Pub Date : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874192
Qiuhan Han, Atsushi Yoshikawa, M. Yamamura
In this study, we proposed a new framework to mine and analyze information from GPS trajectory data to find similar users from a spatial-temporal and semantic perspective. The framework combines spatial-temporal and semantic similarity techniques to achieve a system with low computational overhead and good similarity accuracy by using the characteristics of individual movements to identify similar users. It consists of three steps: first, spatial-temporal features are obtained by modeling and clustering stay points, and using them to calculate spatial-temporal similarities; next, using categories of points of interest within stay regions as semantic information, the semantic similarity can then be computed by frequent sequential pattern mining; finally, the spatial-temporal and semantic similarities can be combined to calculate the user similarity. We compared the results with those of related studies. The K-nearest neighbors experiments showed that the combination of spatial-temporal and semantic similarity methods exhibited excellent performance, being able to identify similar users more accurately. Consequently, our proposed method could be a useful identification framework in situations where large volumes of human spatial-temporal trajectory data exist, possibly due to the development of GPS devices and storage technology.
{"title":"Mining User Similarity from GPS Trajectory Based on Spatial-temporal and Semantic Information","authors":"Qiuhan Han, Atsushi Yoshikawa, M. Yamamura","doi":"10.1109/ISPDS56360.2022.9874192","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874192","url":null,"abstract":"In this study, we proposed a new framework to mine and analyze information from GPS trajectory data to find similar users from a spatial-temporal and semantic perspective. The framework combines spatial-temporal and semantic similarity techniques to achieve a system with low computational overhead and good similarity accuracy by using the characteristics of individual movements to identify similar users. It consists of three steps: first, spatial-temporal features are obtained by modeling and clustering stay points, and using them to calculate spatial-temporal similarities; next, using categories of points of interest within stay regions as semantic information, the semantic similarity can then be computed by frequent sequential pattern mining; finally, the spatial-temporal and semantic similarities can be combined to calculate the user similarity. We compared the results with those of related studies. The K-nearest neighbors experiments showed that the combination of spatial-temporal and semantic similarity methods exhibited excellent performance, being able to identify similar users more accurately. Consequently, our proposed method could be a useful identification framework in situations where large volumes of human spatial-temporal trajectory data exist, possibly due to the development of GPS devices and storage technology.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116334691","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874180
Ning Nie, Yuanyuan Zhou, Jiangping Zhou
Focusing on the application scenario where the underwater mobile platforms wirelessly access the cabled underwater information networks to achieve communication, an underwater access scheme for measurement-device-independent quantum key distribution is proposed to ensure communication security. Based on the analysis of the optical characteristics of the seawater channel, an underwater access model of measurement-device-independent quantum key distribution is constructed, simulated and analyzed to verify the feasibility and effectiveness of the scheme. The simulation results show that the maximum secure access distance of the scheme (under extreme conditions) can be extended from 147 meters to 230 meters or even 451 meters as the seawater type changes from turbid seawater to moderately turbid seawater to clear seawater. The vacuum + weak decoy state scheme can obtain performance that is very close to this limit. After considering the effect of finite data-set size, the performance of the scheme is reduced, but it can still meet the application requirements of underwater mobile platform access within a certain range. In practical applications, measures such as deploying wired communication buoys at network nodes can be used to further expand the effective access range.
