Pub Date : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536155
Jianxiao Chen, Guang Chen, Zhijun Li, Ya Wu, Alois Knoll
Predicting the future trajectory of different traffic agents in the complex traffic environments plays an important role in keeping the driving safety of self-driving cars, especially on urban roads. In the most of the existing works, researchers always use the long short-term memory network (LSTM) to solve this problem, since the LSTM has powerful capability for capturing the temporal dependency in motion trajectory. However, they only consider forward time cues and ignore the spatial-temporal correlations between traffic agents. Inspired by the previous work which utilizing the spatial-temporal graph, we design a spatial attention based spatial-temporal graph convolutional network, which assigns different attention weight to the the graph to take the different social interactions among the self-driving cars into consideration. We conduct extensive experiments on the benchmark InD to compare our method against many baselines. The experiment results indicate the superiority of our method than previous method, about 22% and 17% improvement on the metric of ADE and FDE respectively.
{"title":"Attention Based Graph Convolutional Networks for Trajectory Prediction","authors":"Jianxiao Chen, Guang Chen, Zhijun Li, Ya Wu, Alois Knoll","doi":"10.1109/ICARM52023.2021.9536155","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536155","url":null,"abstract":"Predicting the future trajectory of different traffic agents in the complex traffic environments plays an important role in keeping the driving safety of self-driving cars, especially on urban roads. In the most of the existing works, researchers always use the long short-term memory network (LSTM) to solve this problem, since the LSTM has powerful capability for capturing the temporal dependency in motion trajectory. However, they only consider forward time cues and ignore the spatial-temporal correlations between traffic agents. Inspired by the previous work which utilizing the spatial-temporal graph, we design a spatial attention based spatial-temporal graph convolutional network, which assigns different attention weight to the the graph to take the different social interactions among the self-driving cars into consideration. We conduct extensive experiments on the benchmark InD to compare our method against many baselines. The experiment results indicate the superiority of our method than previous method, about 22% and 17% improvement on the metric of ADE and FDE respectively.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116137206","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536080
Qingsheng Meng, Zhijun Li, Junjun Li
In this paper, we present a prosthetic system for humeral amputation patients. The design of neuro-prosthesis includes the remaining upper arm receiving cavity, forearm, wrist and five-fingered hand, which has 8 degrees of freedom driven by 8 actuators. The outline dimensions, structural design, dynamics system and motion control of the prosthetic system, as well as a crossmodal-based integration control method, which combines EMG signal, IMU signal, visual information and tactile information, are presented. The reliability of the state control of the inertial measurement unit is verified through simple task experiments. Results show our proposed method has a good manipulation performance. This work has a potential to improve the human-computer interaction experience with prosthesis.
{"title":"An Intelligent Upper Limb Prosthesis with Crossmodal Integration and Recognition","authors":"Qingsheng Meng, Zhijun Li, Junjun Li","doi":"10.1109/ICARM52023.2021.9536080","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536080","url":null,"abstract":"In this paper, we present a prosthetic system for humeral amputation patients. The design of neuro-prosthesis includes the remaining upper arm receiving cavity, forearm, wrist and five-fingered hand, which has 8 degrees of freedom driven by 8 actuators. The outline dimensions, structural design, dynamics system and motion control of the prosthetic system, as well as a crossmodal-based integration control method, which combines EMG signal, IMU signal, visual information and tactile information, are presented. The reliability of the state control of the inertial measurement unit is verified through simple task experiments. Results show our proposed method has a good manipulation performance. This work has a potential to improve the human-computer interaction experience with prosthesis.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116569359","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536119
E. Wang, Jian Huang, Yuge Li, Yuqi Cui, Xiaolong Li
Gait phase recognition can improve the control of lower limb exoskeleton robot and promote human-machine collaboration. One of the current mainstream methods is to use electromyogram (EMG) to recognize gait phase, but the EMG signal has shortcomings such as weak signal, difficult to wear, easy to be affected by noise and sweat. Therefore, we designed a novel air-pressure mechanomyograph (PMMG) sensor, and further made a wearable PMMG-based sensing system composed of PMMG-based thighrings and inertial measurement units (IMUs). In order to improve the performance of gait phase recognition, we used five popular machine learning algorithms to fuse the data from PMMG-based thighrings and IMUs. We recruited three experimental subjects and constructed two datasets for different walking conditions: constant speed walking and variable speed walking. Experimental results show that the proposed PMMG sensor is effective, and the gait phase recognition accuracy reached 96.25% by using only the PMMG-based thighrings. In addition, we found that the performance of multi-modal sensor fusion is better than that of single-modal sensor fusion through three comparative experiments. Among the five machine learning algorithms, the SVM fusion model got the highest average accuracy of 98.82%.
