Proceedings of the 3rd International Conference on Vision, Image and Signal Processing最新文献_第10页

Detecting Protuberant Saliency from a Depth Image 从深度图像中检测凸起性显著性

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387171

Yuseok Ban

{"title":"Detecting Protuberant Saliency from a Depth Image","authors":"Yuseok Ban","doi":"10.1145/3387168.3387171","DOIUrl":"https://doi.org/10.1145/3387168.3387171","url":null,"abstract":"The visual attention of a human enables quick perception of noticeable regions in an image. The research on the models of visual attention has been actively studied for decades in the computer vision areas. For example, detecting visual saliency in a scene allows to estimate which details humans find interesting in advance to understand the scene. This also forms the important basis of a variety of latter tasks related to visual detection and tracking. By virtue of increasing diffusion of low-cost 3D sensors, many studies have been proposed to examine how to incorporate 3D information into visual attention models. Despite many advantages of depth data, relatively few studies on the visual attention of a depth image have delved into how to fully exploit the structural information of depth perception based on depth data itself. In this paper, Protuberant saliency is proposed to effectively detect the saliency in a depth image. The proposed approach explores the inherent protuberance information encoded in a depth structure. The fixation of a human eye in a depth scene is directly estimated by Protuberant saliency. It is robust to the isometric deformation and varying orientation of a depth region. The experimental results show that the rotation invariant and flexible architecture of Protuberant saliency produces the effectiveness against those challenging conditions.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132799803","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

Image Thresholding Based on Two-Dimensional Tsallis Gray Entropy Using Fast Iterative Algorithm 基于二维Tsallis灰度熵的快速迭代图像阈值分割

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387249

Li Li

{"title":"Image Thresholding Based on Two-Dimensional Tsallis Gray Entropy Using Fast Iterative Algorithm","authors":"Li Li","doi":"10.1145/3387168.3387249","DOIUrl":"https://doi.org/10.1145/3387168.3387249","url":null,"abstract":"In order to extract target from complex background more quickly and accurately, and efficiently improve the computational efficiency of the optimal thresholds, the rapid iteration method based on 2D Tsallis gray entropy thresholding is proposed. First of all, the rapid iteration method of one-dimensional gray-entropy threshold Tsallis is proposed. Then considering the within-class grayscale uniformity of image target and background, Tsallis gray entropy thresholding based on Grayscale-Average gray level two-dimensional histogram is derived, which along with the Intermediate variables in the recursion formula can be used to efficiently remove the redundant computation and decrease the romputation. At last, the rapid iteration method of 2D Tsallis gray entropy thresholding is proposed. The efficiency of the romputation is improved greatly by deriving the rorresponding rormula. A great number of experimental results have proven that, compared to the four similar thresholding algorithm, the method put forward in this paper can more precisely and completely fragmenting the target needed with better fragmenting performance and faster running speed, which turns out a real-time and efficient image segmenting method.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115392716","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

Using Passive DNS to Detect Malicious Domain Name 使用被动DNS检测恶意域名

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387236

Zhouyu Bao, Wenbo Wang, Yuqing Lan

引用次数: 6

Passive Target Detection and Location using UAV-borne RF Sensors 使用无人机机载射频传感器的被动目标探测和定位

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387200

F. Dilkes, Huai-Jing Du

引用次数: 0

A Crowdsourcing Repeated Annotations System for Visual Object Detection 一种面向视觉目标检测的众包重复标注系统

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387242

Yucheng Hu, Zhonghong Ou, Xiangyu Xu, Meina Song

{"title":"A Crowdsourcing Repeated Annotations System for Visual Object Detection","authors":"Yucheng Hu, Zhonghong Ou, Xiangyu Xu, Meina Song","doi":"10.1145/3387168.3387242","DOIUrl":"https://doi.org/10.1145/3387168.3387242","url":null,"abstract":"As a fundamental task in compute vision, object detection has been developed rapidly driven by the deep learning. The lack of a large number of images with ground truth annotations has become a chief obstacle to object detection applications in many fields. Eliciting labels from crowds is a potential way to obtain large labeled data. Nonetheless, existing crowdsourced techniques, e.g., Amazon Mechanical Turk (MTurk), often fail to guarantee the quality of the annotations, which have a bad influence on the accuracy of the deep detector. A variety of methods have been developed for ground truth inference and learning from crowds. In this paper, we study strategies to crowd-source repeated labels in support for these methods. The core challenge of building such a system is to reduce the difficulty to annotate multiple objects of interest and improve the data quality as much as possible. We present a system that adopts the turn-based annotation mechanism and consists of three simple sub-tasks: a single object annotation, a quality verification task and a coverage verification task. Experimental results demonstrate that our system is scalable, accurate and can assist the detector of obtaining higher accuracy.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132118979","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: 4

Power Spectrum Estimation Method Based on Matlab 基于Matlab的功率谱估计方法

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387223

Xiaobo Jin, Yuwen Wang, Wenjun Hong

引用次数: 3

ICGNI

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387189

Wenchao Li, Wei Zhang, Jianming Zhang

引用次数: 0

Classification and Predictive Analysis of the Stocks Listed with NIFTY50 NIFTY50成分股的分类与预测分析

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3389118

K. Jain, Neeti Mathur

{"title":"Classification and Predictive Analysis of the Stocks Listed with NIFTY50","authors":"K. Jain, Neeti Mathur","doi":"10.1145/3387168.3389118","DOIUrl":"https://doi.org/10.1145/3387168.3389118","url":null,"abstract":"Indian stock market has its prominent position in the globe. In 2018, the healthy economic growth in India has supported its stock market and become one of the largest stock market in the world. India's ascent reflects the growing blow of emerging markets. It also indicates its economy is positioned for sustained growth, even if the manufacturing sector is not firing on all cylinders. SENSEX and NIFTY are considered as the barometers of Indian stock market. Approximately 1600 companies are listed on National Stock Exchange of India Ltd. (NSE), from which fifty companies are listed with the prestigious index NIFTY50.The NIFTY50, is the leading index on the NSE, which is commonly known as NIFTY. It is derived from economic research and is created for the interest of investors, who wants to invest and trade in Indian equities. The NIFTY 50 stocks comprises of leading Indian companies from various sectors. The stocks of listed companies are relatively less volatile and offer a rather steady return. The NIFTY 50 covers major sectors of the Indian economy and offers great exposure to the investment managers to Indian stock market in one's competent portfolio. The companies listed with NIFTY50, show significantly diversified behavior with respect to their price movements. Thus, the risk and returns associated with the stocks found to be wide-ranging in nature. Also, the range of the beta factors of these stocks is significantly varied. The present study is an attempt to analysis the fifty stocks of NIFTY50 based on the returns offered by the stocks, risk associated with these stocks and their respective beta factors. The weekly data of past years have been collected and used to calculate the returns, risk and beta factors associated with the fifty stocks listed in NIFTY50. Using cluster analysis, the fifty stocks of NIFTY50 are classified into segments based on their respective returns, risk and beta values. Further for each segment, a predictive model for returns is Proposed.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133253674","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