect the material properties more effectively than visual characterization methods.Thus,this study employs hyperspectral imaging to obtain mural information and proposes a mural anomaly detection algorithm based on a hyperspectral multi-scale residual attention network(HM-MRANet).The innovations of this paper include:(1)Constructing mural painting hyperspectral datasets.(2)Proposing a multi-scale residual spectral-spatial feature extraction module based on a 3D CNN(Convolutional Neural Networks)network to better capture multiscale information and improve performance on small-sample hyperspectral datasets.(3)Proposing the Enhanced Residual Attention Module(ERAM)to address the feature redundancy problem,enhance the network’s feature discrimination ability,and further improve abnormal area detection accuracy.The experimental results show that the AUC(Area Under Curve),Specificity,and Accuracy of this paper’s algorithm reach 85.42%,88.84%,and 87.65%,respectively,on this dataset.These results represent improvements of 3.07%,1.11%and 2.68%compared to the SSRN algorithm,demonstrating the effectiveness of this method for mural anomaly detection.

Sand-bed defect recognition for 3D sand printing based on deep residual network

The 3D sand printing(3DSP),by binder jetting technology for rapid casting,has a pivotal role in promoting the development of the traditional casting industry as a result of producing high-quality and economical sand molds.This work presents an approach for monitoring and analyzing powder sand-bed images to serve as a real-time control system in a 3DSP machine.A deep residual network(ResNet)is used to classify the defects occurring during the powder spreading stage of the process.Firstly,a pre-trained network was applied as the initial parameter;then it was fine-tuned on the labelled defective sample dataset to accomplish the task,which defines the sand-bed defects induced in the 3DSP processing.Furthermore,the recognition and positioning of sand-bed defects were readily achieved by dividing the sand-bed images into blocks.Experiments show that the fine-tuned network has a 98.7%classification accuracy on the validation dataset of sand-bed defects and 95.4%recognition accuracy for the sand-bed images.

Behavior recognition algorithm based on the improved R3D and LSTM network fusion

Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.

3-Dimensional Bag of Visual Words Framework on Action Recognition

Human motion recognition plays a crucial role in the video analysis framework.However,a given video may contain a variety of noises,such as an unstable background and redundant actions,that are completely different from the key actions.These noises pose a great challenge to human motion recognition.To solve this problem,we propose a new method based on the 3-Dimensional(3D)Bag of Visual Words(BoVW)framework.Our method includes two parts:The first part is the video action feature extractor,which can identify key actions by analyzing action features.In the video action encoder,by analyzing the action characteristics of a given video,we use the deep 3D CNN pre-trained model to obtain expressive coding information.A classifier with subnetwork nodes is used for the final classification.The extensive experiments demonstrate that our method leads to an impressive effect on complex video analysis.Our approach achieves state-of-the-art performance on the datasets of UCF101(85.3%)and HMDB51(54.5%).

Improved Medical Image Segmentation Model Based on 3D U-Net

With the widespread application of deep learning in the field of computer vision,gradually allowing medical image technology to assist doctors in making diagnoses has great practical and research significance.Aiming at the shortcomings of the traditional U-Net model in 3D spatial information extraction,model over-fitting,and low degree of semantic information fusion,an improved medical image segmentation model has been used to achieve more accurate segmentation of medical images.In this model,we make full use of the residual network(ResNet)to solve the over-fitting problem.In order to process and aggregate data at different scales,the inception network is used instead of the traditional convolutional layer,and the dilated convolution is used to increase the receptive field.The conditional random field(CRF)can complete the contour refinement work.Compared with the traditional 3D U-Net network,the segmentation accuracy of the improved liver and tumor images increases by 2.89%and 7.66%,respectively.As a part of the image processing process,the method in this paper not only can be used for medical image segmentation,but also can lay the foundation for subsequent image 3D reconstruction work.

基于双注意力融合和残差优化的点云语义分割

在直接处理原始点云的语义分割算法中,存在局部特征提取模块细粒度特征描述能力不足和逐步下采样使得网络深度受到限制的问题。提出一种双注意力特征增强模块,其中点注意模块学习邻域点之间的相互关联性,捕捉上下文信息,提高局部特征的分辨能力,通道注意模块聚合通道结构信息,减少噪声影响。构建编码器多尺度残差结构增加网络深度,避免下采样造成的关键点信息丢失。方法在S3DIS数据集上准确率为88.9%,平均交并比为70.7%;在Semantic3D数据集上准确率为95.8%,平均交并比为78.5%。实验结果表明,所提出的算法对物体边缘特征具有良好的区分性,具有更好的泛化性能。