Pub Date : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00045
Xinlei Wei, Ying-Ji Liu, Haiying Xia, Xuan Dong, Shuquan Xu, Wei Zhou, Hong Jia, Guoliang Dong
This phenomenon can be described as an intentional act of lying on the compliant vehicle verification with the intent to obtain an illegal operation certificate of transport. These false data will bring safety problems in the management of transport vehicles. Regrettably, the fraud behaviors of compliant vehicle verification are too hidden to come to light, therefore access to labeled historical information is extremely limited. For this reason, the applicability of supervised machine learning techniques for compliant vehicle verification fraud detection is severely hindered. Such limitations motivate the contribution of this work. We present a novel approach for the detection of potential fraudulent compliant transport vehicle verification using only rule inference techniques and allowing the future use of supervised learning techniques. We demonstrate the ability of our model to identify potential fraudulent verification vehicles on compliant transport vehicle verification data, reducing the number of potential fraudulent verification vehicles. The obtained results demonstrate that our model doesn’t miss on real compliant transport vehicles verification data, increasing the operational efficiency in the compliant transport vehicles verification process without needing historic labeled data.
{"title":"Compliant Transport Vehicles Verification Fraud Detection of Based on Rule Inference","authors":"Xinlei Wei, Ying-Ji Liu, Haiying Xia, Xuan Dong, Shuquan Xu, Wei Zhou, Hong Jia, Guoliang Dong","doi":"10.1109/ICDSBA51020.2020.00045","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00045","url":null,"abstract":"This phenomenon can be described as an intentional act of lying on the compliant vehicle verification with the intent to obtain an illegal operation certificate of transport. These false data will bring safety problems in the management of transport vehicles. Regrettably, the fraud behaviors of compliant vehicle verification are too hidden to come to light, therefore access to labeled historical information is extremely limited. For this reason, the applicability of supervised machine learning techniques for compliant vehicle verification fraud detection is severely hindered. Such limitations motivate the contribution of this work. We present a novel approach for the detection of potential fraudulent compliant transport vehicle verification using only rule inference techniques and allowing the future use of supervised learning techniques. We demonstrate the ability of our model to identify potential fraudulent verification vehicles on compliant transport vehicle verification data, reducing the number of potential fraudulent verification vehicles. The obtained results demonstrate that our model doesn’t miss on real compliant transport vehicles verification data, increasing the operational efficiency in the compliant transport vehicles verification process without needing historic labeled data.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129646875","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00040
Xiang Xu, Shan Liu, Lipeng Luo, Yuanqing Luo, Xin Liu
The shared economy is emerging dramatically in recent years including shared bicycles (Mobike/Ofo), shared accommodation (Airbnb/Xiaozhu), ridesharing (Uber and DiDi), and shared office space (Wework). Both criticisms and praises appeared to this situation. In this paper, we employ a Hadoop platform and survey to collect data of shared bikes in Chengdu, China, and then to perform data mining and cleansing, and further utilize data visualization to visualize and analyze the data. Experiments and results demonstrate the high distribution of shared bicycles in high density population area and the distribution changes between working hours and non-working hours. The individual tracking of a randomly selected bicycle indicates that the usage efficiency of shared bicycles could be improve by well management.
{"title":"Shared Transport in a Digitalized World: A Case Study of Shared Bicycles through Data Mining and Visualization","authors":"Xiang Xu, Shan Liu, Lipeng Luo, Yuanqing Luo, Xin Liu","doi":"10.1109/ICDSBA51020.2020.00040","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00040","url":null,"abstract":"The shared economy is emerging dramatically in recent years including shared bicycles (Mobike/Ofo), shared accommodation (Airbnb/Xiaozhu), ridesharing (Uber and DiDi), and shared office space (Wework). Both criticisms and praises appeared to this situation. In this paper, we employ a Hadoop platform and survey to collect data of shared bikes in Chengdu, China, and then to perform data mining and cleansing, and further utilize data visualization to visualize and analyze the data. Experiments and results demonstrate the high distribution of shared bicycles in high density population area and the distribution changes between working hours and non-working hours. The individual tracking of a randomly selected bicycle indicates that the usage efficiency of shared bicycles could be improve by well management.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129456541","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00067
Liming Zhao, Dazhou Long, Yi Zhang, Xiaolin Hu, Bin Xing
This paper proposes to use nonlinear factors to recover odometry information and use it in the optimization of global consistent map construction. In the front-end, the pixel matching is carried out by the direct method assisted with IMU information. Then the reprojection error and IMU error are minimized to obtain the initial pose estimation of robot. In the back-end, we use a fix-size optimization window to optimize mapping. When new frames are added, we marginalize the old state. We use a set of nonlinear factors to approximate the marginal distribution, and combine it with loop-closing constraints to construct a globally consistent map. Finally, the performance of the system is verified on the open dataset EuRoC, and conduct experiments in a real environment. The results show that the method improves the accuracy and robustness of mapping.
