检索结果-内蒙古大学图书馆

2nd Advanced Imaging and Information processing conference, AIIP 2024

作者： Jin, Nanxi xin, Yuelan Deng, Shenghui Chen, Kuan Yang, Lan Huo, Haoyi Zhao, Jia Fang, Huiting Dept. of Physics and Electronic Information Engineering Qinghai Normal University 38 Wusi West Road. Qinghai Xining810001 China State Key Laboratory of Tibetan Language Information Processing and Applications Qinghai Normal University 38 Wusi West Road. Qinghai Xining810001 China Dept. of Computer Science Qinghai Normal University 38 Wusi West Road. Qinghai Xining810001 China

ISBN: (纸本)9781510683068

To enhance the accuracy of existing algorithms in the task of retinal vessel image segmentation, this paper proposes the incorporation of two modified convolutional blocks, in lieu of traditional ones, within the framework of the U-Net neural network, aiming to strengthen the extraction of detailed features. Firstly, a convolutional block equipped with local channel attention is devised for feature extraction in the shallow layers of the network. Secondly, a convolutional block incorporating global channel attention is introduced for feature extraction in the deeper layers. Lastly, skip connections are employed to feed the features extracted from the shallow layers into the deeper layers. Experimental results demonstrate that the proposed retinal vessel segmentation algorithm achieves a Dice coefficient of 88.21% and a sensitivity of 87.16%, marking improvements of 2.25% and 1.64% respectively over the original UNet network. © 2024 SPIE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Neural Photo-Finishing

引用

ACM TRANSACTIONS ON GRAPHICS 2022年第6期41卷 p1-15页

作者： Tseng, Ethan Zhang, Yuxuan Jebe, Lars Zhang, Xuaner xia, Zhihao Fan, Yifei Heide, Felix Chen, Jiawen Princeton Univ Princeton NJ 08544 USA Adobe San Jose CA USA

image processing pipelines are ubiquitous and we rely on them either directly, by filtering or adjusting an image post-capture, or indirectly, as image signal processing (ISP) pipelines on broadly deployed camera systems. Used by artists, photographers, system engineers, and for downstream vision tasks, traditional image processing pipelines feature complex algorithmic branches developed over decades. Recently, image-to-image networks have made great strides in image processing, style transfer, and semantic understanding. The differentiable nature of these networks allows them to fit a large corpus of data;however, they do not allow for intuitive, fine-grained controls that photographers find in modern photo-finishing tools. This work closes that gap and presents an approach to making complex photo-finishing pipelines differentiable, allowing legacy algorithms to be trained akin to neural networks using first-order optimization methods. By concatenating tailored network proxy models of individual processing steps (e.g. white-balance, tone-mapping, color tuning), we can model a non-differentiable reference image finishing pipeline more faithfully than existing proxy image-to-image network models. We validate the method for several diverse applications, including photo and video style transfer, slider regression for commercial camera ISPs, photography-driven neural demosaicking, and adversarial photo-editing.

关键词： image processing photo-finishing raw processing

来源：评论

学校读者我要写书评

暂无评论

Brain tumor classification model of ResNet-50 network based on different data enhancement algorithms 8

Brain tumor classification model of ResNet-50 network based ...

引用

8th International conference on Intelligent Computing and Signal processing, ICSP 2023

作者： Zou, Menghan Ma, Mingze Wang, Anan Li, Yujie Toe, Teoh Teik Harbin Institute of Technology Weihai School of Computer Science and Technology WeiHai China Harbin Institute of Technology Weihai Welding Technology and Engineering WeiHai China Harbin Institute of Technology Weihai Marine Information Engineering WeiHai China Harbin Institute of Technology Weihai Information Management and Information System WeiHai China Nanyang Technological University Ntu Business Ai Lab Singapore

ISBN: (纸本)9798350302455

The accuracy and stability of brain tumor MRI image classification is significant for the healthcare system, but the traditional models have the defects of difficulty in handling complex features and unstable classification. In this paper, we propose a novel brain tumor classification model based on residual neural network, and use three different data enhancement algorithms: geometric transformation, mixup, and SamplePairing to process a dataset containing four different types of brain tumor images, and finally evaluate the classification effect of our proposed model. Among them, the best results were achieved by using geometric transformations for data enhancement. © 2023 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

The Real-Time High-Voltage Switch Position Detection Method 3

The Real-Time High-Voltage Switch Position Detection Method

引用

3rd IEEE International conference on Electrical Engineering, Big Data and algorithms, EEBDA 2024

作者： Yang, Jinming Ma, Jing Yang, Jihaoyu Luo, Weiqi Shaanxi University of Science & Technology Xi'an China