{"title":"Gait Phase Recognition Based on Air-pressure Mechanomyogram and Sensor Fusion","authors":"E. Wang, Jian Huang, Yuge Li, Yuqi Cui, Xiaolong Li","doi":"10.1109/ICARM52023.2021.9536119","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536119","url":null,"abstract":"Gait phase recognition can improve the control of lower limb exoskeleton robot and promote human-machine collaboration. One of the current mainstream methods is to use electromyogram (EMG) to recognize gait phase, but the EMG signal has shortcomings such as weak signal, difficult to wear, easy to be affected by noise and sweat. Therefore, we designed a novel air-pressure mechanomyograph (PMMG) sensor, and further made a wearable PMMG-based sensing system composed of PMMG-based thighrings and inertial measurement units (IMUs). In order to improve the performance of gait phase recognition, we used five popular machine learning algorithms to fuse the data from PMMG-based thighrings and IMUs. We recruited three experimental subjects and constructed two datasets for different walking conditions: constant speed walking and variable speed walking. Experimental results show that the proposed PMMG sensor is effective, and the gait phase recognition accuracy reached 96.25% by using only the PMMG-based thighrings. In addition, we found that the performance of multi-modal sensor fusion is better than that of single-modal sensor fusion through three comparative experiments. Among the five machine learning algorithms, the SVM fusion model got the highest average accuracy of 98.82%.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129777574","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536115
Chong Li, Ying Feng, H. Yoong, Mingwei Liang, J. Chen
Novel designs and control methods have been addressed in areas from sensing technology to robotics with the development of smart materials and compliant actuating components, which are showing some good actuating performances compared with the traditional actuating components utilizing air valves, hydraulic pumps and electro-motors. In this paper, the working properties of a class of compliant actuators utilizing liquid alloy conductors, and magnetorheological elastomers (MREs) are discussed. The magnetorheological (MR) effect in the complaint MRE actuators are analyzed so the working properties between input (voltage)and the output (displacement) can be modeled analytically.
{"title":"Working Properties of Compliant Actuators Based on Magnetorheological Elastomer","authors":"Chong Li, Ying Feng, H. Yoong, Mingwei Liang, J. Chen","doi":"10.1109/ICARM52023.2021.9536115","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536115","url":null,"abstract":"Novel designs and control methods have been addressed in areas from sensing technology to robotics with the development of smart materials and compliant actuating components, which are showing some good actuating performances compared with the traditional actuating components utilizing air valves, hydraulic pumps and electro-motors. In this paper, the working properties of a class of compliant actuators utilizing liquid alloy conductors, and magnetorheological elastomers (MREs) are discussed. The magnetorheological (MR) effect in the complaint MRE actuators are analyzed so the working properties between input (voltage)and the output (displacement) can be modeled analytically.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127409017","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536161
Zhihao Zhang, Fei Meng, Lei Wang, Ru Kang, Sai Gu, Botao Liu, Xuxiao Fan, A. Ming, Qiang Huang
Wheel-legged robots have the potential of highly dynamic locomotion. The development of Wheel-legged robots might extend the capabilities and provide a solution to the challenges of legged robots. We first modeled our self-developed quadruped experimental platform and expanded our previous work. For the scene of long-range and high-speed movement, we propose a deviation-based online locomotion planner to improve the efficiency and stability of a wheeled quadrupedal robot by reducing unnecessary steps. In the process, relative deviation values are obtained by comparing the ideal foothold reference with the actual wheel position and used to generate locomotion commands. With a control framework of robot locomotion based on a whole-body controller, the robot can move stably for a long distance in the simulation environment. The simulation results also show that compared with the time-based scheduler, this approach has advantages in efficiency and stability.