{"title":"Non-Linear Factor Recovery for Visual-Inertial SLAM","authors":"Liming Zhao, Dazhou Long, Yi Zhang, Xiaolin Hu, Bin Xing","doi":"10.1109/ICDSBA51020.2020.00067","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00067","url":null,"abstract":"This paper proposes to use nonlinear factors to recover odometry information and use it in the optimization of global consistent map construction. In the front-end, the pixel matching is carried out by the direct method assisted with IMU information. Then the reprojection error and IMU error are minimized to obtain the initial pose estimation of robot. In the back-end, we use a fix-size optimization window to optimize mapping. When new frames are added, we marginalize the old state. We use a set of nonlinear factors to approximate the marginal distribution, and combine it with loop-closing constraints to construct a globally consistent map. Finally, the performance of the system is verified on the open dataset EuRoC, and conduct experiments in a real environment. The results show that the method improves the accuracy and robustness of mapping.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"08 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127263317","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00023
Yalan Li, Min Yao, Jianquan Huang, Xiaoqin Zhang, Ruhua Lu
It is essential to align different 3d models from different scale, posture and translation to a uniform coordinate system in many 3d applications. Traditional alignment algorithm iterative optimizes the scale, posture and translation parameters from random initial values which is usually time consumed especially dealing with huge 3d point cloud data. To solve this problem, a novel alignment algorithm is proposed, which mainly consists of two step. At the first step, the scale, posture and translation are quickly adjust by re-projecting and least square solving. At the second step, the scale, posture and translation parameters are fine tuned by iterative optimization. The experiments show that the alignment algorithm is efficient and accurate.
{"title":"A Novel Alignment Algorithm for 3D Models","authors":"Yalan Li, Min Yao, Jianquan Huang, Xiaoqin Zhang, Ruhua Lu","doi":"10.1109/ICDSBA51020.2020.00023","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00023","url":null,"abstract":"It is essential to align different 3d models from different scale, posture and translation to a uniform coordinate system in many 3d applications. Traditional alignment algorithm iterative optimizes the scale, posture and translation parameters from random initial values which is usually time consumed especially dealing with huge 3d point cloud data. To solve this problem, a novel alignment algorithm is proposed, which mainly consists of two step. At the first step, the scale, posture and translation are quickly adjust by re-projecting and least square solving. At the second step, the scale, posture and translation parameters are fine tuned by iterative optimization. The experiments show that the alignment algorithm is efficient and accurate.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121894491","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00043
Yuting Yang, Houliang Kang
The "Thirteenth Five-Year Plan" Period is the Time Node for Building a Well-off Society in China. Ensuring that the poor population and poor counties in China can be lifted out and solve regional poverty by 2020 are the key to building a well-off society. Therefore, taking the Yizidian village as an ex-ample, we analyzed the causes of poverty and the work that has been completed. By comparing the exit criteria of poor households, we have identified the problems still existing in the current poverty alleviation process in Yizidian, and given some specific and effective solutions. It will give some strength to the fight against poverty and build a well-off society.
{"title":"Analysis the Problems of Deep Poverty Villages and Explore Some Solutions","authors":"Yuting Yang, Houliang Kang","doi":"10.1109/ICDSBA51020.2020.00043","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00043","url":null,"abstract":"The \"Thirteenth Five-Year Plan\" Period is the Time Node for Building a Well-off Society in China. Ensuring that the poor population and poor counties in China can be lifted out and solve regional poverty by 2020 are the key to building a well-off society. Therefore, taking the Yizidian village as an ex-ample, we analyzed the causes of poverty and the work that has been completed. By comparing the exit criteria of poor households, we have identified the problems still existing in the current poverty alleviation process in Yizidian, and given some specific and effective solutions. It will give some strength to the fight against poverty and build a well-off society.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121456127","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00071
Tao Zhang, Xi Guo
SQL injection is a typical kind of Web vulnerability, and it is also the most common method used by attackers to attack databases. Attackers usually detect and use this vulnerability to access the back-end database of target website, and illegally obtain confidential information in the database through a series of injection methods, thereby causing unpredictable damage and loss. This paper studies the attack principle, detection technologies and preventive measures of SQL injection, and proposes an approach and a tool named SQLIiscan. The tool is tested by detecting a popular project WAVSEP1.5 which includes many test cases of different vulnerabilities, and the test results show that it can detect SQL injection cases efficiently and accurately.
