Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976821
Qing Li, Hongcheng Huang, Pengzhi Chu
Target detection and distance estimation for autonomous driving have been making remarkable strides in recent years. In autonomous driving, target detection mainly refers to the identification of vehicles, pedestrians, traffic signs, etc. Nowadays, target detection technology has gradually matured, especially with the emergence of Faster R-CNN and YOLO, which has greatly improved the accuracy and efficiency of target detection. Not only to detect objects, we want to know more about spatial and distance information between the vehicle and the objects, however, the complexity of road conditions challenges the ranging methods. When the road is crowded and there are many vehicles, which will block each other, reduces the ranging performance, especially for laser ranging and ultrasonic ranging. In this paper, a monocular visual ranging method based on YOLOv5 is proposed, which is divided into two steps. Stage one detects vehicles and pedestrians, predicts a bounding box for each detected target. The second stage determines the position of the object with the help of the bounding boxes and accurately extracts the feature points, then computes the specific distance base on the geometric relationship. In this paper, we considered various road conditions to improve performance in real-world road scenes and the distance measurement method in this paper is proved to be robust under different road conditions. Since only one camera is required, the equipment cost is greatly reduced. What's more, our model can be combined with lane detection to realize target recognition, object ranging and lane detection at the same time.
{"title":"The research of vehicle monocular ranging based on YOlOv5","authors":"Qing Li, Hongcheng Huang, Pengzhi Chu","doi":"10.1109/IAI55780.2022.9976821","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976821","url":null,"abstract":"Target detection and distance estimation for autonomous driving have been making remarkable strides in recent years. In autonomous driving, target detection mainly refers to the identification of vehicles, pedestrians, traffic signs, etc. Nowadays, target detection technology has gradually matured, especially with the emergence of Faster R-CNN and YOLO, which has greatly improved the accuracy and efficiency of target detection. Not only to detect objects, we want to know more about spatial and distance information between the vehicle and the objects, however, the complexity of road conditions challenges the ranging methods. When the road is crowded and there are many vehicles, which will block each other, reduces the ranging performance, especially for laser ranging and ultrasonic ranging. In this paper, a monocular visual ranging method based on YOLOv5 is proposed, which is divided into two steps. Stage one detects vehicles and pedestrians, predicts a bounding box for each detected target. The second stage determines the position of the object with the help of the bounding boxes and accurately extracts the feature points, then computes the specific distance base on the geometric relationship. In this paper, we considered various road conditions to improve performance in real-world road scenes and the distance measurement method in this paper is proved to be robust under different road conditions. Since only one camera is required, the equipment cost is greatly reduced. What's more, our model can be combined with lane detection to realize target recognition, object ranging and lane detection at the same time.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115055134","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976541
Lingyun Xu, Ying Wan
This paper studies a distributed combined economic environmental dispatch problem (CEEDP) of the smart grid. CEEDP aims to minimize the economic costs and also emissions with supply-demand balance and generation constraints. A distributed reputation-based algorithm is proposed to defend against non-colluding and colluding attacks, integrating attack detection, isolation, and restoration strategy. By dynamically updating the reputation value of each generator, the isolation process can intelligently adjust the communication weights among the generator units to isolate the units that are under attack. Finally, simulation examples are given to verify the effectiveness of the proposed strategy.
{"title":"Distributed Reputation-based Strategy for Economic Environmental Dispatch under Cyber Attacks","authors":"Lingyun Xu, Ying Wan","doi":"10.1109/IAI55780.2022.9976541","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976541","url":null,"abstract":"This paper studies a distributed combined economic environmental dispatch problem (CEEDP) of the smart grid. CEEDP aims to minimize the economic costs and also emissions with supply-demand balance and generation constraints. A distributed reputation-based algorithm is proposed to defend against non-colluding and colluding attacks, integrating attack detection, isolation, and restoration strategy. By dynamically updating the reputation value of each generator, the isolation process can intelligently adjust the communication weights among the generator units to isolate the units that are under attack. Finally, simulation examples are given to verify the effectiveness of the proposed strategy.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129288029","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976806
W. Yumei, Han Mei, Gao Xiuyun
The replacement of old growth drivers with new ones injects a new impetus for economic development, puts forward higher and more comprehensive requirements for talents, and puts forward new standards for enterprise employment and current talent education, which leads to the disconnection between enterprise employment standards and college education mode. Under the background of the replacement of old growth drivers with new ones, this study constructs the talent training evaluation index system, including two aspects: input and output of talent training. The existing input index is usually composed of human input, material input and financial input, while the output index includes teaching output, scientific research output and social service output. Taking China Education Statistics Yearbook (2016–2020) as the data source, Composite DEA method is used to comprehensively evaluate and analyze the talent training system under the background of the replacement of old growth drivers with new ones.