{"title":"Research on Underwater Measurement-Device-Independent Quantum Key Distribution","authors":"Ning Nie, Yuanyuan Zhou, Jiangping Zhou","doi":"10.1109/ISPDS56360.2022.9874180","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874180","url":null,"abstract":"Focusing on the application scenario where the underwater mobile platforms wirelessly access the cabled underwater information networks to achieve communication, an underwater access scheme for measurement-device-independent quantum key distribution is proposed to ensure communication security. Based on the analysis of the optical characteristics of the seawater channel, an underwater access model of measurement-device-independent quantum key distribution is constructed, simulated and analyzed to verify the feasibility and effectiveness of the scheme. The simulation results show that the maximum secure access distance of the scheme (under extreme conditions) can be extended from 147 meters to 230 meters or even 451 meters as the seawater type changes from turbid seawater to moderately turbid seawater to clear seawater. The vacuum + weak decoy state scheme can obtain performance that is very close to this limit. After considering the effect of finite data-set size, the performance of the scheme is reduced, but it can still meet the application requirements of underwater mobile platform access within a certain range. In practical applications, measures such as deploying wired communication buoys at network nodes can be used to further expand the effective access range.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"391 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126745645","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}
Omicron BA.2, a new variant of severe acute respiratory syndrome coronavirus (SARS-CoV-2), has attracted worldwide attention due to its high infectivity and vaccine escape mutation. Based on the SEIR model being susceptible to changes in external factors and having specific errors, the ARIMA model is data-dependent and can only capture linear relationships. In this paper, based on the traditional infectious disease dynamic model SEIR and the differential integrated mean autoregressive model ARIMA, an SEIR-ARIMA mixed model is proposed to predict and evaluate the virus outbreak in March in Jilin Province, China. The data from SEIR and ARIMA models were processed using SPSS to obtain the predicted values f and e, respectively. Linear regression modeling was performed on the predicted values f and e to establish the SEIR-ARIMA model. MATLAB is used to complete the best linear fitting line. Furthermore, The results show that the model's predicted value is in good agreement with the actual value. It shows that the SEIR-ARIMA mixed model based on the SEIR-ARIMA model has a good prediction effect, which is beneficial for the country to make the right decision when facing the epidemic. It is of great value for preventing other types of infectious diseases in China in the future.
{"title":"Omicron BA.2 Prediction Research Based on SEIR-ARIMA Mixed Model","authors":"Kai Hu, Jinghao Yang, Chuante Hou, Zhengyao Bi, Jinxian Wang, Yujie Zhang","doi":"10.1109/ISPDS56360.2022.9874160","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874160","url":null,"abstract":"Omicron BA.2, a new variant of severe acute respiratory syndrome coronavirus (SARS-CoV-2), has attracted worldwide attention due to its high infectivity and vaccine escape mutation. Based on the SEIR model being susceptible to changes in external factors and having specific errors, the ARIMA model is data-dependent and can only capture linear relationships. In this paper, based on the traditional infectious disease dynamic model SEIR and the differential integrated mean autoregressive model ARIMA, an SEIR-ARIMA mixed model is proposed to predict and evaluate the virus outbreak in March in Jilin Province, China. The data from SEIR and ARIMA models were processed using SPSS to obtain the predicted values f and e, respectively. Linear regression modeling was performed on the predicted values f and e to establish the SEIR-ARIMA model. MATLAB is used to complete the best linear fitting line. Furthermore, The results show that the model's predicted value is in good agreement with the actual value. It shows that the SEIR-ARIMA mixed model based on the SEIR-ARIMA model has a good prediction effect, which is beneficial for the country to make the right decision when facing the epidemic. It is of great value for preventing other types of infectious diseases in China in the future.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115937407","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}
In order to solve the problem that the mechanized transplanting of potted seedlings in greenhouse can not realize automation and abandon unqualified potted seedlings, and improve the economic benefits of greenhouse, In this paper, a classification method of glug seedlings based on time series image is proposed, and the seedling stages of plug seedlings are experimentally analyzed. The experimental results show that, compared with the classification method of plug seedlings based on pixel area, the classification method of plug seedlings based on time series can obtain the growth information of plug seedlings in the whole growth stage, and classify plug seedlings quickly and accurately according to the growth situation of plug seedlings. The accuracy of the method based on time series is about 5% higher than that based on pixel area, which can provide a technical basis for automatic screening and transplanting of plug seedlings in agricultural automatic production.