{"title":"Research on SQL Injection Vulnerabilities and Its Detection Methods","authors":"Tao Zhang, Xi Guo","doi":"10.1109/ICDSBA51020.2020.00071","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00071","url":null,"abstract":"SQL injection is a typical kind of Web vulnerability, and it is also the most common method used by attackers to attack databases. Attackers usually detect and use this vulnerability to access the back-end database of target website, and illegally obtain confidential information in the database through a series of injection methods, thereby causing unpredictable damage and loss. This paper studies the attack principle, detection technologies and preventive measures of SQL injection, and proposes an approach and a tool named SQLIiscan. The tool is tested by detecting a popular project WAVSEP1.5 which includes many test cases of different vulnerabilities, and the test results show that it can detect SQL injection cases efficiently and accurately.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116851835","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00077
Yalan Li, Jianquan Huang, Fuming Deng, Ruhua Lu, Min Yao
Correspondences matching is essential to image stitching and greatly influences the stitching quality as the homography matrix is calculated from the correspondences. Mismatching would be generated by using SIFT alone when dealing images with repeat similar structures. To improve the matching accuracy, SIFT and DAISY are combined to extract and match feature points. Then the homography matrix is computed by least square, RANSAC and bundle adjust methods. Experiments show that the matching accuracy is improved and the stitching results are well and robust.
{"title":"An Image Stitching Algorithm Based on SIFT and DAISY Descriptor","authors":"Yalan Li, Jianquan Huang, Fuming Deng, Ruhua Lu, Min Yao","doi":"10.1109/ICDSBA51020.2020.00077","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00077","url":null,"abstract":"Correspondences matching is essential to image stitching and greatly influences the stitching quality as the homography matrix is calculated from the correspondences. Mismatching would be generated by using SIFT alone when dealing images with repeat similar structures. To improve the matching accuracy, SIFT and DAISY are combined to extract and match feature points. Then the homography matrix is computed by least square, RANSAC and bundle adjust methods. Experiments show that the matching accuracy is improved and the stitching results are well and robust.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114344299","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00089
Rongjian Wei, Jianfei Shao, Rong Pu, Xiaowei Zhang, Changli Hu
Tuberculosis is a major public health problem that is the leading cause of death worldwide. Early detection and diagnosis is the key to the treatment of tuberculosis. Computed tomography (CT) can provide more comprehensive tuberculosis lesion information and improve the accuracy of diagnosis. However, due to the characteristics of polymorphism, multiple parts, multiple nodules and cavities of pulmonary tuberculosis, segmentation has become an important and difficult problem in computer-aided diagnosis.Deep learning is widely used in medical image segmentation tasks. This paper proposes to use U-Net and attention mechanism to form Attention U-Net network model for feature extraction and segmentation of labeled CT images of tuberculosis, to achieve unlabeled tuberculosis CT image data Perform lesion segmentation and lesion labeling.
{"title":"Lesion Segmentation Method Based on Deep Learning CT Image of Pulmonary Tuberculosis","authors":"Rongjian Wei, Jianfei Shao, Rong Pu, Xiaowei Zhang, Changli Hu","doi":"10.1109/ICDSBA51020.2020.00089","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00089","url":null,"abstract":"Tuberculosis is a major public health problem that is the leading cause of death worldwide. Early detection and diagnosis is the key to the treatment of tuberculosis. Computed tomography (CT) can provide more comprehensive tuberculosis lesion information and improve the accuracy of diagnosis. However, due to the characteristics of polymorphism, multiple parts, multiple nodules and cavities of pulmonary tuberculosis, segmentation has become an important and difficult problem in computer-aided diagnosis.Deep learning is widely used in medical image segmentation tasks. This paper proposes to use U-Net and attention mechanism to form Attention U-Net network model for feature extraction and segmentation of labeled CT images of tuberculosis, to achieve unlabeled tuberculosis CT image data Perform lesion segmentation and lesion labeling.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125332568","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00039
Yangyi Liu, Yangping Li, Ke Wang, Z. Qiao, Zihao Yuan, Xihan Li, Lu Zhang, Haifeng Zhao
The detection with autonomous burrowing robot might be a low-cost and high-efficient solution for a future lunar subsurface exploration mission. The path planning of underground locomotive robot in a three-dimensional (3-D) domain is a very challenging task under the circumstance of lunar subsurface segregated by lunar rocks. In this work, a pruning-improved RRT algorithm was proposed to generate robotic paths in a 3-D geological model: a confined cubic zone with distributed obstacles. This digital terrain model may be constructed based on the mapping technology of Lunar Penetrating Radar (LPR). Here, a numerical simulation scheme was adapted for a simplicity. The effects of iteration scheme of path finding and distribution of geological structures were discussed. Then, Bezier parametric curve was utilized to enhanced the smoothness of robotic trajectory. After a comprehensive study, the proposed algorithm was proven to outperform the original RRT method in both effectiveness and convergence.