{"title":"Online Locomotion Planner For Wheeled Quadrupedal Robot Using Deviation Based Scheduler","authors":"Zhihao Zhang, Fei Meng, Lei Wang, Ru Kang, Sai Gu, Botao Liu, Xuxiao Fan, A. Ming, Qiang Huang","doi":"10.1109/ICARM52023.2021.9536161","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536161","url":null,"abstract":"Wheel-legged robots have the potential of highly dynamic locomotion. The development of Wheel-legged robots might extend the capabilities and provide a solution to the challenges of legged robots. We first modeled our self-developed quadruped experimental platform and expanded our previous work. For the scene of long-range and high-speed movement, we propose a deviation-based online locomotion planner to improve the efficiency and stability of a wheeled quadrupedal robot by reducing unnecessary steps. In the process, relative deviation values are obtained by comparing the ideal foothold reference with the actual wheel position and used to generate locomotion commands. With a control framework of robot locomotion based on a whole-body controller, the robot can move stably for a long distance in the simulation environment. The simulation results also show that compared with the time-based scheduler, this approach has advantages in efficiency and stability.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123459318","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536189
Longbin Zhang, Xueyu Zhu, Elena Gutierrez Farewik, Ruoli Wang
In this paper, a neuromusculoskeletal (NMS) solver-informed artificial neural network (ANN) is proposed to estimate ankle joint torques in seven movements, including walking at fast, slow and self-selected speeds, ankle isokinetic dorsi- and plantarflexion at 60 and 90°/s. The NMS solver-informed ANN model is an extension of a standard ANN model with additional features from an NMS solver, namely ankle joint torque and muscle forces. The standard ANN, the NMS solver-informed ANN and a muscle-driven NMS model, were used to predict ankle torque. Prediction accuracy were compared, based on data capture in 10 subjects. In all methods, we trained the models with measured ankle joint angle and electromyography signals as inputs. Seven different cases were investigated, using trials at different speeds across three movement types (walking, isokinetic plantarflexion and dorsiflexion) to calibrate/train models in the same movement types. The NMS solver-informed ANN model predicted ankle joint torque better than both the NMS and standard ANN models, which indicates benefit gained from integrating NMS features into standard ANN models. The proposed NMS solver informed-ANN model thus shows promise in assistance-as-needed rehabilitation exoskeleton controller design.
