发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems最新文献

筛选
英文 中文
Golf Swing Correction Based on Deep Learning Body Posture Recognition 基于深度学习身体姿势识别的高尔夫挥杆校正
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480713
Gaoyue Sun
{"title":"Golf Swing Correction Based on Deep Learning Body Posture Recognition","authors":"Gaoyue Sun","doi":"10.1145/3480651.3480713","DOIUrl":"https://doi.org/10.1145/3480651.3480713","url":null,"abstract":"With the rapid development of society and economy, people pay more and more attention to sports. Among them, golf has become more and more popular in China. However, golf swings are highly refined and usually require to be instructed by professional coaches. Actually, the time and economic cost of finding coaches have caused some degree of inconvenience to fast-paced urbanites. And sometimes wrong actions are difficult to be detected with naked eyes. This problem can be effectively solved by applying computerized human body recognition technology to the correction of golf swing. Based on the existing visual solutions for human pose recognition. This paper proposed a method of key frame detecting in video streams, and proposed a posture restoration based on pseudo angular velocity for the error detection problem of the existing Openpose. By quickly detecting key frames in the video stream, not only key skeleton information can be quickly extracted for golf action comparison, but also the amount of calculation can be reduced.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122785985","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: 2
Experimental Study on the Effect of Loss Function on Object Detection 损失函数对目标检测影响的实验研究
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480690
Qianyu Cao
{"title":"Experimental Study on the Effect of Loss Function on Object Detection","authors":"Qianyu Cao","doi":"10.1145/3480651.3480690","DOIUrl":"https://doi.org/10.1145/3480651.3480690","url":null,"abstract":"Abstract. As a classic task in the field of computer vision, the purpose of Object Detection is to find out all the objects of interest in the image and determine their location and size. With the development of neural network technology, Object Detection has entered the era of deep learning. At present, the object detector is divided into two categories: Two-Step detector and One-step detector. The loss function is an important part of the object detector. This paper introduces six loss functions: Smooth L1 Loss, Balanced L1 Loss, IoU Loss, GIoU Loss, DIoU Loss and CIoU Loss. Among these six loss functions, we select the three loss functions of Smooth L1 Loss, Balanced L1 Loss and IoU Loss to experiment. The main purpose of this experiment is to explore and compare the effect of loss function on the performance of Object Detection algorithm. In the experiment, Faster-RCNN and Retinanet represent two different kinds of detectors. We introduce the loss function into the detector in turn and evaluate the performance of the detector using the Pascal VOC0712 dataset. In this experiment, we used the object detection toolbox mmdetection. Meanwhile, the evaluation metric used to evaluate the detector are Recall AP and mAP. The experimental results show that some loss functions have the opposite effect on two different detectors.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124902401","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
Metric Learning For Context-Aware Recommender Systems 上下文感知推荐系统的度量学习
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480695
Firat Ismailoglu
{"title":"Metric Learning For Context-Aware Recommender Systems","authors":"Firat Ismailoglu","doi":"10.1145/3480651.3480695","DOIUrl":"https://doi.org/10.1145/3480651.3480695","url":null,"abstract":"Context-Aware Recommender Systems (CARS) refer to recommender systems that can incorporate side information regarding to users, items and ratings. In the present study, we are concerned with CARS, where the side information is provided in the form of item-attribute matrix with entries indicating whether an item has an attribute. We propose to multiply this matrix with user-item rating matrix to represent the the users in the attribute space of the items. We then apply a popular metric learning method, specifically Mahalanobis Metric Learning (MMC), in the attribute space to calculate the distances between the users and their favorite items as less as possible. We recommend the n items that are closest to the users based on these calculations. We verify the effectiveness of the proposed method on two famous MovieLens datasets that differ in size showing that using metric learning increases the success of CARS up to 7% in comparison with using the traditional cosine similarity.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121699552","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
A Tensor Train Based Change Detection Method for Multitemporal Hyperspectral Images 基于张量序列的多时相高光谱图像变化检测方法
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480666
Muhammad Sohail, Zhao Chen, Guohua Liu
