Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065714
Xiangqi Kong, Peng Zeng, Chengju Li
Smart grid integrates communication and control technologies to enable optimal power transmission and distribution between grid operators and users. Vehicle-to-grid (V2G) is a crucial part of smart grid, which can realize two-way flow of information and electricity between electric vehicles (EV s) and smart grid. Each EV can not only charge itself, but also provide ancillary services such as feeding power back to smart grid. In order to function normally, V2G network has to continuously monitor the status of EV s by collecting enough information, which maybe lead to the exposure and malicious utilization of sensitive information like location and identity. This problem has become an obstacle to the widespread application of V2G network. In this paper, we propose an efficient privacy-preserving fair payment mechanism called PPFP for service/electricity exchanges. PPFP achieves the fairness by introducing the zero- knowledge succinct non-interactive argument of knowledge (zk- SNARK). In addition, PPFP satisfies the privacy-preserving feature by leveraging the bitcoin-based timed commitment and zk-SNARK.
{"title":"PPFP: An Efficient Privacy-Preserving Fair Payment Protocol for V2G Based on Blockchain","authors":"Xiangqi Kong, Peng Zeng, Chengju Li","doi":"10.1109/ICCC56324.2022.10065714","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065714","url":null,"abstract":"Smart grid integrates communication and control technologies to enable optimal power transmission and distribution between grid operators and users. Vehicle-to-grid (V2G) is a crucial part of smart grid, which can realize two-way flow of information and electricity between electric vehicles (EV s) and smart grid. Each EV can not only charge itself, but also provide ancillary services such as feeding power back to smart grid. In order to function normally, V2G network has to continuously monitor the status of EV s by collecting enough information, which maybe lead to the exposure and malicious utilization of sensitive information like location and identity. This problem has become an obstacle to the widespread application of V2G network. In this paper, we propose an efficient privacy-preserving fair payment mechanism called PPFP for service/electricity exchanges. PPFP achieves the fairness by introducing the zero- knowledge succinct non-interactive argument of knowledge (zk- SNARK). In addition, PPFP satisfies the privacy-preserving feature by leveraging the bitcoin-based timed commitment and zk-SNARK.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116309723","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065830
Ya Wang, Zenshan Tian, Ze Li, Sheng Li
Aiming at the localization problem of indoor Non-Line-of-Sight (NLOS) environment, a single base station localization algorithm based on scatterers information is proposed in this paper. Firstly, according to the priori information of indoor scene, the distribution range of scatterers is obtained. Secondly, the Time of Flight TOF (TOF) of a path is selected as a reference, the TOF of the remaining path subtract it to construct difference TOF, thus eliminating the phase error caused by asynchronous receiver and transmitter. At the same time, the location range of the scatterers is further determined according to the AOA of each path and the distribution range of the scatterers. Then, the nonlinear localization target equation is constructed by the difference TOF, and the equation is further transformed into a nonlinear least squares optimization problem. Finally, Genetic Algorithm (GA) was used to preliminarily locate the target, and the modified Gaussian Newton (G-N) algorithm was used to accurately locate the target; Simulation results show that this algorithm can effectively solve the problem of single station Localization in indoor NLOS environment.
