Xu Su, Lubin Hang, Hui Guo, Mingyuan Wang, Zhe Liu, Yong Chen, Yong Hua, Jinliang Du
The sound quality of the vehicle door latch directly affects the subjective evaluation of the passengers. Aiming at studying gear position recovering noise externally produced by the novel electric opening branch inside the latch, the relationship between gear's torque, angular velocity, and angular acceleration are analyzed. With the gear shaft taken as the center axis of rotation and the other direction of freedom constrained, a three-dimensional gear meshing finite element simulation model is established. The acceleration of gear is calculated using Abaqus software. Based on the boundary element method, the latch embodiments are abstracted into a physical model. The acceleration data is imported into the acoustic transient boundary element module, then the acoustic radiation analysis of the gear high-speed light-load transmission is carried out. The results show that the model can reflect the nonlinear force of the gears during high-speed light-load transmission and the position recovering characteristics of the electric opening branch. Finally, the time-domain acoustic response of the electric opening branch gears is calculated and has a good matching relationship with the input torque of gear. It has certain reference significance for the analysis and optimization of the vehicle door latch sound quality.c
{"title":"Simulation Research of Gear Recovery Noise in Electric Opening Branch with the Vehicle Door Latch","authors":"Xu Su, Lubin Hang, Hui Guo, Mingyuan Wang, Zhe Liu, Yong Chen, Yong Hua, Jinliang Du","doi":"10.1145/3366194.3366215","DOIUrl":"https://doi.org/10.1145/3366194.3366215","url":null,"abstract":"The sound quality of the vehicle door latch directly affects the subjective evaluation of the passengers. Aiming at studying gear position recovering noise externally produced by the novel electric opening branch inside the latch, the relationship between gear's torque, angular velocity, and angular acceleration are analyzed. With the gear shaft taken as the center axis of rotation and the other direction of freedom constrained, a three-dimensional gear meshing finite element simulation model is established. The acceleration of gear is calculated using Abaqus software. Based on the boundary element method, the latch embodiments are abstracted into a physical model. The acceleration data is imported into the acoustic transient boundary element module, then the acoustic radiation analysis of the gear high-speed light-load transmission is carried out. The results show that the model can reflect the nonlinear force of the gears during high-speed light-load transmission and the position recovering characteristics of the electric opening branch. Finally, the time-domain acoustic response of the electric opening branch gears is calculated and has a good matching relationship with the input torque of gear. It has certain reference significance for the analysis and optimization of the vehicle door latch sound quality.c","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122347330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development of the automotive industry, the active safety of automobiles has received more and more attention, which is the most promising topic in automotive technology research. The vehicle active collision avoidance system is an early warning assistance system aimed at improving driving safety, and the electric vehicle is an emerging automobile industry. At present, there are still many problems in the research on the active safety collision avoidance system of pure electric vehicles. This paper is a fuzzy control strategy control method to improve the active safety of the car, effectively prevent the occurrence of traffic accidents, and improve the stability and comfort of the vehicle during high-speed driving. Among them, the mathematical model of two-degree-of-freedom vehicle is established, the control strategy of vehicle anti-collision is studied, the Simulink model of the vehicle is constructed, and the fuzzy control is simulated and analyzed. It can be seen from the simulation results that the fuzzy control strategy used can improve the car collision.
{"title":"Research on anti-collision control of pure electric vehicles","authors":"Keke Ouyang, Yanliang Li, Bo Yang","doi":"10.1145/3366194.3366308","DOIUrl":"https://doi.org/10.1145/3366194.3366308","url":null,"abstract":"With the development of the automotive industry, the active safety of automobiles has received more and more attention, which is the most promising topic in automotive technology research. The vehicle active collision avoidance system is an early warning assistance system aimed at improving driving safety, and the electric vehicle is an emerging automobile industry. At present, there are still many problems in the research on the active safety collision avoidance system of pure electric vehicles. This paper is a fuzzy control strategy control method to improve the active safety of the car, effectively prevent the occurrence of traffic accidents, and improve the stability and comfort of the vehicle during high-speed driving. Among them, the mathematical model of two-degree-of-freedom vehicle is established, the control strategy of vehicle anti-collision is studied, the Simulink model of the vehicle is constructed, and the fuzzy control is simulated and analyzed. It can be seen from the simulation results that the fuzzy control strategy used can improve the car collision.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129185621","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}
Chengcheng Zhang, Jianmin Zhou, Lining Sun, Guoqing Jin
In this paper, we present the design, fabrication processes, and control of a new biomimetic origami robot-Pillbot inspired by the pill bugs (Armadillidium vulgare). The pill bugs can travel effectively along pile of dead leaves, weeds, and most nature environment and the biological structures of the pill bugs fit the practical, soft and flexible design concept of the soft robotics. This biological case can be applied to soft robots to overcome the real harsh natural environment by three bionic designs: 1) flexible origami exoskeleton, 2) soft internal muscles, 3) bionic pereiopods. The origami exoskeleton is used to protect the body and reduce the friction between the robot surface and the environment. The soft internal muscles support the completion of the corresponding function with the exoskeleton and other structures of the robot. The bionic pereiopods ensure that the Pillbot can perform a variety of crawling movements. As a result, Pillbot can crawl, turn effective in the real environment, and the innovative designs for Pillbot will be applied to soft robots that are used in a harsh realistic environment.