{"title":"A Tensor Train Based Change Detection Method for Multitemporal Hyperspectral Images","authors":"Muhammad Sohail, Zhao Chen, Guohua Liu","doi":"10.1145/3480651.3480666","DOIUrl":"https://doi.org/10.1145/3480651.3480666","url":null,"abstract":"Remote sensing change detection (CD) using multitemporal hyperspectral images (HSI) is a process of extraction of change features and classification. However, the high dimensionality of HSI not only leads to expensive computation but also suffers from spectral-spatial variability and inner-class heterogeneity. In this paper, we proposed two algorithms for CD based on the tensor train (TT) decomposition, which uses a well-balanced matricization strategy to capture hidden information from tensors. The first algorithm TT decomposition uses nuclear norm hence named TTNN_CD and the second algorithm uses multilinear matrix factorization bypassing the expensive SVD named TTMMF_CD. We use -augmentation (KA) scheme to represent the low-order tensor into a high-order tensor to extract change features efficiently. The experiments reveal that TT-based CD outperforms its tensor counterpart, HOSVD, and some other commonly used approaches.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126385391","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: 1
Infrared and visible image fusion method based on LatLRR and ICA 基于LatLRR和ICA的红外与可见光图像融合方法
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480656
Ying Huang, Zongyu Zhang, Xilin Wen
{"title":"Infrared and visible image fusion method based on LatLRR and ICA","authors":"Ying Huang, Zongyu Zhang, Xilin Wen","doi":"10.1145/3480651.3480656","DOIUrl":"https://doi.org/10.1145/3480651.3480656","url":null,"abstract":"To solve the problem of missing lots of texture details in the fusion image, we propose a new fusion method of infrared and visible images based on latent low-rank representation(LatLRR) and independent component analysis(ICA) in this paper. Firstly, the source image is decomposed into low-rank components, sparse components, and noise components by LatLRR. Secondly, ICA is utilized for the low-rank part of infrared image and visible image to obtain the main difference between two source images. Then, the image containing more information is determined by comparing the entropy of two source images and it is employed as a benchmark. Finally, the fused image is accomplished by connecting the benchmark result, the low-rank components, and the sparse components of another image according to the result obtained by ICA. Compared with other fusion methods, experimental results demonstrate that the proposed method has better visual effects and evaluation indicators.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122520128","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
Research on distortion correction of particleboard surface defect image 刨花板表面缺陷图像畸变校正研究
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480663
Ziyu Zhao, Hui Guo, Xiaoxia Yang, Zhedong Ge, Yucheng Zhou
{"title":"Research on distortion correction of particleboard surface defect image","authors":"Ziyu Zhao, Hui Guo, Xiaoxia Yang, Zhedong Ge, Yucheng Zhou","doi":"10.1145/3480651.3480663","DOIUrl":"https://doi.org/10.1145/3480651.3480663","url":null,"abstract":"In order to improve the barrel distortion of the acquired image in the surface defect detection of particleboard. In this paper, a method based on Zhang Zhengyou calibration is used to solve the camera distortion problem, so as to improve the accuracy of surface defect image processing of particleboard. Firstly, the camera was calibrated, and then the improvement of the camera correction information accuracy was judged by the correction of external parameters and reprojection error of image visualization. The internal parameter matrix and distortion coefficient of the camera were calculated accurately, and the barrel distortion of the image was corrected finally. The position of the inner corner points detected by the camera is accurate, and the reprojected points were included in the inner corner points, which improves the correction accuracy of the image to be measured. It can be clearly seen from the external parameters of visualization that the placement of the 16 sample patterns is within the range of vision. The oblique Angle deviation between the images is within 150mm. The average value of the re projection error was 0.1570 pixels calculated by the point of the camera re projection, which meets the need of correction. In conclusion, the image quality can be improved by accurately correcting the distortion of particleboard image. It lays a foundation for the surface defect extraction of particleboard.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134478908","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: 1
Improved Correlation Filter Visual Tracker By Using Scale Estimation Network 基于尺度估计网络的改进相关滤波视觉跟踪器
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480657
Xiao Tan, Chunsheng An
