{"title":"Joint Target Tracking and Classification with Scattering Center Model for Radar Sensor","authors":"Ronghui Zhan, Liping Wang, Jun Zhang","doi":"10.1109/ICCAIS46528.2019.9074682","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074682","url":null,"abstract":"In this paper, a model-based joint tracking and classification (JTC) method for wideband radar is proposed. The method is based on 3D scattering center model (3D-SCM), which is used to generate the predicted high range resolution profile (HRRP) with the information of target aspect angle. The aspect angle is derived from the target state with particle filter. Target classification is implemented through the data match and correlation of observed HRRP with predicted HRRPs. For the continuity of tracking procedure, the estimate uncertainty of target state and class probability decreases as the filter's recursion proceeds, and thus to obtain a stable tracking and classification result. The effectiveness of the proposed method is validated by simulation results for maritime ship targets.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114959904","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}
Zhi‐guo Cheng, Jintao Xiong, Yingjie Liu, Yin Zhang, Jianyu Yang
{"title":"Research on Fast Target Detection And Classification Algorithm for Passive Millimeter Wave Imaging","authors":"Zhi‐guo Cheng, Jintao Xiong, Yingjie Liu, Yin Zhang, Jianyu Yang","doi":"10.1109/ICCAIS46528.2019.9074548","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074548","url":null,"abstract":"Safety monitoring system based on passive millimeter wave (PMMW) is getting much more popular among security check field due to its advantages as no radiation, no contact, which has been wildly applied in public area as airports, railway stations, etc, to detect dangerous substances hidden under clothing. In this paper, an algorithm of Classifying Target After Segmenting (CTAS) is proposed to solve real-time detecting problem. In segmentation section, the accuracy of target segmentation is improved by applying the modified traditional maximum entropy segmentation algorithm. In classification section, a new neural network which's structure is similar to LeNet-5 is built by using Inception Module. Depthwise Separable convolution is applied to enhance the model's calculation performance. The test result shows that the overall classification accuracy of the test set image is 98.9%, and the calculation speed fits the real-time requirement properly.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122487089","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}
{"title":"RTS Smoother for GLMB filter","authors":"Tran Thien Dat Nguyen, Jongmin Yu","doi":"10.1109/ICCAIS46528.2019.9074579","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074579","url":null,"abstract":"In this paper, we implement a low-cost but effective smoothing strategy to smooth estimated tracks returned by the GLMB filter. While the forward filtering step is carried out via the GLMB filtering procedure, the backward smoothing step is recursively implemented from the final time step to the first time step via a smoothing algorithm. In particular, the smoothing algorithm is based on the Rauch-Tung-Striebel (RTS) of fixed-interval smoother. We demonstrate our smoothing strategy on a linear Gaussian model and the experimental results show consistent improved tracking performance over 100 Monte Carlo runs.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114465858","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}
{"title":"Robust Distributed Sonar CFAR Detection Based on Modified VI-CFAR Detector","authors":"Shuping Lu, Xu Sun, Feng Ding, Ranwei Li","doi":"10.1109/ICCAIS46528.2019.9074669","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074669","url":null,"abstract":"This paper proposes a robust distributed constant false alarm ratio (CFAR) detection algorithm to deal with the multistatic sonar target detection problem in the heterogeneous underwater environment. The local detector in the distributed sonar network employs the modified variability index (VI) CFAR where we apply the automatic censored mean level detector (ACMLD) and order statistic CFAR (OS-CFAR) to enhance its robustness in the more complex environment. The “MAJORITY” fusion rule is considered in the distributed fusion center. The performance of the proposed detection algorithm is analyzed by computer simulation and measured sonar data. The results show that, compared with the distributed cell averaging (CA) CFAR and VI-CFAR detectors, the new distributed detector achieves a better robustness in complex heterogeneous underwater environment.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124577703","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}
{"title":"A Real-Time Filtering Approach for Plot-Sequences Outputted by Multi - Frame Track - Before- Detection","authors":"Kezhu Liu, Wujun Li, L. Kong","doi":"10.1109/ICCAIS46528.2019.9074703","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074703","url":null,"abstract":"This paper addresses the real-time filtering problem respect to the multi-frame track-before-detection (MF - TBD). Instead of making detections on each single frame, MF - TBD jointly processes multiple raw data frames at each time, which can remain and utilize more target information. Thus, different from the conventional detection procedure which provides single point plot to a tracker, output of MF - TBD is plot-sequence. However, for batch processing MF - TBD, there are repetitive parts (named plot-sets) under a number of consecutive batches in time series while the correlation among each plot in the plot-set is complex and unpractical to computation. In this paper, by avoiding the computation of correlation, a novel filtering approach is developed for the plot-sequences outputted by batch processing MF - TBD. Last, simulation results show that the proposed algorithm can correctly estimate target trajectories and significantly enhance the tracking accuracy compared with the MF - TBD without our filtering algorithm.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124716639","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}
Pengfei Wang, Yangyang Ma, Fulai Liang, Huijun Xue, Z. Li, H. Lv, Jianqi Wang
