Ximeng Zhang, Qingping Wang, Zhaoyu Huang, N. Yuan, W. Hu
{"title":"Direct Position Determination of Emitters using Single Moving Coprime Array","authors":"Ximeng Zhang, Qingping Wang, Zhaoyu Huang, N. Yuan, W. Hu","doi":"10.1109/CISP-BMEI53629.2021.9624408","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624408","url":null,"abstract":"The direct position determination (DPD) is a single-step method that is considered to achieve better positioning performance than that of the two-step method. In contrast to the ordinary positioning method which uses a moving uniform linear array (ULA), in this work, we consider the DPD of emitters using a single moving coprime array. The coprime array can be regarded as two subarrays with different spacing, and the initial estimates of the emitters' positions are obtained separately through these two moving subarrays respectively. The final positions are obtained by combining the results of the two subarrays, respectively. The simulation of this study indicates that the proposed DPD method has better performance than the two-step method. Moreover, the method using coprime array can achieve better results compared to the method using ULA with the same number of antenna elements.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114305198","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":"SLBNet: Shallow and Lightweight Bilateral Network for Pose Estimation","authors":"Mao-qing Zhou, W. Sun, F. Yang, Sheng Zhang","doi":"10.1109/CISP-BMEI53629.2021.9624376","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624376","url":null,"abstract":"Human pose estimation from images is an important task in many real-life applications. However, most existing methods focus on improving the effectiveness without considering efficiency, making the networks computationally expensive with a huge size. As depthwise separable convolution can help compress the model size and floating point operations (FLOPs), some methods combined it to make human pose estimation affordable on resource-constrained devices. However, depthwise separable convolution also slows down the inference speed, especially on GPU devices. In this paper, we introduce a shallow and lightweight bilateral network (SLBNet). Our network inferences much faster than the existing methods while achieves competitive performance. We evaluate our networks on the MPII and COCO datasets. Specially, our SLBNet yields 67.8 Average Precision (AP) on COCO test set with only 3.6M parameters and 4.5G FLOPs at 253 FPS on a single 2080Ti GPU, and 25 FPS on an Intel i7-8700K CPU machine.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"424 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121600461","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":"GLM-Net: A multi-scale image segmentation network for brain abnormalities based on GLCM","authors":"Fuchun Zhang, Yuwen Wang, Liang Wu, Mingtao Liu, Shunbo Hu, Meng Li","doi":"10.1109/CISP-BMEI53629.2021.9624341","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624341","url":null,"abstract":"In medical image processing, robust brain Magnetic Resonance (MR) images segmentation algorithm is one of the most concerned research fields. It plays an important role in distinguishing healthy tissues from diseased tissues. Because of the complex structure and unpredictable appearance of the brain, it is a complex task to segment tissue parts from brain MR images. The current brain segmentation methods are mostly based on the deep convolution network model, which has the problem of large loss of information in the encoding and decoding process. In order to solve this problem, we propose a brain MR images tissue segmentation method, Gray Level Multiscale Network (GLM-Net), based on three-dimensional U-Net network. The input of the network is constructed of the original image and four characteristic images. The original image is enhanced by Contrast-Limited Adaptive Histogram Equalization (CLAHE) algorithm, and the four characteristic images are generated by Gray Level Co-occurrence Matrix (GLCM) method. The network fused the residual module and dilated convolution for multi-scale feature restoration in the upsampling process of the network decoder to segment the brain MR images into white matter (WM), gray matter (GM), cerebrospinal fluid (CSF) and tumor. The skip connection is used to transmit each set of feature maps generated on the encoder path to the corresponding feature map on the decoder path. Tested and trained on the BraTS 2020 dataset, the average Dice coefficients of WM, GM, CSF and tumor in the segmentation results of the model are about 0.92, 0.91, 0.92 and 0.82 respectively.