Proceedings of the 2020 4th International Conference on Digital Signal Processing最新文献_第6页

Research on Weak Signal Detection Performance Based on Chaotic Image Intelligent Recognition 基于混沌图像智能识别的弱信号检测性能研究

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408161

Pengjing, Shiyuan Liang, Fuzhou Yang, Changxin Cai

{"title":"Research on Weak Signal Detection Performance Based on Chaotic Image Intelligent Recognition","authors":"Pengjing, Shiyuan Liang, Fuzhou Yang, Changxin Cai","doi":"10.1145/3408127.3408161","DOIUrl":"https://doi.org/10.1145/3408127.3408161","url":null,"abstract":"The noise immune characteristics of chaotic systems can effectively detect useful signals in the background of strong noise. Aiming at the problem that the state of phase space is judged by human eye observation as the main means and lack of reliable theoretical support, a small sample SVM algorithm for intelligent recognition of chaotic images is proposed in this paper. Firstly, the detection flow of Duffing oscillator under the background of strong acoustic noise while drilling is given, and the weak signal detection models of different state space are given based on phase space and Lyapunov index. The simulation is carried out under different SNR and measured data. Finally, the SVM model is used to intelligently identify chaos and other state space results. The simulation results show that the chaotic system can detect the target signal effectively under different SNR. The minimum SNR is about-80dB and the recognition accuracy of SVM intelligent model is 95%. This conclusion verifies the strong noise immunity of Duffing oscillator system and the effectiveness of SVM model recognition image.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131813588","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 Deep Reinforcement Learning based Network Management System in Smart Identifier Network 基于深度强化学习的智能标识网络管理系统

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408173

Shihua Chen, Jia Chen, Jing Chen

引用次数: 2

Locality Preserving based Motion Consensus for Endoscopic Image Feature Matching 基于局部保持的内镜图像运动一致性特征匹配

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408157

Xu Li, Danni Ai, Yakui Chu, Jingfan Fan, Hong Song, Ying Gu, Jian Yang

{"title":"Locality Preserving based Motion Consensus for Endoscopic Image Feature Matching","authors":"Xu Li, Danni Ai, Yakui Chu, Jingfan Fan, Hong Song, Ying Gu, Jian Yang","doi":"10.1145/3408127.3408157","DOIUrl":"https://doi.org/10.1145/3408127.3408157","url":null,"abstract":"Feature matching of endoscopic images is an important and challengeable task for many clinical applications, such as tissue surface reconstruction and object tracking. In this study, we proposed a locality preserving based motion consensus method for endoscopic image feature matching. Firstly, a local distance constraint is applied to maintain the local structure of initial matches derived from the ASIFT algorithm. Secondly, bilateral affine motion boundaries are estimated from the local structure preserving based matches to obtain precise motion constraint. Initial matches that meet the criterion of adaptive threshold of the bilateral affine motion boundaries are considered as final matches. Through considering both locality and global motion coherence of feature points, the proposed method can effectively find reliable matches from initial matches of large outlier ratios. We test our method and four state-of-the-art methods on simulated-nonrigid deformation and simulated-tool occlusion endoscopic images. The proposed method outperforms the other state-of-the-art methods in Precision, Recall, F1-Score, and Accuracy.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114941996","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

Venous Tree Separation based on Local Feature 基于局部特征的静脉树分离

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408202

Yuhan Liu, Tianyu Fu, Qing Guo, Jingfan Fan, Hong Song, Yurong Jiang, Jian Yang

引用次数: 0

Low-latency Block-wise Object Detection Method using SSD for High Resolution Video 基于SSD的高分辨率视频低延迟块对象检测方法

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408167

Kazuki Hozumi, Yoichi Tomioka

{"title":"Low-latency Block-wise Object Detection Method using SSD for High Resolution Video","authors":"Kazuki Hozumi, Yoichi Tomioka","doi":"10.1145/3408127.3408167","DOIUrl":"https://doi.org/10.1145/3408127.3408167","url":null,"abstract":"In recent years, in the fields such as surveillance cameras and in-vehicle camera systems, efficient deep-learning-based object detection methods, such as Single Shot MultiBox Detector (SSD), that do not require window scanning have received a significant attention. However, these methods require a lot of memory and computation. For this reason, when we applying them to higher definition video, it can be necessary to divide the video into multiple blocks for inference processing due to restrictions on memory capacity of GPUs or FPGAs. To avoid accuracy degeneration due to block division, we can use conventional overlapping block technique. However, it increases the latency of object detection because we need to process more blocks. In this paper, we propose a low-latency block-wise object detection method which assigns a different block pattern into each frame, divides each frame based on the block pattern assignment, and integrates the results of multiple frames. In the experiments, the object detection accuracy and latency were evaluated using three data from the Multiple Object Tracking Benchmark dataset 2017. When the movement of object is small, we reduced the latency of human detection by about 40% while the accuracy degeneration is 0% to 2%.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130070972","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

