Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268294
Ji-Seok Han, Tae-Ho Oh, Young-Seok Kim, Hyun-Taek Lim, Dae-Young Yang, Sang-Hoon Lee, D. Cho
This paper designed a new robust velocity control method for industrial servo systems. Exogenous disturbances and control input saturation are considered by using the discrete-time Sliding mode control with Decoupled disturbance compensator and Auxiliary state (SDA) method. The discrete-time SDA method preserves the original stability of the sliding mode dynamics as well as the stability of the disturbance estimation error dynamics under both control input saturation and disturbance. Due to these attributes, the discrete-time SDA method has been utilized in various control applications. In this paper, the discrete-time SDA method is newly designed for velocity control applications. Based on the error dynamics of the discrete-time SDA method, the gain of the auxiliary state is set to "1". This design provides the stability of velocity error, and there is nearly zero overshoot under control input saturation. Experiments are performed to demonstrate the performance of the designed control method.
{"title":"Velocity Control of Servo Systems Under Control Input Saturation and Disturbance Using Robust Discrete-Time Sliding Mode Control Method","authors":"Ji-Seok Han, Tae-Ho Oh, Young-Seok Kim, Hyun-Taek Lim, Dae-Young Yang, Sang-Hoon Lee, D. Cho","doi":"10.23919/ICCAS50221.2020.9268294","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268294","url":null,"abstract":"This paper designed a new robust velocity control method for industrial servo systems. Exogenous disturbances and control input saturation are considered by using the discrete-time Sliding mode control with Decoupled disturbance compensator and Auxiliary state (SDA) method. The discrete-time SDA method preserves the original stability of the sliding mode dynamics as well as the stability of the disturbance estimation error dynamics under both control input saturation and disturbance. Due to these attributes, the discrete-time SDA method has been utilized in various control applications. In this paper, the discrete-time SDA method is newly designed for velocity control applications. Based on the error dynamics of the discrete-time SDA method, the gain of the auxiliary state is set to \"1\". This design provides the stability of velocity error, and there is nearly zero overshoot under control input saturation. Experiments are performed to demonstrate the performance of the designed control method.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"66 1","pages":"1034-1038"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81376507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268328
Arpan Ghosh, Jeongwon Pyo, Tae-Yong Kuc
In this paper, we propose a modular approach to estimate the position and rotation of any mobile robot more precisely in an indoor environment using text and sign recognition. The modular approach for the text and sign recognition is performed in a twofold method in figure 1. First is the detection of the region with texts and various signs in the image which is done by an object detection system. The second part is the character recognition, where the detected textual region from the image will be passed onto an optical character recognition engine(OCR) engine to be recognized. This modular approach can be modified at any point based on any mobile robot in an indoor environment with texts and signs to help localize its position and rotation.
{"title":"Text and Sign Recognition for Indoor Localization","authors":"Arpan Ghosh, Jeongwon Pyo, Tae-Yong Kuc","doi":"10.23919/ICCAS50221.2020.9268328","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268328","url":null,"abstract":"In this paper, we propose a modular approach to estimate the position and rotation of any mobile robot more precisely in an indoor environment using text and sign recognition. The modular approach for the text and sign recognition is performed in a twofold method in figure 1. First is the detection of the region with texts and various signs in the image which is done by an object detection system. The second part is the character recognition, where the detected textual region from the image will be passed onto an optical character recognition engine(OCR) engine to be recognized. This modular approach can be modified at any point based on any mobile robot in an indoor environment with texts and signs to help localize its position and rotation.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"1 1","pages":"1006-1009"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85286750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268295
Younggeol Cho, Pyungkang Kim, Kyung-Soo Kim
For a several decades, myoelectric control of robotic prosthesis has used electromyograpy (EMG) as its control input to infer human intention. In this paper, we propose to use impedance change of musculoskeletal system to estimate kinematics change of human hand in prosthesis control based on its several features superior to the EMG as follows: clearer signal with much less noise so is less delay caused by filtering and little change of the signal at stationary state of hand motion. We investigated these features of electrical impedance myography (EIM) through several experiments. The result shows it is only minute change of signal occurs at the stationary pose. Although it is sensitive to the motion of other parts (e.g. elbow), it is surely a promising signal for the control of robotic prosthetic hand.