{"title":"Time series based method for classification of plug seedlings","authors":"Jing Zeng, Gang Xu, Yunkuan Xu, Yue Cui, Yougang Zhao, Jiangjan Xiao","doi":"10.1109/ISPDS56360.2022.9874156","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874156","url":null,"abstract":"In order to solve the problem that the mechanized transplanting of potted seedlings in greenhouse can not realize automation and abandon unqualified potted seedlings, and improve the economic benefits of greenhouse, In this paper, a classification method of glug seedlings based on time series image is proposed, and the seedling stages of plug seedlings are experimentally analyzed. The experimental results show that, compared with the classification method of plug seedlings based on pixel area, the classification method of plug seedlings based on time series can obtain the growth information of plug seedlings in the whole growth stage, and classify plug seedlings quickly and accurately according to the growth situation of plug seedlings. The accuracy of the method based on time series is about 5% higher than that based on pixel area, which can provide a technical basis for automatic screening and transplanting of plug seedlings in agricultural automatic production.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115418452","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874004
Enjing Zhang, Jiandong Fang, Yudong Zhao
This Compared with the single-dimensional ecologi-cal footprint evaluation, the three-dimensional ecological footprint evaluation of grass and livestock has the characteristics of categor-ical characterization of natural resource flow occupation and stock consumption status of grass and livestock, and at the same time can reflect the relationship between natural resources and sustain-able development more accurately. In this paper takes the grass-livestock balance relationship as the entry point, based on the eco-logical footprint and ecological carrying capacity, and uses the 3D ecological footprint improvement model to calculate the depth of grass-livestock footprint, the breadth of grass-livestock footprint and the 3D ecological footprint of grass-livestock in the agricul-tural and pastoral areas of each league and city in Inner Mongolia from 2018 to 2020, and then decodes the causes of formation. The results of the simulation experiment show that: at the social level, the more rural population, the larger the grass-livestock ecological footprint; at the economic level, industry accounts for a large pro-portion, there is industrial competition for food, and the grass-live-stock ecological footprint is small; at the natural level, the annual rainfall is more, and the corresponding grass-livestock ecological footprint is small.
{"title":"Improvement and application of a three-dimensional ecological footprint evaluation model for grass and livestock","authors":"Enjing Zhang, Jiandong Fang, Yudong Zhao","doi":"10.1109/ISPDS56360.2022.9874004","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874004","url":null,"abstract":"This Compared with the single-dimensional ecologi-cal footprint evaluation, the three-dimensional ecological footprint evaluation of grass and livestock has the characteristics of categor-ical characterization of natural resource flow occupation and stock consumption status of grass and livestock, and at the same time can reflect the relationship between natural resources and sustain-able development more accurately. In this paper takes the grass-livestock balance relationship as the entry point, based on the eco-logical footprint and ecological carrying capacity, and uses the 3D ecological footprint improvement model to calculate the depth of grass-livestock footprint, the breadth of grass-livestock footprint and the 3D ecological footprint of grass-livestock in the agricul-tural and pastoral areas of each league and city in Inner Mongolia from 2018 to 2020, and then decodes the causes of formation. The results of the simulation experiment show that: at the social level, the more rural population, the larger the grass-livestock ecological footprint; at the economic level, industry accounts for a large pro-portion, there is industrial competition for food, and the grass-live-stock ecological footprint is small; at the natural level, the annual rainfall is more, and the corresponding grass-livestock ecological footprint is small.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126028644","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874196
Song Zhou, Yueling Zhao, Dong Guo
Vehicle detection is an important technology in au-tonomous driving, for which high detection accuracy and real-time performance are often required. The YOLOv5-GE vehicle detection algorithm is proposed to address the situation that the YOLOv5 vehicle detection model has false detection and missed detection for small and dense targets in complex environments. The global attention mechanism is added to the backbone net-work of the YOLOOv5 model, which is composed of two inde-pendent submodules of channel attention and convolutional spa-tial attention, which prevents the loss of information to a certain extent and amplifies the interaction of global dimensions. Second-ly, the training process is optimized using the Focal-EloU loss function to replace the GloU loss function, which improves the accuracy of vehicle detection. Finally, the proposed YOLOv5-GE algorithm and the YOLOv5 algorithm are subjected to a con-trolled experiment on the KITTI dataset. The experimental re-sults show that the YOLOv5-GE algorithm achieves an average accuracy of 86% while maintaining real-time performance, which is 2.5% higher than that of the YOLOv5 algorithm, and can im-prove the detection accuracy of small and dense targets in com-plex environments.