{"title":"Pillbot: a soft origami robot inspired by pill bugs","authors":"Chengcheng Zhang, Jianmin Zhou, Lining Sun, Guoqing Jin","doi":"10.1145/3366194.3366315","DOIUrl":"https://doi.org/10.1145/3366194.3366315","url":null,"abstract":"In this paper, we present the design, fabrication processes, and control of a new biomimetic origami robot-Pillbot inspired by the pill bugs (Armadillidium vulgare). The pill bugs can travel effectively along pile of dead leaves, weeds, and most nature environment and the biological structures of the pill bugs fit the practical, soft and flexible design concept of the soft robotics. This biological case can be applied to soft robots to overcome the real harsh natural environment by three bionic designs: 1) flexible origami exoskeleton, 2) soft internal muscles, 3) bionic pereiopods. The origami exoskeleton is used to protect the body and reduce the friction between the robot surface and the environment. The soft internal muscles support the completion of the corresponding function with the exoskeleton and other structures of the robot. The bionic pereiopods ensure that the Pillbot can perform a variety of crawling movements. As a result, Pillbot can crawl, turn effective in the real environment, and the innovative designs for Pillbot will be applied to soft robots that are used in a harsh realistic environment.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127566052","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 length of dry beach determines the safety and stability of tailings dam. In order to measure the dry beach length more accurately, we put forward a method of measuring the dry beach length of tailings dam based on deep learning. This method is carried out in three steps:(1) installing monitoring cameras on both sides of tailings dam. (2) training the network model based on Mask R-CNN algorithm, identify waterline and outputs waterline coordinates. (3) measuring the length of dry beach by video screen in real time through inputting the waterline coordinates into the functional relationship between waterline coordinates and measured values. The results show that this model can accurately measure the length of dry beach, and is suitable for the conditions of insufficient illumination, blurred image, rain and snow.
{"title":"Measure Dry Beach Length of Tailings Pond Using Deep Learning Algorithm","authors":"Jun Yang, Yeqing Sun, Qing Li, Zhiyu Qian","doi":"10.1145/3366194.3366284","DOIUrl":"https://doi.org/10.1145/3366194.3366284","url":null,"abstract":"The length of dry beach determines the safety and stability of tailings dam. In order to measure the dry beach length more accurately, we put forward a method of measuring the dry beach length of tailings dam based on deep learning. This method is carried out in three steps:(1) installing monitoring cameras on both sides of tailings dam. (2) training the network model based on Mask R-CNN algorithm, identify waterline and outputs waterline coordinates. (3) measuring the length of dry beach by video screen in real time through inputting the waterline coordinates into the functional relationship between waterline coordinates and measured values. The results show that this model can accurately measure the length of dry beach, and is suitable for the conditions of insufficient illumination, blurred image, rain and snow.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128291516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid development of the mobile communication technology, the number of long-term evolution (LTE) users and the volume of data is continually increasing, which greatly increases the amount of data transferred by fronthaul, resulting in a huge investment in optical fiber resource. In order to control the consumption of optical fiber resource, lower the cost of operator and avoid congestion in the premise of increasing data volume, it is necessary to compress the data for fronthaul. According to the characteristics of the LTE baseband signal, this paper proposes a data compression scheme on the basis of discrete cosine transform (DCT) and vector quantization. Firstly, the time domain signal is transformed in DCT. And then, the k-means clustering algorithm is used for vector quantization on the transformed signal. Finally, the Huffman coding is applied to further increase the compression ratio (CR) under the promise of an acceptable error. The simulation results show that the scheme proposed has a good performance in both compression ratio and error vector Magnitude (EVM) for the LTE baseband signal base on orthogonal frequency division multiplexing (OFDM).