{"title":"Electrical impedance myography (EIM) For multi-class prosthetic robot hand control","authors":"Younggeol Cho, Pyungkang Kim, Kyung-Soo Kim","doi":"10.23919/ICCAS50221.2020.9268295","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268295","url":null,"abstract":"For a several decades, myoelectric control of robotic prosthesis has used electromyograpy (EMG) as its control input to infer human intention. In this paper, we propose to use impedance change of musculoskeletal system to estimate kinematics change of human hand in prosthesis control based on its several features superior to the EMG as follows: clearer signal with much less noise so is less delay caused by filtering and little change of the signal at stationary state of hand motion. We investigated these features of electrical impedance myography (EIM) through several experiments. The result shows it is only minute change of signal occurs at the stationary pose. Although it is sensitive to the motion of other parts (e.g. elbow), it is surely a promising signal for the control of robotic prosthetic hand.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"26 1","pages":"1092-1094"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86833001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268303
Julia Baumgärtner, Henrik Bey, Dennis Fassbender, J. Thielecke
Automated vehicles perceive only a small part of their environment. Especially unobservable vehicles pose a significant risk. To achieve safe but also comfortable behavior, potential, unobservable vehicles must be considered in behavior planning. Conventional methods use solely the current observation of the environment to determine potential obstacles. Past observations are rarely considered, although these may contain helpful information to rule out potential obstacle positions. This paper presents a novel algorithm that uses past observations besides the current observation to determine possible obstacle states. By means of a particle filter, we iteratively predict and filter feasible states of a potential obstacle. This results in a probability distribution for the position and velocity of an unobservable obstacle. We furthermore present a concept for the interface between our method and a basic behavior planning algorithm. The real-time capable method is tested on both simulated and real-world data. By comparing the algorithm to a baseline algorithm which uses only the current observation, we show that our algorithm prevents overly cautious assumptions about a potential obstacle’s state in certain situations. As a result, a more comfortable driving behavior can be achieved.
{"title":"Determining Potential Obstacles in Unobservable Areas Based on Current and Past Perception","authors":"Julia Baumgärtner, Henrik Bey, Dennis Fassbender, J. Thielecke","doi":"10.23919/ICCAS50221.2020.9268303","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268303","url":null,"abstract":"Automated vehicles perceive only a small part of their environment. Especially unobservable vehicles pose a significant risk. To achieve safe but also comfortable behavior, potential, unobservable vehicles must be considered in behavior planning. Conventional methods use solely the current observation of the environment to determine potential obstacles. Past observations are rarely considered, although these may contain helpful information to rule out potential obstacle positions. This paper presents a novel algorithm that uses past observations besides the current observation to determine possible obstacle states. By means of a particle filter, we iteratively predict and filter feasible states of a potential obstacle. This results in a probability distribution for the position and velocity of an unobservable obstacle. We furthermore present a concept for the interface between our method and a basic behavior planning algorithm. The real-time capable method is tested on both simulated and real-world data. By comparing the algorithm to a baseline algorithm which uses only the current observation, we show that our algorithm prevents overly cautious assumptions about a potential obstacle’s state in certain situations. As a result, a more comfortable driving behavior can be achieved.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"32 1","pages":"761-768"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87216713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268405
Hyeong Heo, Dae Jung Kim, C. Chung
In this paper, we propose an estimation of the accurate vehicle position using Interacting Multiple Model Extended Kalman Filter (IMM EKF) when road surface varies. Since the vehicle has different cornering stiffness as the road surface varies, it is difficult to accurately estimate the position of the vehicle. To resolve this problem, we present the IMM EKF considering each model of different roads to improve the estimation performance. From the numerical simulation using MATLAB/CARSIM, we observed that the performance of the proposed algorithm improves vehicle positioning performance.
{"title":"IMM EKF based Sensor Fusion for Vehicle Positioning Under Various Road Surface Conditions","authors":"Hyeong Heo, Dae Jung Kim, C. Chung","doi":"10.23919/ICCAS50221.2020.9268405","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268405","url":null,"abstract":"In this paper, we propose an estimation of the accurate vehicle position using Interacting Multiple Model Extended Kalman Filter (IMM EKF) when road surface varies. Since the vehicle has different cornering stiffness as the road surface varies, it is difficult to accurately estimate the position of the vehicle. To resolve this problem, we present the IMM EKF considering each model of different roads to improve the estimation performance. From the numerical simulation using MATLAB/CARSIM, we observed that the performance of the proposed algorithm improves vehicle positioning performance.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"62 1","pages":"1220-1224"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83022741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268275
Toui Ogawa, Humin Lu, A. Watanabe, I. Omura, Tohru Kamiya
Power devices are semiconductor devices that handle high voltages and large currents, which are used in electric vehicles, televisions, and trains. Therefore, high reliability and safety are required, and to ensure this, power cycle tests are performed to analyze the breakdown process. Conventional tests are often difficult to analyze due to the influence of sparks generated during the test. Therefore, new tests are being developed by adding ultrasound to conventional methods. The new technology is capable of continuously recording structural changes inside the device during testing, which is expected to make testing much easier than conventional testing. However, the new technology still has some challenges. The main problems are the lack of a method for analyzing large amounts of image data and the extraction of small changes in image features that are difficult to distinguish with the human eye, and the establishment of such a system is required. In this paper, we use deep learning for image classification of the obtained ultrasound images. We propose a new network model with the addition of Batch normalization and Global average pooling to VGG16, which is a pre-trained model. In the experiment, accuracy=98.29%, TPR=98.96% and FPR=7.43% classification accuracy was obtained.