{"title":"Estimation of Ankle Dynamic Joint Torque by a Neuromusculoskeletal Solver-informed NN Model","authors":"Longbin Zhang, Xueyu Zhu, Elena Gutierrez Farewik, Ruoli Wang","doi":"10.1109/ICARM52023.2021.9536189","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536189","url":null,"abstract":"In this paper, a neuromusculoskeletal (NMS) solver-informed artificial neural network (ANN) is proposed to estimate ankle joint torques in seven movements, including walking at fast, slow and self-selected speeds, ankle isokinetic dorsi- and plantarflexion at 60 and 90°/s. The NMS solver-informed ANN model is an extension of a standard ANN model with additional features from an NMS solver, namely ankle joint torque and muscle forces. The standard ANN, the NMS solver-informed ANN and a muscle-driven NMS model, were used to predict ankle torque. Prediction accuracy were compared, based on data capture in 10 subjects. In all methods, we trained the models with measured ankle joint angle and electromyography signals as inputs. Seven different cases were investigated, using trials at different speeds across three movement types (walking, isokinetic plantarflexion and dorsiflexion) to calibrate/train models in the same movement types. The NMS solver-informed ANN model predicted ankle joint torque better than both the NMS and standard ANN models, which indicates benefit gained from integrating NMS features into standard ANN models. The proposed NMS solver informed-ANN model thus shows promise in assistance-as-needed rehabilitation exoskeleton controller design.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126845210","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}
Amphibious robots can be used in both land and underwater environments, which has a wider range of applications than traditional mobile robots. However, the development of propulsion mechanisms for use in amphibious environments is very challenging. In this study, a new type of composite propulsion mechanism is presented, hinged by a plurality of deformable joints, and is suitable for amphibious environments. By changing the relative position of the rotation center of the slider chain and the rotation center of the outer track, the mechanism can be transformed between the land curved-legged state and the underwater webbed state. The mechanism has the advantages of high terrain adaptability and fast speed of curved legs when moving on land, and has good webbed flexibility when moving underwater. In this paper, aiming at the typical terrain of the amphibious environment, a new amphibious robot equipped with the propulsion mechanism is developed, and the kinematic performance of the amphibious robot is tested. The results show that the design method of composite propulsion mechanism suitable for the amphibious environment can improve amphibious robots’ kinematic performance and provide a valuable reference for the design and control of other amphibious robots.
{"title":"Amphibious Robot with a Novel Composite Propulsion Mechanism","authors":"L. Bai, Gongzhi Dou, Wenbo Duan, Yuanxi Sun, Jia Zheng, Xiaohong Chen","doi":"10.1109/ICARM52023.2021.9536191","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536191","url":null,"abstract":"Amphibious robots can be used in both land and underwater environments, which has a wider range of applications than traditional mobile robots. However, the development of propulsion mechanisms for use in amphibious environments is very challenging. In this study, a new type of composite propulsion mechanism is presented, hinged by a plurality of deformable joints, and is suitable for amphibious environments. By changing the relative position of the rotation center of the slider chain and the rotation center of the outer track, the mechanism can be transformed between the land curved-legged state and the underwater webbed state. The mechanism has the advantages of high terrain adaptability and fast speed of curved legs when moving on land, and has good webbed flexibility when moving underwater. In this paper, aiming at the typical terrain of the amphibious environment, a new amphibious robot equipped with the propulsion mechanism is developed, and the kinematic performance of the amphibious robot is tested. The results show that the design method of composite propulsion mechanism suitable for the amphibious environment can improve amphibious robots’ kinematic performance and provide a valuable reference for the design and control of other amphibious robots.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"122 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114049408","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536181
Guo He, Fei Zhang, Xiang Li, Weiwei Shang
Aiming at the degradation of lidar, we propose a Robust Mapping and Localization (RMAL) method, which combines the classic Extended Kalman Filter (EKF) algorithm with the back-end pose graph optimization for 3D real-time mapping. Utilizing the complementary advantages of multiple sensors, the robustness of the mapping method is enhanced. In addition, we choose to save the feature keyframes and the corresponding optimal pose transformations as the offline map during the mapping process. Cooperating with subsequent mapping again, we can improve the positioning accuracy of the robot in the offline map. Finally, we also conduct experimental tests in different real scenarios, and the results verify the robustness and engineering practicability of the proposed method.