针对室内非视距(NLOS)环境下的定位问题，提出了一种基于散射体信息的单基站定位算法。首先，根据室内场景的先验信息，得到散射体的分布范围;其次，选取一条路径的飞行时间TOF (Time of Flight TOF, TOF)作为参考，将剩余路径的TOF相减，构成差分TOF，从而消除了因收发端异步引起的相位误差。同时，根据各路径的AOA和散射体的分布范围，进一步确定散射体的位置范围。然后，利用差分TOF构造非线性定位目标方程，并将其转化为非线性最小二乘优化问题。最后，采用遗传算法(GA)对目标进行初步定位，并采用改进的高斯牛顿(G-N)算法对目标进行精确定位;仿真结果表明，该算法能有效解决室内近距离定位环境下的单站定位问题。
{"title":"Indoor NLOS Single Base Station Localization Algorithm Based on Scatterer Information","authors":"Ya Wang, Zenshan Tian, Ze Li, Sheng Li","doi":"10.1109/ICCC56324.2022.10065830","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065830","url":null,"abstract":"Aiming at the localization problem of indoor Non-Line-of-Sight (NLOS) environment, a single base station localization algorithm based on scatterers information is proposed in this paper. Firstly, according to the priori information of indoor scene, the distribution range of scatterers is obtained. Secondly, the Time of Flight TOF (TOF) of a path is selected as a reference, the TOF of the remaining path subtract it to construct difference TOF, thus eliminating the phase error caused by asynchronous receiver and transmitter. At the same time, the location range of the scatterers is further determined according to the AOA of each path and the distribution range of the scatterers. Then, the nonlinear localization target equation is constructed by the difference TOF, and the equation is further transformed into a nonlinear least squares optimization problem. Finally, Genetic Algorithm (GA) was used to preliminarily locate the target, and the modified Gaussian Newton (G-N) algorithm was used to accurately locate the target; Simulation results show that this algorithm can effectively solve the problem of single station Localization in indoor NLOS environment.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123607232","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065634
Wang Jijun, Chen Yongqiu, Cheng Li
In view of the characteristics of current electric power data, such as massive, high dimensional and multi-source heterogeneous, to meet the development needs of electric power enterprises, a multi-layer power enterprise data management architecture based on big data is proposed in the paper on the basis of summarizing the concept, development status, major difficulties and challenges in the field of electric power data control. Firstly, a general mathematical model of data management and control architecture is established with reference to the characteristics of electric power data, and the key technologies of its data processing are described algorithmically. Then, after analyzing and referring to the idea of big data platform architecture construction, a multi-layer system architecture for data management and control of electric power enterprises is further proposed. The architecture is divided into three layers: infrastructure virtualization layer, cloud computing support platform layer and power data application layer, which truly realizes the integration of physical facilities, data resources and business applications in one while taking into account security. Finally, the possible future research directions in this field are summarized and prospected.
{"title":"Research on Multi-layer Power Enterprise Data Management Architecture Based on Big Data","authors":"Wang Jijun, Chen Yongqiu, Cheng Li","doi":"10.1109/ICCC56324.2022.10065634","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065634","url":null,"abstract":"In view of the characteristics of current electric power data, such as massive, high dimensional and multi-source heterogeneous, to meet the development needs of electric power enterprises, a multi-layer power enterprise data management architecture based on big data is proposed in the paper on the basis of summarizing the concept, development status, major difficulties and challenges in the field of electric power data control. Firstly, a general mathematical model of data management and control architecture is established with reference to the characteristics of electric power data, and the key technologies of its data processing are described algorithmically. Then, after analyzing and referring to the idea of big data platform architecture construction, a multi-layer system architecture for data management and control of electric power enterprises is further proposed. The architecture is divided into three layers: infrastructure virtualization layer, cloud computing support platform layer and power data application layer, which truly realizes the integration of physical facilities, data resources and business applications in one while taking into account security. Finally, the possible future research directions in this field are summarized and prospected.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123695394","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065813
Minghui Liu, Yi Yuan, Meiyi Yang, Hong-yu Pu, Xiaomin Wang, Meilin Liu
Coronavirus Disease 2019(COVID-19) has shocked the world with its rapid spread and enormous threat to life and has continued up to the present. In this paper, a computer-aided system is proposed to detect infections and predict the disease progression of COVID-19. A high-quality CT scan database labeled with time-stamps and clinicopathologic variables is constructed to provide data support. To our knowledge, it is the only database with time relevance in the community. An object detection model is then trained to annotate infected regions. Using those regions, we detect the infections using a model with semi-supervised-based ensemble learning and predict the disease progression depending on reinforcement learning. We achieve an mAP of 0.92 for object detection. The accuracy for detecting infections is 98.46%, with a sensitivity of 97.68%, a specificity of 99.24%, and an AUC of 0.987. Significantly, the accuracy of predicting disease progression is 90.32% according to the timeline. It is a state-of-the-art result and can be used for clinical usage.