ISBN: (纸本)9798350380989

This method discloses the real-time high-voltage switch position detection method, which is implemented in accordance with the following steps: installing a coms photoelectric sensor on the video acquisition unit, and installing the video acquisition unit at a specified position on the isolation switch housing;illuminating the inside of the isolation switch through LED devices in the switch detection device, and collecting the action video of the isolation switch as the raw video signal through the video acquisition unit. The video acquisition unit collects the action video of the isolating switch as the original video signal;the coms photoelectric sensor converts the light signal in the original video signal into an electric signal, and then sends the electric signal to the video server for processing to get the RGB spatial area image;the RGB spatial area image is transmitted to the on-line monitoring backstage system, and the movement trajectory of the high-voltage switch is judged through the LK optical flow method to get the actual position of the contacts. This detection method solves the hidden problem of GIS equipment operation and maintenance that the current GIS products need manual observation and the data cannot be transmitted to the background in real time. © 2024 IEEE.

关键词： High-Voltage Switch Detection Real-time Monitoring Smart Electronics

来源：评论

学校读者我要写书评

暂无评论

Possibilistic Fuzzy C-Means Clustering with region-level Information for image Segmentation 6

Possibilistic Fuzzy C-Means Clustering with region-level Inf...

引用

6th International conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Li, Honglei Yu, Haiyan School of Communications and Information Engineering Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

The possibilistic fuzzy c-means clustering (PFCM) algorithm is a hybrid clustering algorithm based on the fuzzy c-means clustering (FCM) algorithm. It can improve the anti-noise ability of FCM and the stability of PCM. However, there are great challenges when it is applied in image segmentation for images with strong noise injection. Therefore, we propose an improved Possibilistic Fuzzy C-Means Clustering with adaptive region-level information (RIPFCM). The first is that both the region-level information and the original information are integrated into the objective function of PFCM. The second is that we introduce a method to adaptively set the weighted factors which are used to balance the influence of the region-level information and the original information. Finally, experiments of color image segmentation show that the proposed RIPFCM method achieves better results compared with several clustering algorithms. © 2023 ACM.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Prediction Of Coal And Gas Outburst Based On Support Vector Machine 2

Prediction Of Coal And Gas Outburst Based On Support Vector ...

引用

2nd International conference on Advanced algorithms and Signal image processing, AASIP 2022

作者： Yabing, M.A. School of Management Xi'an University of Science and Technology Xi'an China

ISBN: (纸本)9781510660571

Coal and gas disasters occur frequently, which not only cause casualties, but also bring economic losses. The prediction of coal and gas outburst has important research significance. In this paper, a security combination prediction model for building projects based on PCA-PSO-SVM is proposed. Principal Component Analysis was used for dimension reduction to remove the principal component with low contribution rate, PSO was used to avoid the blindness of selecting parameters of SVM manually. The average prediction accuracy of this model is 93.85%. Compared with the traditional method, the prediction accuracy and the calculation speed is faster. © 2022 SPIE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Smart and Quick Parking Spot Detection 15

Smart and Quick Parking Spot Detection

引用

15th International conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Veeramalla, Santhosh Kumar Gali, Rama Lakshmi Ranjeeth, M. Tara, Saikumar Hindumathi, V. Bhargava Kumar, L. Bvrit Hyderabad College of Engineering for Women Department of Ece Hyderabad India

ISBN: (纸本)9798350370249

The rapid expansion of urban areas has intensified the challenge of finding parking spaces for drivers. Intelligent parking systems emerge as a crucial solution by providing real-time detection of available spaces. While various methods exist, from basic magnetic sensors to advanced computer vision algorithms, their effectiveness can be hindered by environmental factors. Recognizing the importance of automated systems, this paper focuses on implementing an image processing approach for parking space detection. By strategically placing cameras in parking lots, the system identifies vacant spaces and transforms images to determine availability. Integrating these techniques into mobile applications could further aid drivers in locating parking spots, improving their overall experience. Ultimately, accurate and efficient parking space identification is vital for reducing congestion, enhancing air quality, and improving urban environments. © 2024 IEEE.

关键词： CCTV Computer vision image processing Parking availability Parking guidance Smart parking Sustainable cities

来源：评论

学校读者我要写书评

暂无评论

An Efficient Implementation of the Threshold-based VNG Demosaicing with Reduced Calculations

An Efficient Implementation of the Threshold-based VNG Demos...