{"title":"Robust Mapping and Localization in Offline 3D Point Cloud Maps","authors":"Guo He, Fei Zhang, Xiang Li, Weiwei Shang","doi":"10.1109/ICARM52023.2021.9536181","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536181","url":null,"abstract":"Aiming at the degradation of lidar, we propose a Robust Mapping and Localization (RMAL) method, which combines the classic Extended Kalman Filter (EKF) algorithm with the back-end pose graph optimization for 3D real-time mapping. Utilizing the complementary advantages of multiple sensors, the robustness of the mapping method is enhanced. In addition, we choose to save the feature keyframes and the corresponding optimal pose transformations as the offline map during the mapping process. Cooperating with subsequent mapping again, we can improve the positioning accuracy of the robot in the offline map. Finally, we also conduct experimental tests in different real scenarios, and the results verify the robustness and engineering practicability of the proposed method.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123927563","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 : 2021-07-03DOI: 10.1109/ICARM52023.2021.9536088
Min Zhang, Wenxia Xu, Baocheng Yu, Deng Cheng, Jian Huang, Moutang Fan, Jing Wu
Composite material is widely used in modern industry due to its high strength, aging resistance, and strong environmental adaptability. Therefore, composite material manufacturers have a growing need to improve the production efficiency of composite materials. Then, a composite rod scraper robot for the production of composite materials and a complex trajectory planning-based motion control algorithm are proposed. Firstly, the mechanism and principle of the composite rod scraper robot are first introduced. According to the scraping model of rectangular composite rod and the process of mandrel rotation, the trajectory of the scraper head is analyzed. Then the trajectory planning method for the rectangular composite rod is presented. Finally, the validity of the proposed algorithm is confirmed by the experiments. The experimental results show that the designed composite rod scraper robot can follow the trajectory of rotating mandrel precisely with complex trajectory planning method.
{"title":"Complex Trajectory Planning based Motion Control Algorithm for Compliance Composite Rod Scraper Robot","authors":"Min Zhang, Wenxia Xu, Baocheng Yu, Deng Cheng, Jian Huang, Moutang Fan, Jing Wu","doi":"10.1109/ICARM52023.2021.9536088","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536088","url":null,"abstract":"Composite material is widely used in modern industry due to its high strength, aging resistance, and strong environmental adaptability. Therefore, composite material manufacturers have a growing need to improve the production efficiency of composite materials. Then, a composite rod scraper robot for the production of composite materials and a complex trajectory planning-based motion control algorithm are proposed. Firstly, the mechanism and principle of the composite rod scraper robot are first introduced. According to the scraping model of rectangular composite rod and the process of mandrel rotation, the trajectory of the scraper head is analyzed. Then the trajectory planning method for the rectangular composite rod is presented. Finally, the validity of the proposed algorithm is confirmed by the experiments. The experimental results show that the designed composite rod scraper robot can follow the trajectory of rotating mandrel precisely with complex trajectory planning method.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115876202","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}
The three-dimensional porous structure is a common scene in the field of medical surgery. However, the imaging resolution of the endoscope is low, and its scene has weak texture features and high noise, which leads it difficult for traditional algorithms to segment the porous structure. In this study, a new approach for efficient segmentation of intrarenal porous areas in endoscopic images is put forward. The proposed method first classifies the images into deep and shallow groups based on the statistical vectors derived from the color feature histogram. Then for each group, the improved U-Net learning strategy is used to extract the intrarenal porous areas at the pixel level, and its segmentation results could be accurately obtained. The effectiveness and accuracy of this work are evaluated on the data of the ureteroscopic holmium laser lithotripsy.
{"title":"A Study on Intrarenal Porous Segmentation of Endoscopic Images","authors":"Yu Zhao, Rui Li, Minghui Han, Gongping Chen, Yu Dai, Jianxun Zhang","doi":"10.1109/ICARM52023.2021.9536211","DOIUrl":"https://doi.org/10.1109/ICARM52023.2021.9536211","url":null,"abstract":"The three-dimensional porous structure is a common scene in the field of medical surgery. However, the imaging resolution of the endoscope is low, and its scene has weak texture features and high noise, which leads it difficult for traditional algorithms to segment the porous structure. In this study, a new approach for efficient segmentation of intrarenal porous areas in endoscopic images is put forward. The proposed method first classifies the images into deep and shallow groups based on the statistical vectors derived from the color feature histogram. Then for each group, the improved U-Net learning strategy is used to extract the intrarenal porous areas at the pixel level, and its segmentation results could be accurately obtained. The effectiveness and accuracy of this work are evaluated on the data of the ureteroscopic holmium laser lithotripsy.","PeriodicalId":367307,"journal":{"name":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117287650","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：