Proceedings of the 6th International Conference on Advances in Image Processing最新文献_第2页

Deep learning for image segmentation: Ultrasound image segmentation of thyroid nodules based on U_Net 图像分割的深度学习:基于U_Net的甲状腺结节超声图像分割

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577144

Xueting Zhou, Yan Chen, Shoushan Liu

引用次数: 1

Water Surface Oil Film Inversion Method Based on Infrared Imager 基于红外成像仪的水面油膜反演方法

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577124

Shuai Xu, Jin Xu, Bo Li, Rong Chen

引用次数: 0

An Attention Based Network for Two-dimensional Hand Pose Estimation 基于注意力的二维手部姿态估计网络

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577133

Yujie Fang, Junfan Wang, Yi Chen, Mingyu Gao, Hongtao Zhou, Yaonong Wang

引用次数: 0

Characterization Test for Multivariate Scale Mixtures of Skew- Normal Distributions 偏态-正态分布多元尺度混合的特征检验

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577138

Yan Su, Yue Wu, Jiangchao Zhu

引用次数: 0

Remote Sensing Information Extraction and Dynamic Change Analysis of Leizhou Peninsula Coastline 雷州半岛海岸线遥感信息提取与动态变化分析

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577143

Mingfa Wu, Fengyi Li, Yaoyao Liu, Yao Huang, Yiting Zhou, Xianjun Pan

{"title":"Remote Sensing Information Extraction and Dynamic Change Analysis of Leizhou Peninsula Coastline","authors":"Mingfa Wu, Fengyi Li, Yaoyao Liu, Yao Huang, Yiting Zhou, Xianjun Pan","doi":"10.1145/3577117.3577143","DOIUrl":"https://doi.org/10.1145/3577117.3577143","url":null,"abstract":"With the rapid expansion of the scale of urbanization and the rapid economic and social development of coastal areas, the use changes of the coastline and coastal areas of the Leizhou Peninsula is increasing. Employing envi5.1 and arcgis10.2 tools, the normalized difference water index (NDWI) was used to process the image, and the water and land separation was carried out according to the threshold segmentation method. The data of the coastline in 2001, 2008, 2015 and 2020 were extracted from the interpretation of the remote sensing image maps, and the results of the automatic computer interpretation were examined using the fixed-sample visual interpretation method to analyze the coastline dynamics of the Leizhou Peninsula in the past 20 years. The results showed that: (1) From 2001 to 2020, the total length of the coastline of Leizhou Peninsula showed an increasing trend, a total increase of 95.98km, and annual variation was 4.80km; (2) From 2001 to 2008, the coastline increased the most, with an increase of 44.25km; from 2008 to 2015, the increase of the coastline was smaller, with an increase of 18.69km; from 2015 to 2020, the coastline increased by 33.04km; (3) The areas with large changes in coastline length were Xuwen county, Leizhou city, and Potou district, which increased by 38.29km, 34.21km, and 18.86km respectively; (4) The areas with the most complex coastline changes were mainly concentrated in Potou district, Xuwen county, Leizhou city and Suixi county for economic development, tourism development, marine aquaculture and other areas. In this regard, it was proposed to strengthen the basic dynamic information monitoring of the coastline, carry out the repair and survey of the coastline in a timely manner, grasp the utilization information of the coastline, and implement the task of protecting the coastline resources.","PeriodicalId":309874,"journal":{"name":"Proceedings of the 6th International Conference on Advances in Image Processing","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115292718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Improved Defect Detection Algorithm for Industrial Products via Lightweight Convolutional Neural Network 基于轻量级卷积神经网络的工业产品缺陷检测改进算法

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577140

Bo Hu, Donghao Zhou, Quhua Wu, Jinrong Dong, Sheng Kuang, Jie Huang

引用次数: 0

A Real Time Mask Wearing Detection Based on Lightweight CenterNet in Complex Scenes 基于轻量级CenterNet的复杂场景面具佩戴实时检测

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577130

Keqiao Huang, Linyan Ling, Tianlang Tan, Jin Zhan, Zhenmeng Yue, Si Tang, Zhiyong Lin, Guiyuan Xie