引用

2024 Smart systems Integration conference and Exhibition

作者： Alnaser, Yousef Ravichandran, Anbumani Langer, Jan Fraunhofer ENAS Chemnitz Germany TU Chemnitz Chemnitz Germany

ISBN: (纸本)9798350388787;9798350388770

Color Filter Arrays (CFA) are essential components of digital cameras and image sensors to capture the color information needed to produce full-color images from only a single image sensor per pixel. Many methods and algorithms have been proposed to recover the missing color information of CFAs. In this work, we use a simplified version of the Theshold-based Variable Number of Gradients algorithm proposed by Chang et al. to estimate the full-color information from Bayer images. We also show that the slight modification to algorithm does not effect images quality while making it more compatible with hardware. We propose an efficient implementation of the algorithm that reduces the number of calculations per pixel at the cost of increased memory resources. Our implementation targets an image processing pipeline in an FPGA platform which is short on LUTs and FF resources but has DSPs and BRAMs to spare. We buffer the absolute differences and average color components to be shared and re-used between neighboring pixels, on two levels: within the same row, and between different rows. The latter strategy reduces the number of absolute differences calculated every cycle from 32 to 4 and average color components from 32 to 6. However, the memory requirements are increased from storing 4 image rows to 18 image rows. We implement the solutions on an FPGA using high-level synthesis (HLS) and optimize it to further reduce resources.

关键词： Demosaicing Variable Number of Gradients Bayer image FPGA

来源：评论

学校读者我要写书评

暂无评论

Retrofitting a Legacy Cutlery Washing Machine Using Computer Vision 16th

Retrofitting a Legacy Cutlery Washing Machine Using Computer...

引用

16th International conference on Computational Collective Intelligence (ICCCI)

作者： Fwa, Hua Leong Singapore Management Univ 81 Victoria St Singapore 188065 Singapore

ISBN: (纸本)9783031702587;9783031702594

Industry 4.0, the digitalization of manufacturing promises to lead to lowered cost, efficient processes and even discovery of new business models. However, many of the enterprises have huge investments in legacy machines which are not 'smart'. In this study, we thus designed a cost-efficient solution to retrofit a legacy conveyor belt-based cutlery washing machine with a commodity web camera. We then applied computer vision (using both traditional image processing and deep learning techniques) to infer the speed and utilization of the machine. We detailed the algorithms that we designed for computing both speed and utilization. With the existing operational constraints of our client, frequent re-training of the deep learning model for object detection is not feasible. Thus, we compared the generalizability of the two techniques across 'unseen' cutleries and found traditional image processing to be generalizable across 'unseen' images. Our proposed final solution uses traditional image processing for computation of utilization but a hybrid of traditional image processing and deep learning model for speed computation as it is more reliable. Our client has implemented our proposed solution for one conveyor belt-based cutlery washing machine and will be planning to scale this to multiple conveyor belt-based cutlery washing machines.

关键词： Industry 4.0 Computer Vision Deep Learning image processing

来源：评论

学校读者我要写书评

暂无评论

Research on Insulator Defect Detection Algorithm in Different Environments Based on Multi-head Attention Mechanism 4

Research on Insulator Defect Detection Algorithm in Differen...

引用

4th International conference on Electrical Engineering and Control Science, IC2ECS 2024

作者： Liang, Chengliang Ji, Chao Wang, Boya Zhou, Siyuan Xi'an Polytechnic University Xi'an China State Grid Ankang Power Supply Company Ankang China

ISBN: (纸本)9798331510107

The problem of multiple targets, occlusions, small targets, and a complex background in insulator images make it difficult for conventional image processing algorithms to guarantee detection accuracy. An insulator defect detection algorithm based on the Deep Convolution Network and Multi-head Attention Mechanism(MHAM) was proposed in this paper. Firstly, based on You Only Look Once (YOLO)-v5, the MHAM is proposed to obtain rich contextual information in insulator images and improve the accuracy of defect detection. Secondly, Multi-Scale Spatial Pyramid Pooling (MSPP) module is proposed to enhance the efficiency of targets recognition at different scales. Thirdly, the Simplify Optimal Transport Assignment (SimOTA) algorithm is used to improve the traditional Label Allocation Strategy to improve the accuracy of target box detection. Finally, the PIOU, Focal Loss, and Balanced Cross-Entropy functions are used to improve the Loss Function of the model to address the problem of unbalanced samples and to improve the accuracy of algorithm. By using insulator images of 750kV transmission lines in Qinghai to produce the datasets and compared the proposed algorithm with the current mainstream target detection algorithms. Compared with the traditional YOLO-v5, mAP of the algorithm in this paper is improved by 10.82%, the Precision is improved by 14.62%, and Recall is improved by 11.80%. © 2024 IEEE.

关键词： Gluing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：