{"title":"Comprehensive Evaluation and Analysis The Talent Training System Using Composite DEA under the Background of the Replacement of Old Growth Drivers with New Ones","authors":"W. Yumei, Han Mei, Gao Xiuyun","doi":"10.1109/IAI55780.2022.9976806","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976806","url":null,"abstract":"The replacement of old growth drivers with new ones injects a new impetus for economic development, puts forward higher and more comprehensive requirements for talents, and puts forward new standards for enterprise employment and current talent education, which leads to the disconnection between enterprise employment standards and college education mode. Under the background of the replacement of old growth drivers with new ones, this study constructs the talent training evaluation index system, including two aspects: input and output of talent training. The existing input index is usually composed of human input, material input and financial input, while the output index includes teaching output, scientific research output and social service output. Taking China Education Statistics Yearbook (2016–2020) as the data source, Composite DEA method is used to comprehensively evaluate and analyze the talent training system under the background of the replacement of old growth drivers with new ones.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126219984","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976793
Runda Jia, Shulei Zhang, Zhiqi Li, Kang Li
In this work, a data-driven tube-based model predictive control (MPC) is presented to track the setpoints of the underflow concentration. By defining the terminal admissible set to consider all the possible steady-states, the controller can ensure tracking for all reachable operating setpoints. Besides, a data-driven general polyhedral uncertainty set is constructed by employing the principal component analysis (PCA) technique, which can effectively capture correlations among uncertain variables. Based on the constructed uncertainty set, the feasible region could be enlarged while reducing the conservatism of control performance. In addition, recursive feasibility and stability of the controller can be guaranteed. The effectiveness of the proposed method is verified by tracking problems of the thickening process.
{"title":"Data-Driven Tube-based Model Predictive Control of an Industrial Thickener","authors":"Runda Jia, Shulei Zhang, Zhiqi Li, Kang Li","doi":"10.1109/IAI55780.2022.9976793","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976793","url":null,"abstract":"In this work, a data-driven tube-based model predictive control (MPC) is presented to track the setpoints of the underflow concentration. By defining the terminal admissible set to consider all the possible steady-states, the controller can ensure tracking for all reachable operating setpoints. Besides, a data-driven general polyhedral uncertainty set is constructed by employing the principal component analysis (PCA) technique, which can effectively capture correlations among uncertain variables. Based on the constructed uncertainty set, the feasible region could be enlarged while reducing the conservatism of control performance. In addition, recursive feasibility and stability of the controller can be guaranteed. The effectiveness of the proposed method is verified by tracking problems of the thickening process.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130155178","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976874
Hai Yang, Hong Zhu, Yefeng Liu, Yuan Zhao
Aiming at the characteristic of frequency density of non-stationary random vibration signals of industrial robots during machining, a multi-component process neural network (PNN) auto-regressive model was proposed based on empirical mode decomposition (EMD). First, the original time series were decomposed into intrinsic mode functions (IMF) of different scales by EMD. Then, the time-varying parameters of each IMF were analyzed by PNN and the time-varying power spectral density was determined. Finally, the time-varying independent power spectral density of all components is reconstructed by linear superposition as the time-varying independent power spectral density of the original signal. The calculation results show that the frequency resolution performance of this method is better than that of traditional analysis method.
{"title":"Analysis of non-stationary random vibration environment of industrial robot based on EMD and PNN","authors":"Hai Yang, Hong Zhu, Yefeng Liu, Yuan Zhao","doi":"10.1109/IAI55780.2022.9976874","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976874","url":null,"abstract":"Aiming at the characteristic of frequency density of non-stationary random vibration signals of industrial robots during machining, a multi-component process neural network (PNN) auto-regressive model was proposed based on empirical mode decomposition (EMD). First, the original time series were decomposed into intrinsic mode functions (IMF) of different scales by EMD. Then, the time-varying parameters of each IMF were analyzed by PNN and the time-varying power spectral density was determined. Finally, the time-varying independent power spectral density of all components is reconstructed by linear superposition as the time-varying independent power spectral density of the original signal. The calculation results show that the frequency resolution performance of this method is better than that of traditional analysis method.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127810059","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976560
Changshuai Yu, Yung‐Peng Zhu, Haitao Luo, Zhong Luo
Damage detection of the spacecraft equipment is required in vibration test to avoid the costly spacecraft equipment worsening of damage. The current method is to compare the change of the natural frequencies, which may be failure because linear feature is usually not sensitive to some damage. The objective of this study is to develop a novel structural damage detection method of spacecraft equipment to address the current method problem. To achieve this goal, use regularization FROLS (Forward Regression Orthogonal Least Squares) algorithm to identify the NARX (Nonlinear Autoregressive with Exogenous Input) model of the spacecraft equipment. After that, use the theory of NOFRF (Nonlinear Output Frequency Response Function) under harmonic input to obtain the NOFRFs, which can be used to detect the damage of spacecraft equipment in vibration test. Finally, an experimental study is carried out to conduct damage detection for a cantilever plate structure to demonstrate the effectiveness of the proposed method in engineering.