{"title":"Radar Cross Section analysis of common objects for indoor environment sensing by simulation","authors":"Pengfei Wang, Yangyang Ma, Fulai Liang, Huijun Xue, Z. Li, H. Lv, Jianqi Wang","doi":"10.1109/ICCAIS46528.2019.9074614","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074614","url":null,"abstract":"Given the significance of home environment sensing, a simulation scheme for single static radar cross section measurement, employing the Finite Difference Time Domain (FDTD) method with the frequency range from 0.4 to 3 GHz is proposed, and the scheme is used to carry out the radar cross section of the human body and common objects indoor. The targets to be measured are 3D molding by Computer Aided Design (CAD) firstly and then using a Gaussian plane wave to illuminate the target in far-field conditions. The simulation results clearly show a substantial variation in scattering with azimuth, material, and frequency. The ultimate goal is to achieve radar cross section estimation and differentiation of objects in order to design an ultra-wide band (UWB) radar systems for indoor environment sensing and through-wall imaging.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126521837","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}
{"title":"Compressing Deep Models using Multi Tensor Train Decomposition","authors":"Xin Yang, Weize Sun, Lei Huang, Shaowu Chen","doi":"10.1109/ICCAIS46528.2019.9074612","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074612","url":null,"abstract":"Deep learning is a very influential research direction in data science and has been applied to various fields in recent years. However, deep neural network usually comes with high computational complexity and large memory storage requirement, thus is difficult to be deployed in mobile devices. The technique of deep neural network compression can reduce the parameter redundancy in depth models by using the low rank and sparsity characteristics of weight matrices or tensors and therefore suitable for applications in mobile systems. In this paper, we employ the Tensor Train decomposition with sparsity constraint for the compression of both convolutional layers and the fully connected layers. Furthermore, the idea of multi Tensor Train decomposition is proposed to improve the performance of the compression model. Specifically, a set of patterns are defined to reshape the original weight matrices or tensors into different shape of high dimensional tensors for compression using Tensor Train decomposition. New network structure is then built based on the decomposition and the number of parameters is highly decreased. Experiments show that the robustness of the compression model increases with the number of patterns employed in the deep model, and the proposed compression approach can achieve a high compression ratio with small performance loss.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122254850","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}
Yang Zhang, G. Cui, L. Kong, Shisheng Guo, Huquan Li, N. Li
{"title":"A Fast Building Layout Reconstruction Algorithm for Through-Wall Radar","authors":"Yang Zhang, G. Cui, L. Kong, Shisheng Guo, Huquan Li, N. Li","doi":"10.1109/ICCAIS46528.2019.9074560","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074560","url":null,"abstract":"In this paper, we consider the reconstruction problem of building layout and interior objects only using the attenuation power. Different from the traditional imaging mode, we introduce a novel scanning mechanism based on the bistatic radar. According to the attenuation characteristics of electromagnetic waves penetrating the objects, the received signal power is utilized to complete the reconstruction. We propose a fast building layout reconstruction algorithm which combines the filtered back projection (FBP) and sub-regional optimization. The algorithm not only can greatly improve operational efficiency, but also effectively solve the star-shaped tail problem of the projection algorithm. The numerical results have validated the effectiveness of the algorithm.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125238565","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}
{"title":"Bearings-Only Target Motion Analysis using Ray Tracing","authors":"Raegeun Oh, T. Song, J. Choi","doi":"10.1109/ICCAIS46528.2019.9074715","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074715","url":null,"abstract":"Target angular information in a 3-dimensional space consists of an elevation angle and an azimuth angle. The azimuth angle indicates the direction of the target in a horizontal plane while the elevation angle indicates the direction of target signal in a vertical plane established from a passive line array sonar. The acoustic signals gathered by the line array sonar have different elevation angles as they propagate through multiple paths. The target angle measured by the line array sonar is, in fact, a conical angle that indicates the direction of incoming signal to the line array sonar system. Therefore, bottom bounce path produces an inaccurate target location if it is interpreted as the azimuth angle in the horizontal plane as is commonly used in exiting Target Motion Analysis (TMA) technologies. Therefore, it is necessary to consider the conical angle effect on bearings-only TMA (BO-TMA). In this paper, the conical angle of target that causes angular ambiguity will be simulated, and the BO-TMA method using Particle Swarm Optimization (PSO) is proposed to solve the angular ambiguity problem.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130801652","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}
{"title":"3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos","authors":"Shikha Dubey, Abhijeet Boragule, M. Jeon","doi":"10.1109/ICCAIS46528.2019.9074586","DOIUrl":"https://doi.org/10.1109/ICCAIS46528.2019.9074586","url":null,"abstract":"Abnormal activity detection is one of the most challenging tasks in the field of computer vision. This study is motivated by the recent state-of-art work of abnormal activity detection, which utilizes both abnormal and normal videos in learning abnormalities with the help of multiple instance learning by providing the data with video-level information. In the absence of temporal-annotations, such a model is prone to give a false alarm while detecting the abnormalities. For this reason, in this paper, we focus on the task of minimizing the false alarm rate while performing an abnormal activity detection task. The mitigation of these false alarms and recent advancement of 3D deep neural network in video action recognition task collectively give us motivation to exploit the 3D ResNet in our proposed method, which helps to extract spatial-temporal features from the videos. Afterwards, using these features and deep multiple instance learning along with the proposed ranking loss, our model learns to predict the abnormality score at the video segment level. Therefore, our proposed method 3D deep Multiple Instance Learning with ResNet (MILR) along with the new proposed ranking loss function achieves the best performance on the UCF-Crime benchmark dataset, as compared to other state-of-art methods. The effectiveness of our proposed method is demonstrated on the UCF-Crime dataset.","PeriodicalId":403971,"journal":{"name":"2019 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130858849","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}