{"title":"Computer-Aided System for COVID-19 Using Semi-supervised-based Ensemble Learning and Reinforcement Learning","authors":"Minghui Liu, Yi Yuan, Meiyi Yang, Hong-yu Pu, Xiaomin Wang, Meilin Liu","doi":"10.1109/ICCC56324.2022.10065813","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065813","url":null,"abstract":"Coronavirus Disease 2019(COVID-19) has shocked the world with its rapid spread and enormous threat to life and has continued up to the present. In this paper, a computer-aided system is proposed to detect infections and predict the disease progression of COVID-19. A high-quality CT scan database labeled with time-stamps and clinicopathologic variables is constructed to provide data support. To our knowledge, it is the only database with time relevance in the community. An object detection model is then trained to annotate infected regions. Using those regions, we detect the infections using a model with semi-supervised-based ensemble learning and predict the disease progression depending on reinforcement learning. We achieve an mAP of 0.92 for object detection. The accuracy for detecting infections is 98.46%, with a sensitivity of 97.68%, a specificity of 99.24%, and an AUC of 0.987. Significantly, the accuracy of predicting disease progression is 90.32% according to the timeline. It is a state-of-the-art result and can be used for clinical usage.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123940161","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065766
Xuejing Jiang, Xun Sun, Qiuming Liu
Password is the primary way of identity authentication at present. The password security is closely related to more than 4 billion netizen all over the world. Password contains lots of semantic information, so how to extract the semantic of password and apply it to password guessing algorithm can further uncover the behavior preference of users in creating passwords, and improve the cracking rate of guessing attacks. We analyze the background and present situation of password security research, and determine the general steps and basic framework of password guessing algorithm based on natural language processing technology. We introduce the relevant preparatory knowledge and make statistical analysis on many password data sets. The popular password, password grammar, password pattern, character composition, length distribution, character distribution and semantic information of password data set are analyzed. We propose a password guessing algorithm based on probabilistic context free algorithm. The actual leaked password data set is selected for training and testing, and several groups of password guessing contrast experiments are set up. The results prove the effectiveness of proposed algorithm.
{"title":"Password Guessing Attack Based on Probabilistic Context Free Algorithm","authors":"Xuejing Jiang, Xun Sun, Qiuming Liu","doi":"10.1109/ICCC56324.2022.10065766","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065766","url":null,"abstract":"Password is the primary way of identity authentication at present. The password security is closely related to more than 4 billion netizen all over the world. Password contains lots of semantic information, so how to extract the semantic of password and apply it to password guessing algorithm can further uncover the behavior preference of users in creating passwords, and improve the cracking rate of guessing attacks. We analyze the background and present situation of password security research, and determine the general steps and basic framework of password guessing algorithm based on natural language processing technology. We introduce the relevant preparatory knowledge and make statistical analysis on many password data sets. The popular password, password grammar, password pattern, character composition, length distribution, character distribution and semantic information of password data set are analyzed. We propose a password guessing algorithm based on probabilistic context free algorithm. The actual leaked password data set is selected for training and testing, and several groups of password guessing contrast experiments are set up. The results prove the effectiveness of proposed algorithm.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124003480","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065758
Wangyang Xu, Jiancheng An, Lu Gan, H. Liao
A revolutionary technology, reconfigurable intelligent surface (RIS), has emerged to enhance the signal transmission quality of wireless communications. This paper a RIS-assisted mmWave multiple-input multiple-output system, where practical finite discrete phase-shift constraints are crucial. Then, we discuss the connection between the channel state information (CSI) and the devices' location information in the mmWave band. To provide a model-free and CSI-free solution, the advanced deep reinforcement learning (DRL) technique is proposed for the RIS-assisted system based on the devices' location information. Moreover, we also apply the deep quantization neural network (DQNN) in the proposed DRL algorithm for the practical finite discrete phase-shift constraint. Finally, simulation results demonstrate the viability and efficacy of our proposed approach.