{"title":"YOLOv5-GE Vehicle Detection Algorithm Integrating Global Attention Mechanism","authors":"Song Zhou, Yueling Zhao, Dong Guo","doi":"10.1109/ISPDS56360.2022.9874196","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874196","url":null,"abstract":"Vehicle detection is an important technology in au-tonomous driving, for which high detection accuracy and real-time performance are often required. The YOLOv5-GE vehicle detection algorithm is proposed to address the situation that the YOLOv5 vehicle detection model has false detection and missed detection for small and dense targets in complex environments. The global attention mechanism is added to the backbone net-work of the YOLOOv5 model, which is composed of two inde-pendent submodules of channel attention and convolutional spa-tial attention, which prevents the loss of information to a certain extent and amplifies the interaction of global dimensions. Second-ly, the training process is optimized using the Focal-EloU loss function to replace the GloU loss function, which improves the accuracy of vehicle detection. Finally, the proposed YOLOv5-GE algorithm and the YOLOv5 algorithm are subjected to a con-trolled experiment on the KITTI dataset. The experimental re-sults show that the YOLOv5-GE algorithm achieves an average accuracy of 86% while maintaining real-time performance, which is 2.5% higher than that of the YOLOv5 algorithm, and can im-prove the detection accuracy of small and dense targets in com-plex environments.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130193778","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874027
Peiyi Jia, Shijie Jia, Yangjie Huang
In order to improve the generation quality and personalization of generative adversarial network, this paper proposes an open generative adversarial network (OpenGAN) based on human-computer interaction, which adds human subjective evaluation into the training. A subjective penalty function is added to the original generator loss and the smoothing network layer is designed to reduce the impact of loss mutation in the interaction. Our results show that the IS value on ADE20K, Cityscape and other datasets increases by 61% on average, while KID and LPIPS decrease by 32% and 44%, respectively.
{"title":"Generative Adversarial Networks Based on Human-Computor Interaction","authors":"Peiyi Jia, Shijie Jia, Yangjie Huang","doi":"10.1109/ISPDS56360.2022.9874027","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874027","url":null,"abstract":"In order to improve the generation quality and personalization of generative adversarial network, this paper proposes an open generative adversarial network (OpenGAN) based on human-computer interaction, which adds human subjective evaluation into the training. A subjective penalty function is added to the original generator loss and the smoothing network layer is designed to reduce the impact of loss mutation in the interaction. Our results show that the IS value on ADE20K, Cityscape and other datasets increases by 61% on average, while KID and LPIPS decrease by 32% and 44%, respectively.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122470786","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}
With the application of digitization and informatization in China's industry, the informatization level in highway engineering construction has gradually improved. This paper establishes a comprehensive assessment and evaluation framework based on a typical project management platform. Through business data analysis, real-time assessment and evaluation of the project progress, project quality and project safety are realized. The successful application of the evaluation framework has effectively improved the quality and efficiency of highway construction management.
{"title":"An Assessment and Evaluation Framework for Highway Construction Management based on Data Analysis of the Project Management Platform","authors":"Shuangke Gou, Xinyi Zhao, Zhaohui Tang, Zefei Wang, Zhiheng Yin, Kaibing He","doi":"10.1109/ISPDS56360.2022.9874060","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874060","url":null,"abstract":"With the application of digitization and informatization in China's industry, the informatization level in highway engineering construction has gradually improved. This paper establishes a comprehensive assessment and evaluation framework based on a typical project management platform. Through business data analysis, real-time assessment and evaluation of the project progress, project quality and project safety are realized. The successful application of the evaluation framework has effectively improved the quality and efficiency of highway construction management.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133720598","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}
In the clustering process, the eigenvalues in the data set have mixed type attributes such as numerical and text, and the measurement methods are inconsistent. In this paper, the distance between samples is easily affected by the eigenvalues of a certain dimension. This includes affecting clustering performance and the inability of continuous algorithms to deal with discrete data. These two problems focus on two points in the algorithm of this paper. First, each characteristic attribute of the dataset is analyzed. The type and number of ranges for each attribute is counted. Attributes that are not affected by the clustering algorithm are deleted. Secondly, the text feature attributes with more than 2 range are extended to multiple new feature attributes. Each attribute has only two value fields, replaced by 0 or 1 respectively. This approach makes all textual and numeric attributes use a uniform metric. This method was used to preprocess the mushroom dataset. This keeps the values in the dataset in the same range. Clustering algorithm is used to classify it. In the experiment, the classification accuracy of k-means++ algorithm is improved from 70.9% to 89.2% compared with LabelEncoder method. It also applies to more algorithms. This proves that our method works.