Construction of Block Circulant Measurement Matrix Based on Hybrid Chaos: Bernoulli Sequences 基于混合混沌-伯努利序列的块循环测量矩阵构造

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408151

Yi Sun, Gongfei Han, Lilian Huang, Shiming Wang, Jianhong Xiang

引用次数: 3

Super-resolution Reconstruction of Dual Regular Items Infrared Image Based on Deep Plug-and-Play 基于深度即插即用的双规则项红外图像超分辨率重建

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408162

Xuewei Zhang, Yu Lei

{"title":"Super-resolution Reconstruction of Dual Regular Items Infrared Image Based on Deep Plug-and-Play","authors":"Xuewei Zhang, Yu Lei","doi":"10.1145/3408127.3408162","DOIUrl":"https://doi.org/10.1145/3408127.3408162","url":null,"abstract":"Infrared image has lower resolution, unclear gray level, more concentrated gray distribution and less obvious texture, which is far from meeting the needs of human eyes for resolution, this paper proposes a Super-resolution reconstruction algorithm of dual regular items infrared image based on deep plug-and-play (DMSR). First of all, considering that most algorithms do not estimate the blur kernels accurately in the process of image degradation, the latest deep plug-and-play network (DPSR) is introduced into the algorithm, which proposed a new quality degradation model, DPSR can effectively estimate the blur kernels that leads to image degradation. Secondly, the infrared image texture is not obvious, so another regular term is added to the regular part of the algorithm to enhance the image details. In the experiment, many kinds of noise are used to reduce the quality of HR image to obtain LR image. The results of LR image reconstruction show that the proposed algorithm is more effective than the original algorithm, and compared with the results of other popular algorithms, DMSR algorithm has more advantages in deblurring and detail enhancement.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123587194","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

Pruning Based Deep Network is Used for Text Detection of Natural Scene Images 将基于剪枝的深度网络用于自然场景图像的文本检测

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408200

Jie Liu, Xiaodong Zhang, Yan Wang, Hao Zhang

引用次数: 1

Decoupled DOA and Polarization Estimation Based on Block 2D Sparse Representation 基于块2D稀疏表示的解耦DOA和极化估计

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408143

Shuli Shi, Yougen Xu, K. Zhao, Yulin Huang, Zhiwen Liu

引用次数: 0

Region Growing and Level Set Synergetic Algorithms for Image Segmentation 区域增长和水平集协同图像分割算法

Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408152

Qingling Liu, Ye Lin, F. Siddiqui

{"title":"Region Growing and Level Set Synergetic Algorithms for Image Segmentation","authors":"Qingling Liu, Ye Lin, F. Siddiqui","doi":"10.1145/3408127.3408152","DOIUrl":"https://doi.org/10.1145/3408127.3408152","url":null,"abstract":"The application of segmentation technology in CT images can not only retain the clear characteristics of CT images, but also have the advantages of high resolution, clear anatomical relationship and clear pathological development. Level set segmentation method combines region and boundary information to solve the problems on complex texture and blurred edge of CT image. Therefore, this paper proposes an algorithm for regional growth and level set interaction for the problem of boundary sensitivity and lack of regional information in level set segmentation. In order to improve the efficiency and reduce the error of segmentation, this algorithm uses Gaussian filter to remove noise. Meaning while it adopts Ostu method to transform the image into a binary image. In addition, this algorithm provides an ideal growth environment for the seed point of the region growing algorithm correspondingly. The results of region growth are accomplished as the initial contour of the level set to modify the initial boundary. The boundary indication function introduces the region information; the level set segmentation algorithm achieves the purpose of accelerating in the pixel similar region and stopping at the target boundary as a result. Comparing the overall improved algorithms with the previous both region growing method and the level set method, the experiment results shows convincingly that the interaction between the level set segmentation and the region growing reduces the number of iterations. Under the condition of weak boundary and high noise, the boundary indicator function can accurately and completely segment the organ region and save the details of the internal organ completely, which improves the segmentation accuracy to a certain extent.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116482994","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