{"title":"A Path Planning Algorithm Based on Improved RRT for Lunar Subsurface Autonomous Burrowing Robot","authors":"Yangyi Liu, Yangping Li, Ke Wang, Z. Qiao, Zihao Yuan, Xihan Li, Lu Zhang, Haifeng Zhao","doi":"10.1109/ICDSBA51020.2020.00039","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00039","url":null,"abstract":"The detection with autonomous burrowing robot might be a low-cost and high-efficient solution for a future lunar subsurface exploration mission. The path planning of underground locomotive robot in a three-dimensional (3-D) domain is a very challenging task under the circumstance of lunar subsurface segregated by lunar rocks. In this work, a pruning-improved RRT algorithm was proposed to generate robotic paths in a 3-D geological model: a confined cubic zone with distributed obstacles. This digital terrain model may be constructed based on the mapping technology of Lunar Penetrating Radar (LPR). Here, a numerical simulation scheme was adapted for a simplicity. The effects of iteration scheme of path finding and distribution of geological structures were discussed. Then, Bezier parametric curve was utilized to enhanced the smoothness of robotic trajectory. After a comprehensive study, the proposed algorithm was proven to outperform the original RRT method in both effectiveness and convergence.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125547266","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 : 2020-09-01DOI: 10.1109/ICDSBA51020.2020.00086
Guangjie Fu, Li Yu
Aimed at the current tracking algorithm such as object occlusion, severe deformation, motion blur and background confusion, a tracking method based on multiple template updates is proposed to improve the robustness of the algorithm. First, a response graph quality evaluation index is proposed to evaluate the reliability of the tracking result of the current frame. When the tracking result is unreliable, the model update is stopped immediately, and the tracker can find the object again when the object reappears. However, the indicator will always remain within a reliable range when the object is continuously blocked. At this time, if you stop the update tracking of the model, it will drift due to lack of information. In order to solve the above problems, the algorithm in this chapter adopts a multi-template tracking strategy—adding several additional filters to track the object. The proposed algorithm is compared with several recent state-of-the-art tracking algorithms on OTB100 benchmark datasets (online object tracking benchmark). Especially, the pro-posed algorithm greatly improves its basic algorithm in AUC and Precision on some complex environments of partial occlusion, severe deformation, motion blur, background clutter and illumination variation, which has a better tracking performance.
{"title":"Correlation Filter for Object Tracking Method Based on Multi-Template Update","authors":"Guangjie Fu, Li Yu","doi":"10.1109/ICDSBA51020.2020.00086","DOIUrl":"https://doi.org/10.1109/ICDSBA51020.2020.00086","url":null,"abstract":"Aimed at the current tracking algorithm such as object occlusion, severe deformation, motion blur and background confusion, a tracking method based on multiple template updates is proposed to improve the robustness of the algorithm. First, a response graph quality evaluation index is proposed to evaluate the reliability of the tracking result of the current frame. When the tracking result is unreliable, the model update is stopped immediately, and the tracker can find the object again when the object reappears. However, the indicator will always remain within a reliable range when the object is continuously blocked. At this time, if you stop the update tracking of the model, it will drift due to lack of information. In order to solve the above problems, the algorithm in this chapter adopts a multi-template tracking strategy—adding several additional filters to track the object. The proposed algorithm is compared with several recent state-of-the-art tracking algorithms on OTB100 benchmark datasets (online object tracking benchmark). Especially, the pro-posed algorithm greatly improves its basic algorithm in AUC and Precision on some complex environments of partial occlusion, severe deformation, motion blur, background clutter and illumination variation, which has a better tracking performance.","PeriodicalId":354742,"journal":{"name":"2020 4th Annual International Conference on Data Science and Business Analytics (ICDSBA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121515272","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：