Edge-relevant structure features (ERSFs), e.g., object edges, boundaries and contours, junctions, etc. play an important role in the low and middle level image processing task, such as image segmentation, as well as in higher-level computer vision tasks, such as scene analysis and vision understanding. Commonly-used ERSF detection methods employ the integer-order differentiation-based methods, which are noise-sensitive and have less selectivity of edge feature. Hence, they are difficult to effectively extract object boundaries especially in natural images with rich fractal-like structures. We presented a highly selective and noise-robust ERSF detection approach based on the fractional-order Gaussian derivatives (FoGDs) by using the Caputo-Fabrizio fractional definition. The proposed ERSF detector is constructed based on a concept of robust contour selection and inflexion point localization, whose detection mask can be designed with the close-form FoGD. Theoretical analysis and experimental results show that the proposed operator is capable of extracting ERSFs in natural images. It is especially capable of detecting object edges and junctions from seriously noise- contaminated image.
{"title":"Edge-relevant Structure Feature Detection Using Caputo-Fabrizio Fractional-order Gaussian Derivatives","authors":"Jie Wang, Jinping Liu, Junbin He, Jianyong Zhu, Tianyu Ma, Zhaohui Tang","doi":"10.1109/CCDC.2019.8832964","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832964","url":null,"abstract":"Edge-relevant structure features (ERSFs), e.g., object edges, boundaries and contours, junctions, etc. play an important role in the low and middle level image processing task, such as image segmentation, as well as in higher-level computer vision tasks, such as scene analysis and vision understanding. Commonly-used ERSF detection methods employ the integer-order differentiation-based methods, which are noise-sensitive and have less selectivity of edge feature. Hence, they are difficult to effectively extract object boundaries especially in natural images with rich fractal-like structures. We presented a highly selective and noise-robust ERSF detection approach based on the fractional-order Gaussian derivatives (FoGDs) by using the Caputo-Fabrizio fractional definition. The proposed ERSF detector is constructed based on a concept of robust contour selection and inflexion point localization, whose detection mask can be designed with the close-form FoGD. Theoretical analysis and experimental results show that the proposed operator is capable of extracting ERSFs in natural images. It is especially capable of detecting object edges and junctions from seriously noise- contaminated image.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126052470","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8832345
Tao Wang, Wei-chun Ge, Zhanjun Li, Mo Zhou, Changyong Yu, D. Xie, F. Xue, Yonghui Sun
Regarding the fact that the key characteristic variables of the coordinated operation of the cooling, heat, power, (natural) gas, and steam subsystems (CHPGSS) are not fully considered in the integrated energy system (IES), the day-ahead dynamic economic dispatch (DED) for IES considering these variables of CHPGSS is studied. In order to analyze the interactive influence of CHPGSS, a hybrid CHPGS energy flows model and calculation method are developed in this paper, coupling parts of CHPGSS are concerned with the core concept of energy hub (HB). Firstly, considering the well-known principle of "temperature matched and cascade utilization" based on the concept of thermal energy level, coupled modes of different energy qualities and energy levels are designed in HB. Secondly, based on HB, the model architecture of the energy station with CHPGSS is designed and the steady state operation model of CHPGSS is proposed, respectively. Then, based on time-of-use (TOU) power price power price mechanism, the influence of power storage, heat storage and cold storage on day-ahead DED of IES is analyzed. Finally, a 0-1 mixed integer nonlinear programming (MINLP) for day-ahead DED is established under different load structures with CHPGSS. The numerical results verify the validity of DED calculation and steady state operation analysis for IES. The models and methods are suitable for day-ahead DED analysis of IES containing CHPGSS, which can reasonably reflect the operation characteristics of the IES.
