Pub Date : 2017-07-01DOI: 10.1109/ICAR.2017.8023520
Yuanhui Wang, Yulong Tuo, Simon X. Yang
For floating production storage and offloading (FPSO) vessels, a positioning controller is necessary because only a mooring system alone cannot always keep the ship within a predefined region. This paper develops a new adaptive backstepping controller based on structural reliability index to deal with the model uncertainties of the FPSO vessel. Model uncertainties can be estimated by the adaptive law derived from the Lyapunov stability theory. The capacity of the mooring system can be fully utilized to position the FPSO vessel by adjusting the structural reliability index on the premise of ensuring the safety of mooring lines, and hence less control effort is needed for the positioning controller. The robustness of the proposed control algorithm is demonstrated through simulations using three sets of different system parameters. In addition, a comparison to the PID controller without the structural reliability shows that less control effort is needed using the proposed controller.
{"title":"Adaptive backstepping control based on structural reliability for a turret-moored FPSO vessel","authors":"Yuanhui Wang, Yulong Tuo, Simon X. Yang","doi":"10.1109/ICAR.2017.8023520","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023520","url":null,"abstract":"For floating production storage and offloading (FPSO) vessels, a positioning controller is necessary because only a mooring system alone cannot always keep the ship within a predefined region. This paper develops a new adaptive backstepping controller based on structural reliability index to deal with the model uncertainties of the FPSO vessel. Model uncertainties can be estimated by the adaptive law derived from the Lyapunov stability theory. The capacity of the mooring system can be fully utilized to position the FPSO vessel by adjusting the structural reliability index on the premise of ensuring the safety of mooring lines, and hence less control effort is needed for the positioning controller. The robustness of the proposed control algorithm is demonstrated through simulations using three sets of different system parameters. In addition, a comparison to the PID controller without the structural reliability shows that less control effort is needed using the proposed controller.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"71 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114135868","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023644
John Jairo Paez Rodriguez, Enríque González Guerrero
A challenge of using robots such as learning tool is to support the learning process according to cognitive and emotional user's characteristics. This paper presents a novel framework named Human-Robot Scaffolding, a learning activity during which robots are giving physical, emotional and cognitive support according to the emotional and cognitive learner' scharacteristics. This document is divided into four sections. First, the theoretical concepts from psychology and education, are presented. Second, the scaffolder module grounded in the psychology flow theory, is analyzed. Third, the modules of input, reasoning, interpretation and action, are explained. Finally, the perspectives to implement the framework into Baxter Research Robot, are presented.
{"title":"Human-robot scaffolding: A novel perspective to use robots such as learning tools","authors":"John Jairo Paez Rodriguez, Enríque González Guerrero","doi":"10.1109/ICAR.2017.8023644","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023644","url":null,"abstract":"A challenge of using robots such as learning tool is to support the learning process according to cognitive and emotional user's characteristics. This paper presents a novel framework named Human-Robot Scaffolding, a learning activity during which robots are giving physical, emotional and cognitive support according to the emotional and cognitive learner' scharacteristics. This document is divided into four sections. First, the theoretical concepts from psychology and education, are presented. Second, the scaffolder module grounded in the psychology flow theory, is analyzed. Third, the modules of input, reasoning, interpretation and action, are explained. Finally, the perspectives to implement the framework into Baxter Research Robot, are presented.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124897036","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023639
Haluk Ozakyol, Cenk Karaman, Z. Bingul
The forward and inverse kinematic analysis of the hybrid systems that using serial and parallel robots together such as legged robots and service robots, is a rather difficult and complex problem and a topic of great interest for researchers. There are so many toolboxes that analyze serial and parallel robots separately. With this toolbox, serial, parallel and hybrid robotic systems used together can be analyzed wholly. In this toolbox, forward and inverse kinematics, Jacobian matrix, trajectory planning, workspace, dexterity and singularities can be examined. Users can create their own robotic systems easily. It is useful for researchers, students and educators, because of its easily applicable form. It provides to users improve the understanding of multi-body hybrid robotic systems fundamentals through interactive simulation. The other toolboxes allow to user analyze the predefined robots at their libraries. In some of them, the user can define a new robot, however, the user must have a prior knowledge and it is a very time consuming process. Using this toolbox, this problem has been overcome and it has become very easy to define new robots. What makes this toolbox unique is to analyze any robot structure using MATLAB.