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124152707","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 Multi-Sensor Multi-Target Tracker Based on Labeled MS-CPHD Filter","authors":"Zhiguo Zhang, Jinping Sun, Xiaoke Lu","doi":"10.1109/CISP-BMEI53629.2021.9624356","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624356","url":null,"abstract":"The multi-sensor cardinalized probability hypothesis density (MS-CPHD) filter based on the random finite set (RFS) have been developed in the literature for multi-sensor multitarget tracking. However, this filter is not strictly a multi-target tracker as it cannot estimate identities of individual target states. To form the target tracks, a multiple target tracker based on the MS-CPHD filter is given in this paper. Specifically, in the Gaussian mixture recursion of the MS-CPHD filter, each Gaussian component is identify identified with a unique label for separating different targets. Then the target tracks can be determined from the calculation of the Gaussian component with a corresponding label. Furthermore, we also propose a track management mechanism to determine the creation, maintenance, and termination of tracks. Numerical results from simulations show that, our proposed method can obtain target tracks and has higher filtering accuracy compared with the original MS-CPHD filter, especially in scenarios with high clutter intensity.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125484080","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 New Semantic SLAM Mapping Algorithm Based on Improved YOLOv5","authors":"Weixiang Shen, Yongxing Jia, Mingcan Li, Junchao Zhu","doi":"10.1109/CISP-BMEI53629.2021.9624443","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624443","url":null,"abstract":"Visual SLAM (V-SLAM) uses cameras for information input. In mapping, the spatial geometric information of the point cloud is used, which lacks the semantic information of the objects in the environment. This paper proposes a new semantic mapping algorithm based on improved YOLOv5. Firstly, A Pyramid Scene Parsing Network (PSPNet) segmentation head is added to YOLOv5 for performing semantic extraction of the environment. Subsequently, the robot pose is estimated with the ORB-SLAM2 framework. Finally, the semantic images, the depth images and the pose transformation matrix are sent to a mapping module to fuse a dense point cloud semantic map. Experiments show that the algorithm in this paper builds an accurate semantic map on KITTI dataset. Combined with the depth map that eliminates interference factors, it has good accuracy and robustness for semantic mapping in large-scale scenarios.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128175413","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":"Effect of smartphone camera settings in colorimetric measurements under controlled illumination","authors":"Ritambhara Thakur, Sunita Bhatt, S. Dubey","doi":"10.1109/CISP-BMEI53629.2021.9624389","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624389","url":null,"abstract":"Smartphone based point-of-care diagnostics can be a viable alternative for lab-based methods in low resource settings. However smartphone applications for quantification of colorimetric tests are not robust enough and lack field portability as they require external add-on device to mitigate ambient lighting conditions. To make the system accessory free, we need some features which do not change with ambient light conditions. However, camera ISP system adjust itself to give best image by compromising spectral changes. In this study, we investigated smartphone camera settings; ISO and Focus to study the effect of these settings on colorimetric values in controlled lighting conditions. A total of 198 images were acquired using smartphone, where ISO and focus, were changed manually in different lighting conditions; 3 different color temperature and 10 focus points. It was observed that “Hue” parameter of HSV color space and “a” parameter of CIEL*a*b color space depicts least variation with lighting and ISO variation. Also, colorimetric values change with the focus on strip. Therefore, ISO and Focus settings of smartphone should be taken into account for accurate colorimetric estimation.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129374550","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‐Cheng‐Kuang Chen, Zhongbin Zheng, Shiqiang Li
{"title":"Analysis of Handle System and Performance Optimization Research Based on Industrial Internet Scenario","authors":"Yang‐Cheng‐Kuang Chen, Zhongbin Zheng, Shiqiang Li","doi":"10.1109/CISP-BMEI53629.2021.9624343","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624343","url":null,"abstract":"The Handle system has become to an important practical technology in the field of identifier resolution, and the industrial internet identifier resolution system based on this technology is the infrastructure of the industrial internet. In order to support and maintain the system better, it is very important to conduct systematic analysis and research on the specific implementation of the Handle system. In addition, in order to adapt to the ever-developing high-volume industrial data interaction requirements, the optimization direction of the key performance indicators of the Handle system has gradually become an object that urgently needs research and analysis. By analyzing the latest implementation code, this paper conducts analysis and summary of the Handle system and also conducts the direction of performance optimization based on the scenario of industrial internet.