{"title":"Steady State Analysis of Cold-Heat-Power-Gas-Steam Optimization in Integrated Energy System Considering Energy Storage Devices","authors":"Tao Wang, Wei-chun Ge, Zhanjun Li, Mo Zhou, Changyong Yu, D. Xie, F. Xue, Yonghui Sun","doi":"10.1109/CCDC.2019.8832345","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832345","url":null,"abstract":"Regarding the fact that the key characteristic variables of the coordinated operation of the cooling, heat, power, (natural) gas, and steam subsystems (CHPGSS) are not fully considered in the integrated energy system (IES), the day-ahead dynamic economic dispatch (DED) for IES considering these variables of CHPGSS is studied. In order to analyze the interactive influence of CHPGSS, a hybrid CHPGS energy flows model and calculation method are developed in this paper, coupling parts of CHPGSS are concerned with the core concept of energy hub (HB). Firstly, considering the well-known principle of \"temperature matched and cascade utilization\" based on the concept of thermal energy level, coupled modes of different energy qualities and energy levels are designed in HB. Secondly, based on HB, the model architecture of the energy station with CHPGSS is designed and the steady state operation model of CHPGSS is proposed, respectively. Then, based on time-of-use (TOU) power price power price mechanism, the influence of power storage, heat storage and cold storage on day-ahead DED of IES is analyzed. Finally, a 0-1 mixed integer nonlinear programming (MINLP) for day-ahead DED is established under different load structures with CHPGSS. The numerical results verify the validity of DED calculation and steady state operation analysis for IES. The models and methods are suitable for day-ahead DED analysis of IES containing CHPGSS, which can reasonably reflect the operation characteristics of the IES.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126119715","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8833359
Shengyuan Wang, Fanjun Yao, Xiangru Song, Yumei Wang
Innovation plays an important role in economic growth, and book knowledge plays a pivotal role in technological progress and innovation. With the arrival of the book knowledge economy, the eyes of scholars not only stay in the technological progress in the region. People gradually realize the importance of book knowledge in promoting innovation and national development, and innovation has gradually shifted from the traditional way to the innovative way of creating and flowing book knowledge. Compared with the traditional service industry, high-tech service enterprises emphasize the characteristics of book knowledge and technology intensiveness. It is a human resource-intensive industry and highlights the important role of innovation. Based on the perspective of book knowledge spillover, this study selects two indicators of innovation ability output type and input type index for the analysis index of high-tech service enterprise innovation ability. And the five secondary indicators and 17 third-level indicators under the first-level indicators evaluate the innovation ability of high-tech service industry from the perspective of book knowledge spillover. Based on the perspective of book knowledge spillover, this study selects three levels of indicators to evaluate the knowledge innovation ability of high-tech service enterprises to the knowledge innovation ability of high-tech service industry.
{"title":"Analysis of Knowledge Innovation Capability of High-tech Service Enterprises Based on the Perspective of Book Knowledge Spillover","authors":"Shengyuan Wang, Fanjun Yao, Xiangru Song, Yumei Wang","doi":"10.1109/CCDC.2019.8833359","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8833359","url":null,"abstract":"Innovation plays an important role in economic growth, and book knowledge plays a pivotal role in technological progress and innovation. With the arrival of the book knowledge economy, the eyes of scholars not only stay in the technological progress in the region. People gradually realize the importance of book knowledge in promoting innovation and national development, and innovation has gradually shifted from the traditional way to the innovative way of creating and flowing book knowledge. Compared with the traditional service industry, high-tech service enterprises emphasize the characteristics of book knowledge and technology intensiveness. It is a human resource-intensive industry and highlights the important role of innovation. Based on the perspective of book knowledge spillover, this study selects two indicators of innovation ability output type and input type index for the analysis index of high-tech service enterprise innovation ability. And the five secondary indicators and 17 third-level indicators under the first-level indicators evaluate the innovation ability of high-tech service industry from the perspective of book knowledge spillover. Based on the perspective of book knowledge spillover, this study selects three levels of indicators to evaluate the knowledge innovation ability of high-tech service enterprises to the knowledge innovation ability of high-tech service industry.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126145536","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8832748
Xiao bo Niu, Qun Fang, Xiao Shao
According to the characteristics of command behavior, a command behavior evaluation model based on statistical learning modeling is established, and Gaussian process prediction method is used to evaluate the command behavior. Compared with machine learning methods such as neural network and Support Vector Machine, the output results of Gaussian process have probability meanings and can evaluate the validity and confidence of the predicted results. The algorithm is proved to be effective by comparing it with Support Vector Machine (SVM).