{"title":"Identification of normal and abnormal from ultrasound images of power devices using VGG16","authors":"Toui Ogawa, Humin Lu, A. Watanabe, I. Omura, Tohru Kamiya","doi":"10.23919/ICCAS50221.2020.9268275","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268275","url":null,"abstract":"Power devices are semiconductor devices that handle high voltages and large currents, which are used in electric vehicles, televisions, and trains. Therefore, high reliability and safety are required, and to ensure this, power cycle tests are performed to analyze the breakdown process. Conventional tests are often difficult to analyze due to the influence of sparks generated during the test. Therefore, new tests are being developed by adding ultrasound to conventional methods. The new technology is capable of continuously recording structural changes inside the device during testing, which is expected to make testing much easier than conventional testing. However, the new technology still has some challenges. The main problems are the lack of a method for analyzing large amounts of image data and the extraction of small changes in image features that are difficult to distinguish with the human eye, and the establishment of such a system is required. In this paper, we use deep learning for image classification of the obtained ultrasound images. We propose a new network model with the addition of Batch normalization and Global average pooling to VGG16, which is a pre-trained model. In the experiment, accuracy=98.29%, TPR=98.96% and FPR=7.43% classification accuracy was obtained.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"23 4","pages":"415-418"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91469777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268219
M. Astrid, M. Zaheer, Jin-ha Lee, Jae-Yeong Lee, Seung-Ik Lee
Extensive research has been carried out on intersection classification to assist the navigation in autonomous maneuvering of aerial, road, and cave mining vehicles. In contrast, our work tackles intersection classification at pedestrian-view level to support navigation of the slower and smaller robots for which it is too dangerous to steer on a normal road along with the usual vehicles. Particularly, we focus on investigating the kind of features a network may exploit in order to classify intersection at pedestrian-view. To this end, two sets of experiments have been conducted using an ImageNet-pretrained ResNet-18 architecture fine-tuned on our image-level pedestrian-view intersection classification dataset. First, ablation study is performed on layer depth to evaluate the importance of high-level feature, which demonstrated superiority in using all of the layers by yielding 77.56% accuracy. Second, to further clarify the need of such high level features, Class Activation Map (CAM) is applied to visualize the parts of an image that affect the most on a given prediction. The visualization justifies the high accuracy of an all-layers network.
{"title":"What Do Pedestrians See?: Visualizing Pedestrian-View Intersection Classification","authors":"M. Astrid, M. Zaheer, Jin-ha Lee, Jae-Yeong Lee, Seung-Ik Lee","doi":"10.23919/ICCAS50221.2020.9268219","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268219","url":null,"abstract":"Extensive research has been carried out on intersection classification to assist the navigation in autonomous maneuvering of aerial, road, and cave mining vehicles. In contrast, our work tackles intersection classification at pedestrian-view level to support navigation of the slower and smaller robots for which it is too dangerous to steer on a normal road along with the usual vehicles. Particularly, we focus on investigating the kind of features a network may exploit in order to classify intersection at pedestrian-view. To this end, two sets of experiments have been conducted using an ImageNet-pretrained ResNet-18 architecture fine-tuned on our image-level pedestrian-view intersection classification dataset. First, ablation study is performed on layer depth to evaluate the importance of high-level feature, which demonstrated superiority in using all of the layers by yielding 77.56% accuracy. Second, to further clarify the need of such high level features, Class Activation Map (CAM) is applied to visualize the parts of an image that affect the most on a given prediction. The visualization justifies the high accuracy of an all-layers network.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"86 1","pages":"769-773"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84144193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268270
Amir Ramezani Dooraki, D. Lee
In this research, we show how a reinforcement learning based algorithm called Fault-Tolerant Bio-inspired Flight Controller (FT-BFC) is capable of training a single neural network based model to fly a quadcopter with two, three, and four working rotors. Our algorithm can learn a low-level flight controller that directly controls angular velocities of motors to fly a quadcopter when it has four fully functional motors, and also, despite having one or two motor failures (That is, our proposed flight controller is a fault-tolerant controller as well). In the training and running of our controller, we do not use any conventional flight controller, such as a PID or SMC controller. We test our algorithm in a simulation environment, Gazebo simulator, and illustrate our simulation results that backing up our algorithm capabilities. Finally, before concluding our paper, we discuss the implementation of our algorithm in a real quadcopter.