{"title":"Robotics toolbox for kinematic analysis and design of hybrid multibody systems","authors":"Haluk Ozakyol, Cenk Karaman, Z. Bingul","doi":"10.1109/ICAR.2017.8023639","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023639","url":null,"abstract":"The forward and inverse kinematic analysis of the hybrid systems that using serial and parallel robots together such as legged robots and service robots, is a rather difficult and complex problem and a topic of great interest for researchers. There are so many toolboxes that analyze serial and parallel robots separately. With this toolbox, serial, parallel and hybrid robotic systems used together can be analyzed wholly. In this toolbox, forward and inverse kinematics, Jacobian matrix, trajectory planning, workspace, dexterity and singularities can be examined. Users can create their own robotic systems easily. It is useful for researchers, students and educators, because of its easily applicable form. It provides to users improve the understanding of multi-body hybrid robotic systems fundamentals through interactive simulation. The other toolboxes allow to user analyze the predefined robots at their libraries. In some of them, the user can define a new robot, however, the user must have a prior knowledge and it is a very time consuming process. Using this toolbox, this problem has been overcome and it has become very easy to define new robots. What makes this toolbox unique is to analyze any robot structure using MATLAB.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129873234","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023634
Michael K. L. Siu, K. Woo
Inductance saliency-based position sensing method is a common complement to the ineffectiveness of the traditional back-emf-based methods in low-speed applications, which effect originates from zigzag saturation on core teeth. In this paper, an impedance-tracking based self-sensing method is proposed, which is capable of quickly estimating rotor position by tracking variations on attenuated response of an injected high-frequency signal. Compared to other inductance tracking-based self-sensing methods, this solution removes specific nonlinearities such as semiconductor voltage drop characteristics and coil resistive effect while having minimal impact on the control distortion. Measurements and experiment results demonstrate the versatility of the method on different brushless motor constructions.
{"title":"A high-frequency signal injection based sensorless drive method for brushless DC motor","authors":"Michael K. L. Siu, K. Woo","doi":"10.1109/ICAR.2017.8023634","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023634","url":null,"abstract":"Inductance saliency-based position sensing method is a common complement to the ineffectiveness of the traditional back-emf-based methods in low-speed applications, which effect originates from zigzag saturation on core teeth. In this paper, an impedance-tracking based self-sensing method is proposed, which is capable of quickly estimating rotor position by tracking variations on attenuated response of an injected high-frequency signal. Compared to other inductance tracking-based self-sensing methods, this solution removes specific nonlinearities such as semiconductor voltage drop characteristics and coil resistive effect while having minimal impact on the control distortion. Measurements and experiment results demonstrate the versatility of the method on different brushless motor constructions.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129787607","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023511
Byoung-Ho Kim
This paper analyses the elastic strap-based rehabilitation of the elbow joint of human arms. The basic idea is that an elastic strap can be used as a tool for the typical elbow joint exercise or rehabilitation. Such an elastic strap has been modeled as a linear spring with a stiffness in this paper, and then we consider a stiffness-based elbow training mechanism for the purpose of rehabilitation of the elbow joint. For effective rehabilitation training by using such a mechanism, we need to analyse the available torque characteristics exerted on the elbow joint according to the stiffness level of the strap. Through various simulations, we identify a torque pattern and a range of the elbow joint available for effectively perform a level of elbow rehabilitation. Finally, we show that the specified stiffness-based exercise scheme can give us a guideline for effective rehabilitation of the elbow joint. In addition, we address the reason why our analysis is helpful for a rehabilitation trainee or trainer. Practically, this analysis can contribute to determine a proper load for appropriate elbow rehabilitation.