{"title":"Data Compression Scheme for Fronthaul Based on Vector Quantization","authors":"Chenwei Feng, Mingxia Lin, Xinlin Xie, Mingjiang Zhang","doi":"10.1145/3366194.3366238","DOIUrl":"https://doi.org/10.1145/3366194.3366238","url":null,"abstract":"With the rapid development of the mobile communication technology, the number of long-term evolution (LTE) users and the volume of data is continually increasing, which greatly increases the amount of data transferred by fronthaul, resulting in a huge investment in optical fiber resource. In order to control the consumption of optical fiber resource, lower the cost of operator and avoid congestion in the premise of increasing data volume, it is necessary to compress the data for fronthaul. According to the characteristics of the LTE baseband signal, this paper proposes a data compression scheme on the basis of discrete cosine transform (DCT) and vector quantization. Firstly, the time domain signal is transformed in DCT. And then, the k-means clustering algorithm is used for vector quantization on the transformed signal. Finally, the Huffman coding is applied to further increase the compression ratio (CR) under the promise of an acceptable error. The simulation results show that the scheme proposed has a good performance in both compression ratio and error vector Magnitude (EVM) for the LTE baseband signal base on orthogonal frequency division multiplexing (OFDM).","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"340 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115887496","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}
Tingting Yao, Tao He, Wenlong Zhao, Abdou Yahouza M. Sani
An autonomous underwater vehicle (AUV) is an important tool for the exploration and development of marine resources. Path planning plays an important role in the correct navigation and avoidance of obstacles by underwater robots in the sea. Firstly, according to different marine environmental conditions, AUV path planning is classified into two types. Then, the related algorithms of global path planning and local path planning are reviewed, and the key technologies, development status, advantages and disadvantages of related algorithms are combed. Finally, the development direction of the AUV in complex environment is prospected.
{"title":"Review of Path Planning for Autonomous Underwater Vehicles","authors":"Tingting Yao, Tao He, Wenlong Zhao, Abdou Yahouza M. Sani","doi":"10.1145/3366194.3366280","DOIUrl":"https://doi.org/10.1145/3366194.3366280","url":null,"abstract":"An autonomous underwater vehicle (AUV) is an important tool for the exploration and development of marine resources. Path planning plays an important role in the correct navigation and avoidance of obstacles by underwater robots in the sea. Firstly, according to different marine environmental conditions, AUV path planning is classified into two types. Then, the related algorithms of global path planning and local path planning are reviewed, and the key technologies, development status, advantages and disadvantages of related algorithms are combed. Finally, the development direction of the AUV in complex environment is prospected.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"2010 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123716955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In case of the technical difficulties of the development in manipulator trajectory planning, a solution that builds a manipulator control system based on an open source software platform (Robot Operating System, ROS) is put forward here. The trajectory planning is carried out in the RViz visualization environment with the MotionPlanning plug-in. The trajectory curves of the RRT algorithm and the KPIECE algorithm in different obstacle environments are compared. Finally, during the movement of the Manipulator derived the position of each joint by the ROS tool.
{"title":"Research on Trajectory Planning of ROS-based Manipulator","authors":"H. Tao, Yu Fang, Zhifeng Zhou","doi":"10.1145/3366194.3366260","DOIUrl":"https://doi.org/10.1145/3366194.3366260","url":null,"abstract":"In case of the technical difficulties of the development in manipulator trajectory planning, a solution that builds a manipulator control system based on an open source software platform (Robot Operating System, ROS) is put forward here. The trajectory planning is carried out in the RViz visualization environment with the MotionPlanning plug-in. The trajectory curves of the RRT algorithm and the KPIECE algorithm in different obstacle environments are compared. Finally, during the movement of the Manipulator derived the position of each joint by the ROS tool.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114657794","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}
Power wireless private network has the advantages of high spectrum efficiency, large data throughput and good system stability. However, in practical applications, it may cause large interference to 230 digital transmission stations, which affects the normal operation of the system. Spectrum-sensing technology can be used to capture 230 digital radio signals in the spectrum, so that both systems can work steadily on the same spectrum resources. When it is found that both use the same frequency point at the same time, it is avoided in time to ensure the stable operation of the system. The current communication signal modulation types tend to be diversified and complicated and the signals are more and more dense. Therefore, the perception function of the user is not only to realize the perception of the spectrum signal but also to accurately identify the type of the modulation signal. In view of this, after the cognitive system perceives the presence of authorized user signals in the licensed spectrum, the algorithm proposes a modulation signal recognition technology based on BP neural network, which helps the cognitive radio network of the power wireless private network to better perceive the spectrum environment. Identifying the type of modulation in the spectrum to determine the type of service for the authorized user, thereby facilitating better dynamic use of the spectrum.