{"title":"Structural Damage Detection of Spacecraft Equipment Based on Data Driven Modelling and Nonlinear Output Frequency Response Function","authors":"Changshuai Yu, Yung‐Peng Zhu, Haitao Luo, Zhong Luo","doi":"10.1109/IAI55780.2022.9976560","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976560","url":null,"abstract":"Damage detection of the spacecraft equipment is required in vibration test to avoid the costly spacecraft equipment worsening of damage. The current method is to compare the change of the natural frequencies, which may be failure because linear feature is usually not sensitive to some damage. The objective of this study is to develop a novel structural damage detection method of spacecraft equipment to address the current method problem. To achieve this goal, use regularization FROLS (Forward Regression Orthogonal Least Squares) algorithm to identify the NARX (Nonlinear Autoregressive with Exogenous Input) model of the spacecraft equipment. After that, use the theory of NOFRF (Nonlinear Output Frequency Response Function) under harmonic input to obtain the NOFRFs, which can be used to detect the damage of spacecraft equipment in vibration test. Finally, an experimental study is carried out to conduct damage detection for a cantilever plate structure to demonstrate the effectiveness of the proposed method in engineering.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130329137","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976682
Xinju Wang, Xiaoming Wang
Low-frequency oscillation (LFO) phenomenon of traction network often occurs in vehicle-grid coupling systems (VGCS), which may lead to traction blockade of the electric multiple units (EMUs). To improve the control of traction dual rectifiers (TDR) and suppress LFO, an auto-disturbance rejection control-based model predictive direct power control (ADRC-MPDPC) approach is developed. First, a voltage correction based on Newton interpolation is carried out to eliminate the error caused by the sampling process of the line-side voltage sensor. Besides, to improve the dynamic performance and robustness of the MPDPC, a voltage outer-loop control strategy based on first-order ADRC is designed. Finally, a simulation model of VGCS is constructed to test the control performance and the effectiveness of the proposed algorithm. The experimental results show that the proposed control can not only improve LFO of the dc-link voltage but also effectively alleviate the harmonic distortion of the current and suppress the power pulsation of MPDPC in the TDR.
{"title":"An ADRC-based Model Predictive Direct Power Control to Alleviate Low-Frequency Oscillations of Traction Dual Rectifiers","authors":"Xinju Wang, Xiaoming Wang","doi":"10.1109/IAI55780.2022.9976682","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976682","url":null,"abstract":"Low-frequency oscillation (LFO) phenomenon of traction network often occurs in vehicle-grid coupling systems (VGCS), which may lead to traction blockade of the electric multiple units (EMUs). To improve the control of traction dual rectifiers (TDR) and suppress LFO, an auto-disturbance rejection control-based model predictive direct power control (ADRC-MPDPC) approach is developed. First, a voltage correction based on Newton interpolation is carried out to eliminate the error caused by the sampling process of the line-side voltage sensor. Besides, to improve the dynamic performance and robustness of the MPDPC, a voltage outer-loop control strategy based on first-order ADRC is designed. Finally, a simulation model of VGCS is constructed to test the control performance and the effectiveness of the proposed algorithm. The experimental results show that the proposed control can not only improve LFO of the dc-link voltage but also effectively alleviate the harmonic distortion of the current and suppress the power pulsation of MPDPC in the TDR.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133199271","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976693
Shuo Wang, Shengping Yu, Haikuan Wang, Dakui Wu, Wenju Zhou, H. Luo
Correct assembly behavior in industrial production is a direct means to ensure production quality and efficiency. Aiming at the problems of worker misoperation or lack of important assembly steps in the production and assembly process, a human behavior recognition method based on ToF camera is proposed. The method segments the extracted depth motion maps (DMMs) according to the differences between frames, and extracts histogram of oriented gradient (HOG) descriptors and multiscale grayscale count (MGC) descriptors as local features. Then a hierarchical DMMs multi-classifier recognition framework is built based on stacking strategy, combining support vector machine (SVM), K-nearest neighbor (KNN), random forest (RF) and XGBoost classifiers, achieving 98.2% accuracy on MSR ACTION 3D dataset and 87.1% accuracy on self-built dataset, respectively.