{"title":"Analysis on elastic strap-based rehabilitation of elbow joint","authors":"Byoung-Ho Kim","doi":"10.1109/ICAR.2017.8023511","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023511","url":null,"abstract":"This paper analyses the elastic strap-based rehabilitation of the elbow joint of human arms. The basic idea is that an elastic strap can be used as a tool for the typical elbow joint exercise or rehabilitation. Such an elastic strap has been modeled as a linear spring with a stiffness in this paper, and then we consider a stiffness-based elbow training mechanism for the purpose of rehabilitation of the elbow joint. For effective rehabilitation training by using such a mechanism, we need to analyse the available torque characteristics exerted on the elbow joint according to the stiffness level of the strap. Through various simulations, we identify a torque pattern and a range of the elbow joint available for effectively perform a level of elbow rehabilitation. Finally, we show that the specified stiffness-based exercise scheme can give us a guideline for effective rehabilitation of the elbow joint. In addition, we address the reason why our analysis is helpful for a rehabilitation trainee or trainer. Practically, this analysis can contribute to determine a proper load for appropriate elbow rehabilitation.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125466199","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023637
Huiyu Sun, G. Song, Zhong Wei, Y. Zhang, Shengsong Liu
This paper addresses the problem of the low-energy coordinated formation control of multiple unmanned aerial vehicles (UAVs) in a time-varying bilateral teleoperation system. To achieve the multi-UAV cooperative control with time-varying delays, a passive proportional velocity/position errors plus damping injection controller is proposed to enforce the coordinated formation and force tracking of the master haptic device and the slave UAVs. The stability of the controller is analysed by the Lyapunov-Krasovskii function and the delay-dependent stability criteria of system are obtained. Moreover, a min-weighted rigid graph is adopted to reduce the communication energy dissipation. With the optimal rigid topology, the communication links and costs can be decreased. Finally, the human-in-the-loop simulations are performed to evaluate the effectiveness of the proposed control scheme.
{"title":"Bilateral teleoperation of multiple UAVs with low-energy coordinated formation control","authors":"Huiyu Sun, G. Song, Zhong Wei, Y. Zhang, Shengsong Liu","doi":"10.1109/ICAR.2017.8023637","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023637","url":null,"abstract":"This paper addresses the problem of the low-energy coordinated formation control of multiple unmanned aerial vehicles (UAVs) in a time-varying bilateral teleoperation system. To achieve the multi-UAV cooperative control with time-varying delays, a passive proportional velocity/position errors plus damping injection controller is proposed to enforce the coordinated formation and force tracking of the master haptic device and the slave UAVs. The stability of the controller is analysed by the Lyapunov-Krasovskii function and the delay-dependent stability criteria of system are obtained. Moreover, a min-weighted rigid graph is adopted to reduce the communication energy dissipation. With the optimal rigid topology, the communication links and costs can be decreased. Finally, the human-in-the-loop simulations are performed to evaluate the effectiveness of the proposed control scheme.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116066312","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023526
E. Ayari, S. Hadouaj, K. Ghédira
In some real systems, individual agents often need to form coalitions in order to achieve an overall mission that would be impossible for a single robot. Due to communication and computation constraints, it is infeasible for agents to interact directly with all other agents to form coalitions. This problem becomes more complex and challenging when tasks have different priority levels of execution. Toward this end, in this paper, a decentralized dynamic coalition formation approach is presented. The proposed mechanism operates in a neighborhood agent network. Based on self-adaptation principles, this technique enables agents to dynamically join new coalitions with a higher priority at any time without degrading the system. We empirically evaluate our method through a comparison between a centralized and a decentralized approaches. Experimental results demonstrate the good performance of our proposed approach in terms of computation time with respect to the state-of-the-art approach.
{"title":"A dynamic decentralised coalition formation approach for task allocation under tasks priority constraints","authors":"E. Ayari, S. Hadouaj, K. Ghédira","doi":"10.1109/ICAR.2017.8023526","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023526","url":null,"abstract":"In some real systems, individual agents often need to form coalitions in order to achieve an overall mission that would be impossible for a single robot. Due to communication and computation constraints, it is infeasible for agents to interact directly with all other agents to form coalitions. This problem becomes more complex and challenging when tasks have different priority levels of execution. Toward this end, in this paper, a decentralized dynamic coalition formation approach is presented. The proposed mechanism operates in a neighborhood agent network. Based on self-adaptation principles, this technique enables agents to dynamically join new coalitions with a higher priority at any time without degrading the system. We empirically evaluate our method through a comparison between a centralized and a decentralized approaches. Experimental results demonstrate the good performance of our proposed approach in terms of computation time with respect to the state-of-the-art approach.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133641526","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023670
Wenzheng Chi, M. Meng
In the human robot coexisting environment, to reach the goal efficiently and safely is very meaningful for the mobile service robot. In this paper, a Risk based Rapidly-exploring Random Tree for optimal motion planning (Risk-RRT∗) algorithm is proposed by combining the comfort and collision risk (CCR) map with the RRT∗ algorithm, which provides a variant of the RRT∗ algorithm in the dynamic human robot coexisting environment. In the experiments, the time cost in the navigation process and the length of the trajectory are utilized for the evaluation of the proposed algorithm. A comparison with the Risk-RRT algorithm is carried out and experimental results reveal that our proposed algorithm can achieve a better performance than that of the Risk-RRT in both static and dynamic environments.