{"title":"A Practical Design Based on Deep Reinforcement Learning for RIS-Assisted mmWave MIMO Systems","authors":"Wangyang Xu, Jiancheng An, Lu Gan, H. Liao","doi":"10.1109/ICCC56324.2022.10065758","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065758","url":null,"abstract":"A revolutionary technology, reconfigurable intelligent surface (RIS), has emerged to enhance the signal transmission quality of wireless communications. This paper a RIS-assisted mmWave multiple-input multiple-output system, where practical finite discrete phase-shift constraints are crucial. Then, we discuss the connection between the channel state information (CSI) and the devices' location information in the mmWave band. To provide a model-free and CSI-free solution, the advanced deep reinforcement learning (DRL) technique is proposed for the RIS-assisted system based on the devices' location information. Moreover, we also apply the deep quantization neural network (DQNN) in the proposed DRL algorithm for the practical finite discrete phase-shift constraint. Finally, simulation results demonstrate the viability and efficacy of our proposed approach.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"15 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124469477","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065999
Jiyan Zhang, Yu Xue, Jiale Wang, Yuan Qi
Millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) technology is considered as a key feature for 5G and B5G systems because of its extensive spectrum resources. Accurately and timely estimating the channel state information (CSI) is critical for guaranteeing the effective signal transmission. In this paper, we propose an algorithm called Sparse Accelerated projection consensus (SAPC) to estimate the mmWave massive MIMO channel in a parallel computing way, which should be suitable for FPGA and ASIC implementations. Also, SAPC takes into account the sparsity of the channel to reduce the complexity.
{"title":"A Parallelized Algorithm for Channel Estimation in mmWave Massive MIMO Communications","authors":"Jiyan Zhang, Yu Xue, Jiale Wang, Yuan Qi","doi":"10.1109/ICCC56324.2022.10065999","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065999","url":null,"abstract":"Millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) technology is considered as a key feature for 5G and B5G systems because of its extensive spectrum resources. Accurately and timely estimating the channel state information (CSI) is critical for guaranteeing the effective signal transmission. In this paper, we propose an algorithm called Sparse Accelerated projection consensus (SAPC) to estimate the mmWave massive MIMO channel in a parallel computing way, which should be suitable for FPGA and ASIC implementations. Also, SAPC takes into account the sparsity of the channel to reduce the complexity.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125748972","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}
Kinship verification is one of the interesting and critical problems in computer vision research, with significant progress in the past decades. Meanwhile, Vision Transformer (VIT) has recently achieved impressive success in many domains, including object detection, image recognition, and semantic segmentation, among others. Most of the previous work on kinship verification are based on convolutional or recurrent neural networks. Compared with the local processing of images like convolutions, transformers can effectively understand and process images globally. However, due to overuse, there are many Transformer layers of fully connected layers, and VIT speed is still an issue. Therefore, in this paper, inspired by the recent success of Transformer models in vision tasks, we propose a Transformer-based kinship verification for training and optimizing kinship verification models. We first train the basic vision transformer (VIT-B) with 12 transformer layers, then we reduce the transformer layers to 6 layers, namely VIT-S (Small Vit) and 4 layers, namely VIT-T (Tiny Vit), to make a tradeoff between optimization accuracy and efficiency. As the first attempt to apply Transformer to the kinship verification task, it provides a feasible strategy for kinship research topics and verifies the effectiveness of the method in terms of the accuracy of the experimental results.
亲属关系验证是计算机视觉研究中一个有趣而关键的问题，在过去的几十年里取得了重大进展。与此同时，视觉转换器(Vision Transformer, VIT)最近在许多领域取得了令人瞩目的成功，包括目标检测、图像识别和语义分割等。以往的亲属关系验证工作大多基于卷积或递归神经网络。与卷积等图像的局部处理相比，变压器可以有效地对图像进行全局理解和处理。然而，由于过度使用，有许多完全连接层的Transformer层，VIT速度仍然是一个问题。因此，在本文中，受最近Transformer模型在视觉任务中的成功启发，我们提出了一个基于Transformer的亲属验证来训练和优化亲属验证模型。我们首先训练具有12层变压器的基本视觉变压器(viti - b)，然后将变压器层减少到6层，即viti - s (Small Vit)和4层，即vitt - t (Tiny Vit)，以在优化精度和效率之间进行权衡。作为将Transformer应用于亲属关系验证任务的首次尝试，为亲属关系研究课题提供了可行的策略，并从实验结果的准确性方面验证了该方法的有效性。