{"title":"Command Behavior Evaluation Based on Statistical Learning Modeling","authors":"Xiao bo Niu, Qun Fang, Xiao Shao","doi":"10.1109/CCDC.2019.8832748","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832748","url":null,"abstract":"According to the characteristics of command behavior, a command behavior evaluation model based on statistical learning modeling is established, and Gaussian process prediction method is used to evaluate the command behavior. Compared with machine learning methods such as neural network and Support Vector Machine, the output results of Gaussian process have probability meanings and can evaluate the validity and confidence of the predicted results. The algorithm is proved to be effective by comparing it with Support Vector Machine (SVM).","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123264065","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8832961
Yanqing Cui, Chuanlin Huang, Yanping Wang
Tourists face a large number of tourist attractions, and spend a considerable amount of time and energy to select satisfactory tourist attractions. The application of personalized recommendation technology is an effective way to solve this problem. On the one hand, users' consumption frequency in tourism is much lower than other commodities such as music and movies; on the other hand, the increasing number of tourist attractions has led to the problem of sparse scoring data in personalized recommendations of tourist attractions. The traditional collaborative filtering algorithm is not satisfactory in the recommendation of tourist attractions. This paper builds a tourist attraction tag system, which links tourists and tourist attractions through the attractions tag from four aspects: location, location type, travel time, and travel method. By calculating the relationship between tourists and attractions tags, tourist attractions and attractions tags, a user interest model is constructed. Then, according to the user interest model, the interest degree of the new attraction to be recommended is predicted, and finally the tourist attraction recommendation set is generated.
{"title":"Research on Personalized Tourist Attraction Recommendation based on Tag and Collaborative Filtering","authors":"Yanqing Cui, Chuanlin Huang, Yanping Wang","doi":"10.1109/CCDC.2019.8832961","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832961","url":null,"abstract":"Tourists face a large number of tourist attractions, and spend a considerable amount of time and energy to select satisfactory tourist attractions. The application of personalized recommendation technology is an effective way to solve this problem. On the one hand, users' consumption frequency in tourism is much lower than other commodities such as music and movies; on the other hand, the increasing number of tourist attractions has led to the problem of sparse scoring data in personalized recommendations of tourist attractions. The traditional collaborative filtering algorithm is not satisfactory in the recommendation of tourist attractions. This paper builds a tourist attraction tag system, which links tourists and tourist attractions through the attractions tag from four aspects: location, location type, travel time, and travel method. By calculating the relationship between tourists and attractions tags, tourist attractions and attractions tags, a user interest model is constructed. Then, according to the user interest model, the interest degree of the new attraction to be recommended is predicted, and finally the tourist attraction recommendation set is generated.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"356 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123318323","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8832532
Yupeng Pan, Hongliang Yu, Ping Jiang
The raw meal quality control of cement is an important link in cement production. The pass rate of raw meal quality control has a crucial impact on clinker calcination. Cement production is a complex large-scale system control process, the production process has randomness, hysteresis and uncertainty., the quality control of raw meal has a certain degree of control difficulties. Most cement production enterprises adopt manual control to control. Intelligent control can make up for the defects caused by manual control, and the intelligent control system can take effective detection means and control methods according to the situation in the field. This paper will elaborate on the process and control difficulties of raw meal production from the perspective of intelligent control. First, classify intelligent devices that detect raw meal. Then, fuzzy identification of work condition. Third, control by trend control and deviation control. Finally, the intelligent control results are analyzed and verified.