{"title":"Risk-RRT∗: A robot motion planning algorithm for the human robot coexisting environment","authors":"Wenzheng Chi, M. Meng","doi":"10.1109/ICAR.2017.8023670","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023670","url":null,"abstract":"In the human robot coexisting environment, to reach the goal efficiently and safely is very meaningful for the mobile service robot. In this paper, a Risk based Rapidly-exploring Random Tree for optimal motion planning (Risk-RRT∗) algorithm is proposed by combining the comfort and collision risk (CCR) map with the RRT∗ algorithm, which provides a variant of the RRT∗ algorithm in the dynamic human robot coexisting environment. In the experiments, the time cost in the navigation process and the length of the trajectory are utilized for the evaluation of the proposed algorithm. A comparison with the Risk-RRT algorithm is carried out and experimental results reveal that our proposed algorithm can achieve a better performance than that of the Risk-RRT in both static and dynamic environments.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132952280","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023638
Hasan U. Zaman, Joytu Khisha, Naushaba Zerin, Md. Hasin Jamal
In this paper we present a robot with mechanical gripper which has the capability of transporting limited sized objects from one place to another with pick-up and drop capabilities. The robot's responses are based on speech recognition of verbal commands. In our project we have used Google speech recognition module in order to understand verbal commands. We also categorized the objects into six specific categories according to the amount of gripping force required to lift the objects. The categories are divided according to object stiffness. An android application was used to communicate with the robot through Bluetooth communication. The application decodes the human speech into an array of characters which are transmitted to the robot using Bluetooth technology. The robot uses microcontroller which decodes the messages into executable functions. In this project we have designed the robot such that it understands only fifteen distinct verbal commands and ignores others. Being a speech responsive mobile robot it can be effectively used to move objects from one place to another by people with disability or handicap.
{"title":"Speech responsive mobile robot for transporting objects of different weight categories","authors":"Hasan U. Zaman, Joytu Khisha, Naushaba Zerin, Md. Hasin Jamal","doi":"10.1109/ICAR.2017.8023638","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023638","url":null,"abstract":"In this paper we present a robot with mechanical gripper which has the capability of transporting limited sized objects from one place to another with pick-up and drop capabilities. The robot's responses are based on speech recognition of verbal commands. In our project we have used Google speech recognition module in order to understand verbal commands. We also categorized the objects into six specific categories according to the amount of gripping force required to lift the objects. The categories are divided according to object stiffness. An android application was used to communicate with the robot through Bluetooth communication. The application decodes the human speech into an array of characters which are transmitted to the robot using Bluetooth technology. The robot uses microcontroller which decodes the messages into executable functions. In this project we have designed the robot such that it understands only fifteen distinct verbal commands and ignores others. Being a speech responsive mobile robot it can be effectively used to move objects from one place to another by people with disability or handicap.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131907926","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 : 2017-07-01DOI: 10.1109/ICAR.2017.8023662
P. Sun, H. Lau
This paper provides a novel feature detection method which utilizes illumination invariant space to achieve a high performance of robustness under the variating lighting conditions. Taking advantage of the dark channel prior knowledge, the proposed method builds three indicators to describe the illumination invariant components in the RGB color space and eliminates the light sensitive parts. The components retained are transformed to the illumination invariant space in which the traditional feature detection methods works more robustly. In contrast to the current transformation method, the method gives a clearer projection from the RGB space to the illumination invariant space which improve the discerning ability of the feature detection methods. The dark channel prior knowledge helps not only the building of more distinguishable indicators, but also the detection of edge features of an object.
{"title":"Dark channel based illumination invariant feature detection","authors":"P. Sun, H. Lau","doi":"10.1109/ICAR.2017.8023662","DOIUrl":"https://doi.org/10.1109/ICAR.2017.8023662","url":null,"abstract":"This paper provides a novel feature detection method which utilizes illumination invariant space to achieve a high performance of robustness under the variating lighting conditions. Taking advantage of the dark channel prior knowledge, the proposed method builds three indicators to describe the illumination invariant components in the RGB color space and eliminates the light sensitive parts. The components retained are transformed to the illumination invariant space in which the traditional feature detection methods works more robustly. In contrast to the current transformation method, the method gives a clearer projection from the RGB space to the illumination invariant space which improve the discerning ability of the feature detection methods. The dark channel prior knowledge helps not only the building of more distinguishable indicators, but also the detection of edge features of an object.","PeriodicalId":198633,"journal":{"name":"2017 18th International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124320342","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：