{"title":"A Real Time Mask Wearing Detection Based on Lightweight CenterNet in Complex Scenes","authors":"Keqiao Huang, Linyan Ling, Tianlang Tan, Jin Zhan, Zhenmeng Yue, Si Tang, Zhiyong Lin, Guiyuan Xie","doi":"10.1145/3577117.3577130","DOIUrl":"https://doi.org/10.1145/3577117.3577130","url":null,"abstract":"CenterNet is a one-stage target detector based on key points with high detection accuracy. However, its backbone is Hourglass network with a large number of parameters, the recognition speed is slow and cannot be recognized in real time. In this paper, we proposes a lightweight Hourglass network based on CenterNet model for mask wearing detection. Firstly, we adopts the depth wise separable convolution network in the reverse residual block of the Hourglass network. In the upsampling and downsampling block, different stride set and two branches are used to reduce the number of model parameters and improve the detection speed. Secondly, we redefine the focal loss function which can correlate the loss values of two Hourglass networks and complement each other to improve the accuracy of difficult targets in complex environments. Finally, in order to improve the test robustness of the method, we constructed a data set of masks under different challenge scenarios. The experimental results show that the average accuracy of our method is 0.922 and the parameters are reduced to 1/25 of CenterNet, and the detection speed is increased by nearly 3 times. Our method can achieve real-time mask wearing detection in videos with better robustness, which provides practicality for deploying the network model to mobile terminals.","PeriodicalId":309874,"journal":{"name":"Proceedings of the 6th International Conference on Advances in Image Processing","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132172528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hyperspectral Image Residual Denoising Network Based on Mixed-Domain Attention Mechanism 基于混合域注意机制的高光谱图像残差去噪网络

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577137

Huan Yang, Juan Xu, Kunhua Liu, Xinyu Lin

{"title":"Hyperspectral Image Residual Denoising Network Based on Mixed-Domain Attention Mechanism","authors":"Huan Yang, Juan Xu, Kunhua Liu, Xinyu Lin","doi":"10.1145/3577117.3577137","DOIUrl":"https://doi.org/10.1145/3577117.3577137","url":null,"abstract":"Hyperspectral images (HSIs) contain not only spatial information, but also detail information on spectrum that reflects the internal features of objects, which can be used to monitor crop growth, for example. It is noteworthy that noises are inevitably introduced in the obtained HSIs due to the imperfection of imaging equipment and data transmission process, which will probably lead to misjudging the species of objects. Currently, HSIs-denoising methods based on deep learning have received considerable amount of attention and achieved promising results. However, these methods did not consider the interdependence among the three domains of HSIs. Based on this, we present a mixed-domain attention-based residual denoising network (for short named MA-RDN), so as to better the noises suppression by taking all the three domains into consideration. Different from existing methods, we introduce a mixed-domain attention module, which consists of three branches, respectively modeling the correlation between two of the domains. In this way, the model is guided to simultaneously focus on all the cross-domain features that are influential in denoising tasks. We take the average value of the three branches as the module's output. Then, a sparse feature extraction subnetwork is designed to preserve spatial-spectral features of HSIs as many as possible, which contains several multiscale structures and channel attentions. In order to avoid the gradient disappearance and model degradation caused by the deepening of the network, we utilize two weighted skip connections in the output. Simulation experiments show that, in different noise conditions, the peak signal-to-noise ratio PSNR of our method is increased of about 1.6 that compared with the Cao et al's GRN [11] method, and the structural similarity SSIM is slightly better than it.","PeriodicalId":309874,"journal":{"name":"Proceedings of the 6th International Conference on Advances in Image Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127981607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On Greedy Kaczmarz Method with Uniform Sampling for Consistent Tensor Linear Systems Based on T-Product: tGK method for consistent tensor linear systems 基于T-Product的一致张量线性系统的一致采样贪心Kaczmarz方法:一致张量线性系统的tGK方法

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577127

Yimou Liao, Tianxiu Lu

引用次数: 0

Research on Campus Indoor and Outdoor Unmanned Vehicle Navigation Technology 校园室内外无人驾驶车辆导航技术研究

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577128

Xinyu Cheng, Zhaoyi Li, Yuanyuan Zhu, Yanqing Wang

引用次数: 0