{"title":"Application of Intelligent Control in Raw Meal Quality Control","authors":"Yupeng Pan, Hongliang Yu, Ping Jiang","doi":"10.1109/CCDC.2019.8832532","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832532","url":null,"abstract":"The raw meal quality control of cement is an important link in cement production. The pass rate of raw meal quality control has a crucial impact on clinker calcination. Cement production is a complex large-scale system control process, the production process has randomness, hysteresis and uncertainty., the quality control of raw meal has a certain degree of control difficulties. Most cement production enterprises adopt manual control to control. Intelligent control can make up for the defects caused by manual control, and the intelligent control system can take effective detection means and control methods according to the situation in the field. This paper will elaborate on the process and control difficulties of raw meal production from the perspective of intelligent control. First, classify intelligent devices that detect raw meal. Then, fuzzy identification of work condition. Third, control by trend control and deviation control. Finally, the intelligent control results are analyzed and verified.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126608758","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8832601
Xiaozheng Jin, Jizhou Yu, Li Zhou, Yong-Yue Zheng
This paper addresses the trajectory tracking control problem of a class of faulty mobile robot systems with actuator faults. The bias actuator faults are studied without knowing any fault information of actuators. Firstly, an adaptive scheme is proposed to estimate the effects of bias actuator faults. Then a state feedback control strategy based on adaptive estimations is constructed by using backstepping control technology. Through Lyapunov stability theory, it is proved that the azimuthal angle and forward speed of the wheeled mobile robot can track the desired trajectories under the influence of bias actuator faults. The validity of the design is verified by an example of mobile robot system.
{"title":"Robust Adaptive Trajectory Tracking Control of Mobile Robots with Actuator Faults","authors":"Xiaozheng Jin, Jizhou Yu, Li Zhou, Yong-Yue Zheng","doi":"10.1109/CCDC.2019.8832601","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832601","url":null,"abstract":"This paper addresses the trajectory tracking control problem of a class of faulty mobile robot systems with actuator faults. The bias actuator faults are studied without knowing any fault information of actuators. Firstly, an adaptive scheme is proposed to estimate the effects of bias actuator faults. Then a state feedback control strategy based on adaptive estimations is constructed by using backstepping control technology. Through Lyapunov stability theory, it is proved that the azimuthal angle and forward speed of the wheeled mobile robot can track the desired trajectories under the influence of bias actuator faults. The validity of the design is verified by an example of mobile robot system.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126630067","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8832349
Xiaoliang Zhang, Zaopeng Dong, Min Yu, S. Chu
The problem of static docking and recovery of an underactuated AUV in the presence of ocean current disturbances is addressed in this paper, and according to the planned recovery path, a novel path following control algorithm is proposed. Firstly, the path following control for the static docking and recovery of an underactuated AUV in the presence of ocean currents is formulated, and tracking errors are designed in Serret-Frenet coordinate system. Meanwhile, the ocean current relative coordinate system and ocean current relative velocity are designed, in order to integrate the ocean current disturbance into the kinematic and dynamic equations of the AUV. Secondly, an improved line of sight virtual guidance law for heading control is proposed, and the longitudinal position error and lateral position error are both introduced into the guidance law. Thirdly, in order to simplify the underactuated AUV path following control system, a virtual velocity in the tangent direction of the planned path to be followed is designed, and the inspiration comes from the virtual design of nonlinear backstepping method. Stability of the control laws designed is prove by Lyapunov stability theory, then simulation experiments are carried out on semi-physical simulation platform in our laboratory in order to show the effectiveness and reliability of the control algorithm designed.
{"title":"Path Following Control for Static Docking Recovery of an Underactuated AUV in the presence of Ocean Current Disturbances","authors":"Xiaoliang Zhang, Zaopeng Dong, Min Yu, S. Chu","doi":"10.1109/CCDC.2019.8832349","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832349","url":null,"abstract":"The problem of static docking and recovery of an underactuated AUV in the presence of ocean current disturbances is addressed in this paper, and according to the planned recovery path, a novel path following control algorithm is proposed. Firstly, the path following control for the static docking and recovery of an underactuated AUV in the presence of ocean currents is formulated, and tracking errors are designed in Serret-Frenet coordinate system. Meanwhile, the ocean current relative coordinate system and ocean current relative velocity are designed, in order to integrate the ocean current disturbance into the kinematic and dynamic equations of the AUV. Secondly, an improved line of sight virtual guidance law for heading control is proposed, and the longitudinal position error and lateral position error are both introduced into the guidance law. Thirdly, in order to simplify the underactuated AUV path following control system, a virtual velocity in the tangent direction of the planned path to be followed is designed, and the inspiration comes from the virtual design of nonlinear backstepping method. Stability of the control laws designed is prove by Lyapunov stability theory, then simulation experiments are carried out on semi-physical simulation platform in our laboratory in order to show the effectiveness and reliability of the control algorithm designed.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126725437","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8832546
Xuehui Liang, Jingtao Li, Fei Zhao
Quadrotor Unmanned Aerial Vehicle (UAV) contains nonlinearity and strong coupling, and it is susceptible to external disturbance. Herein, a design method of attitude control of UAV is presented based on Linear Active Disturbance Rejection Control (LADRC) theory. A transition process is firstly arranged to decrease the overshoot and improve the rapidity of the system, then an Extended State Observer (ESO) is processed as broad-band to reduce the number of adjusting parameters, meanwhile the state coupling together with external disturbances are taken as the total disturbance of the system. Furthermore a Linear Extended State Observer (LESO) is constructed and the total disturbance is estimated, and a linear state feedback control element is designed to compensate the total disturbance. Simultaneously, the designed system is compared with the Model Reference Adaptive Control (MRAC) method. The simulation and experiment results show that the designed LADRC system can quickly estimate and eliminate the total disturbance on the attitude.