{"title":"Research on a text data preprocessing method suitable for clustering algorithm","authors":"Chunlin Wang, Neng Yang, Wanjin Xu, Junjie Wang, Jianyong Sun, Xiaolin Chen","doi":"10.1109/ISPDS56360.2022.9874172","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874172","url":null,"abstract":"In the clustering process, the eigenvalues in the data set have mixed type attributes such as numerical and text, and the measurement methods are inconsistent. In this paper, the distance between samples is easily affected by the eigenvalues of a certain dimension. This includes affecting clustering performance and the inability of continuous algorithms to deal with discrete data. These two problems focus on two points in the algorithm of this paper. First, each characteristic attribute of the dataset is analyzed. The type and number of ranges for each attribute is counted. Attributes that are not affected by the clustering algorithm are deleted. Secondly, the text feature attributes with more than 2 range are extended to multiple new feature attributes. Each attribute has only two value fields, replaced by 0 or 1 respectively. This approach makes all textual and numeric attributes use a uniform metric. This method was used to preprocess the mushroom dataset. This keeps the values in the dataset in the same range. Clustering algorithm is used to classify it. In the experiment, the classification accuracy of k-means++ algorithm is improved from 70.9% to 89.2% compared with LabelEncoder method. It also applies to more algorithms. This proves that our method works.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133122074","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 : 2022-07-22DOI: 10.1109/ISPDS56360.2022.9874121
Guohua Gao, Shuangyou Wang, Ciyin Shuai
In order to recognize and detect tomatoes for providing accurate location information for tomato picking robot under the complex environment of facility greenhouse, the recognition and detection method based on YOLOV5 was adopted in this paper. The data enhancement method was used to improve the generalization ability of network model. The binocular camera was also used to collect images to match and calculate the central pixel of the detected tomatoes, according to the binocular ranging principle. At the same time, the parallax value of the detected tomatoes was compared with the real value in different environments. It is proved that the mAP of YOLOV5 method is 96%, the absolute value of stereo matching error is less than 3 pixels, and the matching time of single image is less than 10ms, which effectively improves the accuracy and efficiency of picking robot.
{"title":"Study on Recognition and Location Technology of Tomato in Facility Agriculture","authors":"Guohua Gao, Shuangyou Wang, Ciyin Shuai","doi":"10.1109/ISPDS56360.2022.9874121","DOIUrl":"https://doi.org/10.1109/ISPDS56360.2022.9874121","url":null,"abstract":"In order to recognize and detect tomatoes for providing accurate location information for tomato picking robot under the complex environment of facility greenhouse, the recognition and detection method based on YOLOV5 was adopted in this paper. The data enhancement method was used to improve the generalization ability of network model. The binocular camera was also used to collect images to match and calculate the central pixel of the detected tomatoes, according to the binocular ranging principle. At the same time, the parallax value of the detected tomatoes was compared with the real value in different environments. It is proved that the mAP of YOLOV5 method is 96%, the absolute value of stereo matching error is less than 3 pixels, and the matching time of single image is less than 10ms, which effectively improves the accuracy and efficiency of picking robot.","PeriodicalId":280244,"journal":{"name":"2022 3rd International Conference on Information Science, Parallel and Distributed Systems (ISPDS)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132902997","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：