{"title":"Research and Design of Human Behavior Recognition Method in Industrial Production Based on Depth Image","authors":"Shuo Wang, Shengping Yu, Haikuan Wang, Dakui Wu, Wenju Zhou, H. Luo","doi":"10.1109/IAI55780.2022.9976693","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976693","url":null,"abstract":"Correct assembly behavior in industrial production is a direct means to ensure production quality and efficiency. Aiming at the problems of worker misoperation or lack of important assembly steps in the production and assembly process, a human behavior recognition method based on ToF camera is proposed. The method segments the extracted depth motion maps (DMMs) according to the differences between frames, and extracts histogram of oriented gradient (HOG) descriptors and multiscale grayscale count (MGC) descriptors as local features. Then a hierarchical DMMs multi-classifier recognition framework is built based on stacking strategy, combining support vector machine (SVM), K-nearest neighbor (KNN), random forest (RF) and XGBoost classifiers, achieving 98.2% accuracy on MSR ACTION 3D dataset and 87.1% accuracy on self-built dataset, respectively.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133672189","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976865
Xinghua Liu, Hanjun Xue, Xiang Gao, Jianwei Guan
Event cameras are silicon retina sensors that are more advantageous than traditional cameras in low-latency tracking and high dynamic range scenes. In this paper, we present a visual odometry algorithm based on the Dynamic and Active-pixel Vision Sensor (DAVIS), and the 6 Degree-of-Freedom (6-DoF) object motion can be tracked by the proposed algorithm. We detect features and track motion on the image plane, then feature-based pose estimation and extended Kalman filter (EKF) framework are tightly intertwined in event-based visual odometry. In experiments, the accuracy of our approach is evaluated in several object tracking scenarios. The trajectory of a low-latency and high-rate tracking is obtained, and the utilization rate of CPU resources is improved by using an event-driven strategy.
{"title":"Frame-based Feature Tracking and EKF Framework for Event Cameras","authors":"Xinghua Liu, Hanjun Xue, Xiang Gao, Jianwei Guan","doi":"10.1109/IAI55780.2022.9976865","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976865","url":null,"abstract":"Event cameras are silicon retina sensors that are more advantageous than traditional cameras in low-latency tracking and high dynamic range scenes. In this paper, we present a visual odometry algorithm based on the Dynamic and Active-pixel Vision Sensor (DAVIS), and the 6 Degree-of-Freedom (6-DoF) object motion can be tracked by the proposed algorithm. We detect features and track motion on the image plane, then feature-based pose estimation and extended Kalman filter (EKF) framework are tightly intertwined in event-based visual odometry. In experiments, the accuracy of our approach is evaluated in several object tracking scenarios. The trajectory of a low-latency and high-rate tracking is obtained, and the utilization rate of CPU resources is improved by using an event-driven strategy.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130637631","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976787
Yang Liu, Qiansheng Li, Yanchen Jiang, Yongfu Wang
This paper performs lane line angle detection in autonomous driving scenarios based on an end-to-end learning mechanism. Lane line angle detection is a vital technology research development direction in Autonomous Vehicles. However, since most lane line targets in remote sensing images have sparse features, it is still challenging to achieve accurate lane line angle detection in traffic status images in front of vehicles. A lane line angle detection algorithm based on the improved C3 module YOLOV5n algorithm is proposed, which mainly includes: a self-made lane curvature dataset; improvement of the loss function; improvement of the C3 module to improve the detection accuracy of the network. Experiments are conducted using the traffic status images in front of vehicles in the lane curvature dataset, and the results show that the algorithm achieves better detection results in lane curvature detection.
{"title":"Light Model based on End-to-End for Steering Angle Detection","authors":"Yang Liu, Qiansheng Li, Yanchen Jiang, Yongfu Wang","doi":"10.1109/IAI55780.2022.9976787","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976787","url":null,"abstract":"This paper performs lane line angle detection in autonomous driving scenarios based on an end-to-end learning mechanism. Lane line angle detection is a vital technology research development direction in Autonomous Vehicles. However, since most lane line targets in remote sensing images have sparse features, it is still challenging to achieve accurate lane line angle detection in traffic status images in front of vehicles. A lane line angle detection algorithm based on the improved C3 module YOLOV5n algorithm is proposed, which mainly includes: a self-made lane curvature dataset; improvement of the loss function; improvement of the C3 module to improve the detection accuracy of the network. Experiments are conducted using the traffic status images in front of vehicles in the lane curvature dataset, and the results show that the algorithm achieves better detection results in lane curvature detection.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133013100","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：