{"title":"Improved Correlation Filter Visual Tracker By Using Scale Estimation Network","authors":"Xiao Tan, Chunsheng An","doi":"10.1145/3480651.3480657","DOIUrl":"https://doi.org/10.1145/3480651.3480657","url":null,"abstract":"Object tracking is to accurately track target information in continuous video sequences, and the bounding box of target is also indispensable as an important metric for evaluating tracker algorithms. In recent years, correlation filter trackers have been successfully achieved powerful robustness. To estimate object scale, most correlation filter trackers use a simple multi-scale search that has limited the development of correlation filters in precision tracking. We propose a scale estimation network to solve the problem, which uses the experience of bounding box estimation in object detection. Through extensive offline learning, high-level knowledge is incorporated into target estimation. Our scale estimation network is trained to optimize object scale. We further introduce the fusion method between correlation filter and scale estimation network coordinated operation. Our improved tracker evaluated on three benchmarks: OTB2015, VOT2018, and VOT2019. The evaluation experiments on these benchmarks demonstrate that our tracker has better performance.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125623792","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
Method of physical inventory checking on cigarette stereoscopic warehouse based on UAV 基于无人机的卷烟立体仓库盘点方法
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480655
Zhihao Zhao, Ronggui Dao, Haitao Zhang, Fanwei Zhang, Jianfeng Zeng, Chao Chen
{"title":"Method of physical inventory checking on cigarette stereoscopic warehouse based on UAV","authors":"Zhihao Zhao, Ronggui Dao, Haitao Zhang, Fanwei Zhang, Jianfeng Zeng, Chao Chen","doi":"10.1145/3480651.3480655","DOIUrl":"https://doi.org/10.1145/3480651.3480655","url":null,"abstract":"The elevated warehouse is the initial place of the cigarette end-product. It is an important link between the workshop and the delivery of cigarette. It undertakes large storage tasks of cigarette end-product in the limited space. The traditional manual inventory is difficult because of the large tunnel depth, high building height and dense distribution of goods. Based on the actual situation of the elevated warehouse of cigarette products, by learning the inventory management technology of advanced enterprises outside the tobacco industry, combined with the guidelines and policies of the tobacco industry, applying artificial intelligence technology, this paper puts forward a scheme of UAV inventory of cigarette end-product.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124760439","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: 1
Research of DBN PLSR algorithm Based on Sparse Constraint 基于稀疏约束的DBN PLSR算法研究
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480688
Mengxi Liu, Yingliang Li
{"title":"Research of DBN PLSR algorithm Based on Sparse Constraint","authors":"Mengxi Liu, Yingliang Li","doi":"10.1145/3480651.3480688","DOIUrl":"https://doi.org/10.1145/3480651.3480688","url":null,"abstract":"DBN is a generative model based on unsupervised learning, with strong computing and information processing capabilities. But at the same time, there are some drawbacks: the model is constructed through intensive expression, which leads to relatively low computing performance of the network. The network optimization method based on the BP algorithm is easy to fall into a local minimum, which makes DBN fine-tuning accuracy is reduced. In order to obtain a DBN that is efficient and can avoid local optimization, the paper designs a DBN based on adaptive sparse representation and partial least square regression (PLSR) fine-tuning. First, two regularization factor terms are introduced to punish the densely expressed connection characteristics, thereby constructing an sparse RBM. Secondly, PLSR method is adopted instead of the BP algorithm, and a PLSR model is established between every two layers from the output layer to the input layer. The experiment proved the effectiveness of optimized DBN in improving network performance and learning performance. Project Supported by Natural Science Basic Research Program of Shaanxi (Program No.2020JQ-788). Project Supported by Natural Science Basic Research Program of Shaanxi (ProgramNo.2020JM-542).","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116828025","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
Toward Tracing the Source of Web Attacks Targeted at Web Applications 追踪针对Web应用程序的Web攻击的来源
Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2021-07-28 DOI: 10.1145/3480651.3480654
Shuo Wen, Qi Wu, Xingmin Wu, Yi Ling, Zhuolin Ye
{"title":"Toward Tracing the Source of Web Attacks Targeted at Web Applications","authors":"Shuo Wen, Qi Wu, Xingmin Wu, Yi Ling, Zhuolin Ye","doi":"10.1145/3480651.3480654","DOIUrl":"https://doi.org/10.1145/3480651.3480654","url":null,"abstract":"Nowadays, with the popularity of the computer network, we are facing to complex web service functions and rampant web attacks. In this paper, a research on web attack traceback technology is present for accurately identifying attack source, timely blocking target IP, patching service vulnerability, storing and identifying attack vectors. Existing traceback systems need to change web-based business code or architecture of server route, however, our traceback system can analyze and manage web access behaviors via proxy server, require no agent, and simulate the traceback to source of web attack with the features such as high compatibility, low performance overhead and quick traceback.","PeriodicalId":305943,"journal":{"name":"Proceedings of the 2021 International Conference on Pattern Recognition and Intelligent Systems","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133634007","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
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信