{"title":"A Modified User Identification Signal Recognition Algorithm for Power Wireless Private Network","authors":"Yongming Zhu, Y. Zhen, Kexiang Fang","doi":"10.1145/3366194.3366323","DOIUrl":"https://doi.org/10.1145/3366194.3366323","url":null,"abstract":"Power wireless private network has the advantages of high spectrum efficiency, large data throughput and good system stability. However, in practical applications, it may cause large interference to 230 digital transmission stations, which affects the normal operation of the system. Spectrum-sensing technology can be used to capture 230 digital radio signals in the spectrum, so that both systems can work steadily on the same spectrum resources. When it is found that both use the same frequency point at the same time, it is avoided in time to ensure the stable operation of the system. The current communication signal modulation types tend to be diversified and complicated and the signals are more and more dense. Therefore, the perception function of the user is not only to realize the perception of the spectrum signal but also to accurately identify the type of the modulation signal. In view of this, after the cognitive system perceives the presence of authorized user signals in the licensed spectrum, the algorithm proposes a modulation signal recognition technology based on BP neural network, which helps the cognitive radio network of the power wireless private network to better perceive the spectrum environment. Identifying the type of modulation in the spectrum to determine the type of service for the authorized user, thereby facilitating better dynamic use of the spectrum.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116818424","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}
Shisen Lin, Lubin Hang, Xiaobo Huang, H. Yang, Junrong Chen, Ziyu Liu, Lusheng Zhou, B. Zhang, Xiansheng Zhu
Considering the practical engineering problems of large cylindrical vessels which need to be machined, installed and detected, a new design scheme of large combined ring gear track as operating platform is proposed. The composition of multisegment arc ring gears is realized through pin-steel sleeve by means of 'one surface and two pins' locating method and rapidly spring clinching assembly. A novel fast and practical method to construct fixed fulcrums is proposed. Forming arbitrarily adjustable fixed fulcrums on the outer wall of the cylinder based on the Bernoulli's Principle of the vacuum chuck is proposed, and these fulcrums are used as a fixed platform of 2SPS-1PRR parallel mechanism for pose alignment of levelness. The kinematics model of the parallel mechanism is established and the forward and inverse kinematics problems are solved. The experimental results show that the parallel mechanism has an adjustment effect on the levelness of the track platform.
{"title":"Research on Circular Track Platform and Parallel Mechanism for Pose Alignment of Levelness","authors":"Shisen Lin, Lubin Hang, Xiaobo Huang, H. Yang, Junrong Chen, Ziyu Liu, Lusheng Zhou, B. Zhang, Xiansheng Zhu","doi":"10.1145/3366194.3366220","DOIUrl":"https://doi.org/10.1145/3366194.3366220","url":null,"abstract":"Considering the practical engineering problems of large cylindrical vessels which need to be machined, installed and detected, a new design scheme of large combined ring gear track as operating platform is proposed. The composition of multisegment arc ring gears is realized through pin-steel sleeve by means of 'one surface and two pins' locating method and rapidly spring clinching assembly. A novel fast and practical method to construct fixed fulcrums is proposed. Forming arbitrarily adjustable fixed fulcrums on the outer wall of the cylinder based on the Bernoulli's Principle of the vacuum chuck is proposed, and these fulcrums are used as a fixed platform of 2SPS-1PRR parallel mechanism for pose alignment of levelness. The kinematics model of the parallel mechanism is established and the forward and inverse kinematics problems are solved. The experimental results show that the parallel mechanism has an adjustment effect on the levelness of the track platform.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115558483","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}
According to the statistics of the First National Water Census Bulletin in 2013[1], the number of water conservancy projects in China has exceeded 98,000, and 756 are under construction, with a total storage capacity of more than 930 billion cubic meter, ranking first in the world. While these water conservancy projects bring enormous economic and social benefits to China, they are affected by geology, hydrology, meteorology and other factors, and their buildings such as tunnels are prone to various defects. However, the current methods for detecting cracks on the dam surface are still dominated by humans. This process is not only inefficient, costly, but often incomplete. YOLOv2 lacks the capture of small defects, YOLOv3 uses three scale feature maps for prediction, and enhances the detection of small cracks. This paper aims to propose a new application scenario for applying YOLOv3 to crack detection in floodgate dam surface and share its effects.
{"title":"Dam surface crack detection based on deep learning","authors":"Linjing Li, Hua Zhang, Jie Pang, Jishuang Huang","doi":"10.1145/3366194.3366327","DOIUrl":"https://doi.org/10.1145/3366194.3366327","url":null,"abstract":"According to the statistics of the First National Water Census Bulletin in 2013[1], the number of water conservancy projects in China has exceeded 98,000, and 756 are under construction, with a total storage capacity of more than 930 billion cubic meter, ranking first in the world. While these water conservancy projects bring enormous economic and social benefits to China, they are affected by geology, hydrology, meteorology and other factors, and their buildings such as tunnels are prone to various defects. However, the current methods for detecting cracks on the dam surface are still dominated by humans. This process is not only inefficient, costly, but often incomplete. YOLOv2 lacks the capture of small defects, YOLOv3 uses three scale feature maps for prediction, and enhances the detection of small cracks. This paper aims to propose a new application scenario for applying YOLOv3 to crack detection in floodgate dam surface and share its effects.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127998500","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：