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132267601","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":"Multi-instance Reservoir Sampling and Selection for Online Continual Detection over VHR Remote Sensing Images","authors":"Jie Jiang, Zhen Han, Sheng Wang, C. Wang","doi":"10.1109/CISP-BMEI53629.2021.9624392","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624392","url":null,"abstract":"Convolutional neural networks (CNNs) have shown outstanding performance in object detection over very-high-resolution (VHR) remote sensing images. However, the regular offline learning mode suffers from catastrophic forgetting problems and performs poorly on the non-stationary and never-ending data. To address this issue, a multi-instance reservoir sampling and selection method (MIRSS) is proposed for the continual detection on continuously generated remote sensing images. A multi-instance reservoir sampling module is used to build a size-fixed buffer and stores the previously learned samples for memory consolidation. Meanwhile, the situation that several objects may exist in each class of an image is focused. Moreover, samples in the buffer are selected with the reservoir selection module for retraining detectors. The experimental results based on three publicly available VHR satellite images, including images from the NWPU VHR-10, RSOD and DOTA data sets, highlight the effectiveness and practicality of the method.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127816898","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":"Visual Question Answering Based on Position Alignment","authors":"Qihao Xia, Chao Yu, Pingping Peng, Henghao Gu, Zhengqi Zheng, Kun Zhao","doi":"10.1109/CISP-BMEI53629.2021.9624447","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624447","url":null,"abstract":"The alignment of information from images and questions is of great significance in the visual question answering task. Whether an object in image is related to the question or not is the basic judgement relied on the feature alignment. Many previous works have proposed different alignment methods to build better cross modality interaction. The attention mechanism is the most used method in making alignment. The classical bottom up and top down model builds a top down attention distribution by concatenating question features to each image features and calculates the attention weights between question and image. However, the bottom up and top down model didn't consider the positional information in image and question. In this paper, we revisit the attention distribution from a position perspective which aligns question to object's positional information. We first embed the positional information of each object in image and calculate a position attention distribution to indicate the relevance between objects' positions in context of the current question. Through the attention distribution model can select the related position in image to answer the given question. The position attention distribution is concatenated to the feature attention distribution to get the final distribution. We evaluate our method on visual question answering (VQA2.0) dataset, and show that our method is effective in multimodal alignment.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131879150","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":"False Cores Reduction Based on Global Features of Fingerprint Orientation Field","authors":"X. Ye, Hepeng Wang, Rumeng Zou, Yirui Liu, Huahua Chen, Yuzhong Shen","doi":"10.1109/CISP-BMEI53629.2021.9624425","DOIUrl":"https://doi.org/10.1109/CISP-BMEI53629.2021.9624425","url":null,"abstract":"Singular point detection is a primary step in fingerprint recognition. Many approaches have been proposed, but the positive error rate is still too high. This paper proposes a new method based on global information of fingerprint orientation field to reduce false cores. The proposed method first estimates pixel-level orientation field and extract candidate singular points using the classic nested-Poincare index-based method. Then, both the opening direction of each candidate cores and the corresponding region along the opposite direction to the opening direction are calculated. Finally, the angle between the opening direction of a core and the orientation field in the region along the opposite direction of the opening direction is calculated as a new feature to further reduce false cores in the candidate set. Experimental results show that the error rate of the proposed method is lower than traditional algorithms. The total error rate decreases 29.5% and the false positive rate of cores decreases 35.1% comparing with NPI-based [12] in the database of FVC2000-DB2a.","PeriodicalId":131256,"journal":{"name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115729264","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}