{"title":"Lightweight Transformer Network and Self-supervised Task for Kinship Verification","authors":"Xiaoke Zhu, Yunwei Li, Danyang Li, Lingyun Dong, Xiaopan Chen","doi":"10.1109/ICCC56324.2022.10066034","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10066034","url":null,"abstract":"Kinship verification is one of the interesting and critical problems in computer vision research, with significant progress in the past decades. Meanwhile, Vision Transformer (VIT) has recently achieved impressive success in many domains, including object detection, image recognition, and semantic segmentation, among others. Most of the previous work on kinship verification are based on convolutional or recurrent neural networks. Compared with the local processing of images like convolutions, transformers can effectively understand and process images globally. However, due to overuse, there are many Transformer layers of fully connected layers, and VIT speed is still an issue. Therefore, in this paper, inspired by the recent success of Transformer models in vision tasks, we propose a Transformer-based kinship verification for training and optimizing kinship verification models. We first train the basic vision transformer (VIT-B) with 12 transformer layers, then we reduce the transformer layers to 6 layers, namely VIT-S (Small Vit) and 4 layers, namely VIT-T (Tiny Vit), to make a tradeoff between optimization accuracy and efficiency. As the first attempt to apply Transformer to the kinship verification task, it provides a feasible strategy for kinship research topics and verifies the effectiveness of the method in terms of the accuracy of the experimental results.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124730850","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065630
Ye Tang, Kun Xiong, Chunxi Wang
Aiming at the problems of insufficient background suppression and weak multi-target detection abilities of existing infrared small target detection methods, which lead to high false alarm rate and high omission factor of infrared search and track system, an infrared small target detection method fusing modified anisotropic diffusion coefficients with multiscale patch-based contrast measure (ADMPCM) was proposed. The local contrast values of four different directions in the local area are applied into the modified anisotropic diffusion coefficient equation, and the final filtering result is the minimum function value of the four equations. Extraordinary experimental results revealed that, in average, background suppression factor increased 2.95 times, signal-to-clutter ratio gain increased 6.17 times on single-target detection task and 10.49 times on multi-target detection task, respectively, compared with similar detection methods.
{"title":"An Improved Multiscale Patch-Based Contrast Measure for Small Infrared Target Detection","authors":"Ye Tang, Kun Xiong, Chunxi Wang","doi":"10.1109/ICCC56324.2022.10065630","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065630","url":null,"abstract":"Aiming at the problems of insufficient background suppression and weak multi-target detection abilities of existing infrared small target detection methods, which lead to high false alarm rate and high omission factor of infrared search and track system, an infrared small target detection method fusing modified anisotropic diffusion coefficients with multiscale patch-based contrast measure (ADMPCM) was proposed. The local contrast values of four different directions in the local area are applied into the modified anisotropic diffusion coefficient equation, and the final filtering result is the minimum function value of the four equations. Extraordinary experimental results revealed that, in average, background suppression factor increased 2.95 times, signal-to-clutter ratio gain increased 6.17 times on single-target detection task and 10.49 times on multi-target detection task, respectively, compared with similar detection methods.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129480206","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}
Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065886
Qiuyu Lai, Jie Wang, Huajie Lu, Xinpeng Luo, Xiangyu Zhu, Jin Yu
The task of multi-camera vessel tracking has become a critical issue due to the development of intelligent transportation on water and the need for waterborne traffic supervision. This paper proposes a multi-camera vessel trajectory tracking (MCVTT) system dedicated to improving tracking accuracy. Meanwhile, considering that the Kalman filter has a good performance in the tracking field, an extended Kalman filter for complex vessel motion trajectories is set up as a part of this system to meet the needs of multi-camera vessel traffic scene characteristics. The simulation results show that the system can track the vessel trajectory effectively and achieve the purpose of the system to improve the tracking accuracy gradually.
{"title":"A Multi-camera Vessel Trajectory Tracking System","authors":"Qiuyu Lai, Jie Wang, Huajie Lu, Xinpeng Luo, Xiangyu Zhu, Jin Yu","doi":"10.1109/ICCC56324.2022.10065886","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065886","url":null,"abstract":"The task of multi-camera vessel tracking has become a critical issue due to the development of intelligent transportation on water and the need for waterborne traffic supervision. This paper proposes a multi-camera vessel trajectory tracking (MCVTT) system dedicated to improving tracking accuracy. Meanwhile, considering that the Kalman filter has a good performance in the tracking field, an extended Kalman filter for complex vessel motion trajectories is set up as a part of this system to meet the needs of multi-camera vessel traffic scene characteristics. The simulation results show that the system can track the vessel trajectory effectively and achieve the purpose of the system to improve the tracking accuracy gradually.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129500328","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：