{"title":"Attitude Control of Quadrotor UAV Based on LADRC Method","authors":"Xuehui Liang, Jingtao Li, Fei Zhao","doi":"10.1109/CCDC.2019.8832546","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832546","url":null,"abstract":"Quadrotor Unmanned Aerial Vehicle (UAV) contains nonlinearity and strong coupling, and it is susceptible to external disturbance. Herein, a design method of attitude control of UAV is presented based on Linear Active Disturbance Rejection Control (LADRC) theory. A transition process is firstly arranged to decrease the overshoot and improve the rapidity of the system, then an Extended State Observer (ESO) is processed as broad-band to reduce the number of adjusting parameters, meanwhile the state coupling together with external disturbances are taken as the total disturbance of the system. Furthermore a Linear Extended State Observer (LESO) is constructed and the total disturbance is estimated, and a linear state feedback control element is designed to compensate the total disturbance. Simultaneously, the designed system is compared with the Model Reference Adaptive Control (MRAC) method. The simulation and experiment results show that the designed LADRC system can quickly estimate and eliminate the total disturbance on the attitude.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114936689","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 : 2019-06-01DOI: 10.1109/CCDC.2019.8832957
Haoran Huang, Lidong Liang, Gaopeng Zhao, Yi Yang, Kai Ou
Aiming at the problems of dynamic background and various types of objects in railway clearance intrusion detection in UAV aerial video, a railway clearance intrusion detection algorithm in aerial video based on convolutional neural network is proposed. Firstly, the rail track region is affirmed in aerial single frame image by the linear segmentation detection algorithm, line segments merging and line segments screening; Then, the improved convolution neural network model is used to detect and classify rail track region image in single frame image; Finally, the single frame detection result is optimized by the inter-frame correlation of the video to obtain the final result of the railway clearance intrusion detection in aerial video. Experiments on a self-built dataset show that the proposed method can effectively detect various types of objects in the aerial video.
{"title":"Railway Clearance Intrusion Detection in Aerial Video Based on Convolutional Neural Network","authors":"Haoran Huang, Lidong Liang, Gaopeng Zhao, Yi Yang, Kai Ou","doi":"10.1109/CCDC.2019.8832957","DOIUrl":"https://doi.org/10.1109/CCDC.2019.8832957","url":null,"abstract":"Aiming at the problems of dynamic background and various types of objects in railway clearance intrusion detection in UAV aerial video, a railway clearance intrusion detection algorithm in aerial video based on convolutional neural network is proposed. Firstly, the rail track region is affirmed in aerial single frame image by the linear segmentation detection algorithm, line segments merging and line segments screening; Then, the improved convolution neural network model is used to detect and classify rail track region image in single frame image; Finally, the single frame detection result is optimized by the inter-frame correlation of the video to obtain the final result of the railway clearance intrusion detection in aerial video. Experiments on a self-built dataset show that the proposed method can effectively detect various types of objects in the aerial video.","PeriodicalId":254705,"journal":{"name":"2019 Chinese Control And Decision Conference (CCDC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114936849","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：