{"title":"Reinforcement learning based flight controller capable of controlling a quadcopter with four, three and two working motors","authors":"Amir Ramezani Dooraki, D. Lee","doi":"10.23919/ICCAS50221.2020.9268270","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268270","url":null,"abstract":"In this research, we show how a reinforcement learning based algorithm called Fault-Tolerant Bio-inspired Flight Controller (FT-BFC) is capable of training a single neural network based model to fly a quadcopter with two, three, and four working rotors. Our algorithm can learn a low-level flight controller that directly controls angular velocities of motors to fly a quadcopter when it has four fully functional motors, and also, despite having one or two motor failures (That is, our proposed flight controller is a fault-tolerant controller as well). In the training and running of our controller, we do not use any conventional flight controller, such as a PID or SMC controller. We test our algorithm in a simulation environment, Gazebo simulator, and illustrate our simulation results that backing up our algorithm capabilities. Finally, before concluding our paper, we discuss the implementation of our algorithm in a real quadcopter.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"71 1","pages":"161-166"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80053615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268243
Hoang Anh Tran, Hoang Viet Do, J. Song
The linear motor has been widely applied in industry to provide directly straight motion. The Polysolenoid Linear Motor (PLM), as its name, is one type of the synchronous linear machine. Toward the control problem of the PLM, state observation plays a crucial role due to the lack of measurement. In this paper, an Adaptive Unscented Kalman Filter (AUKF), which can provide reliable information of system state including applied current as well as position and velocity, is proposed. Furthermore, our observer can deal with the uncertainty load force and unknown unbias measurement noises adaptively, which contributes to robust and effective control of PLM with uncertain load condition. A scenario will be made to test the robutness of the algorithm under the value variation of measurement noise covariance. The performance of the system is verified by simulation in an illustrative example.
{"title":"State Estimation for Polysolenoid Linear Motor based on an Adaptive Unscented Kalman Filter with Unknown Load and Measurement Noises","authors":"Hoang Anh Tran, Hoang Viet Do, J. Song","doi":"10.23919/ICCAS50221.2020.9268243","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268243","url":null,"abstract":"The linear motor has been widely applied in industry to provide directly straight motion. The Polysolenoid Linear Motor (PLM), as its name, is one type of the synchronous linear machine. Toward the control problem of the PLM, state observation plays a crucial role due to the lack of measurement. In this paper, an Adaptive Unscented Kalman Filter (AUKF), which can provide reliable information of system state including applied current as well as position and velocity, is proposed. Furthermore, our observer can deal with the uncertainty load force and unknown unbias measurement noises adaptively, which contributes to robust and effective control of PLM with uncertain load condition. A scenario will be made to test the robutness of the algorithm under the value variation of measurement noise covariance. The performance of the system is verified by simulation in an illustrative example.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"21 1","pages":"643-647"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80443528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268397
Saba Arshad, Gon-Woo Kim
Place recognition has typically been addressed as a problem of recognizing the location of a given query image as a previously visited place while comparing it with the geotagged database images. Despite a lot of research in this area, vision-based place recognition is still an open challenge because of the changing environmental conditions which cause drastic appearance changes, making it difficult for a robot to recognize the place. This research addresses the above-mentioned problem and proposes the solution for place recognition at a low memory footprint. The proposed place recognition system focuses on identifying the combination of different feature detectors and descriptors that are invariant to the viewpoint and seasonal changes and can efficiently recognize a place at high accuracy. Through experimental results, it is shown that combination of CenSure based STAR detector and BRISK achieves high detection accuracy.
{"title":"An Appearance and Viewpoint Invariant Visual Place Recognition for Seasonal Changes","authors":"Saba Arshad, Gon-Woo Kim","doi":"10.23919/ICCAS50221.2020.9268397","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268397","url":null,"abstract":"Place recognition has typically been addressed as a problem of recognizing the location of a given query image as a previously visited place while comparing it with the geotagged database images. Despite a lot of research in this area, vision-based place recognition is still an open challenge because of the changing environmental conditions which cause drastic appearance changes, making it difficult for a robot to recognize the place. This research addresses the above-mentioned problem and proposes the solution for place recognition at a low memory footprint. The proposed place recognition system focuses on identifying the combination of different feature detectors and descriptors that are invariant to the viewpoint and seasonal changes and can efficiently recognize a place at high accuracy. Through experimental results, it is shown that combination of CenSure based STAR detector and BRISK achieves high detection accuracy.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"15 1","pages":"1206-1211"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77868409","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：