2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE)最新文献_第2页

Optical Flow-Guided Deep Convolutional Neural Networks for UAV Detection in Infrared Videos 红外视频中无人机检测的光流引导深度卷积神经网络

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101427

Xin Yang, Yi-Zheng Wang, G. Wang

{"title":"Optical Flow-Guided Deep Convolutional Neural Networks for UAV Detection in Infrared Videos","authors":"Xin Yang, Yi-Zheng Wang, G. Wang","doi":"10.1109/ICITE56321.2022.10101427","DOIUrl":"https://doi.org/10.1109/ICITE56321.2022.10101427","url":null,"abstract":"Early warning of small civilian UAVs is a critical issue in the field of public security and is a challenging task in object detection. Video object detection methods based on deep convolution neural networks have attracted increasing attention over recent years. The object detection algorithm designed for static images can hardly be used directly in video object detection, due to motion blur, out-of-focus, etc. Traditional methods mainly apply temporal information to address this problem. In this paper, we proposed a method based on optical flow for UAV video object detection, employing optical flow information and the object appearance visual features in different stages. We establish a motion enhancement module to utilize motion features of moving objects while suppressing complex backgrounds. In addition, direction information is used to associate detection boxes of adjacent frames, improving the stability of the detection. The results of the experiments on the Anti-UAV2021 Challenge dataset show that the average precision of our model is 89.8%, significantly higher than that of FGFA, SELSA, and YOLOv5 models. The experimental results also demonstrate that the motion enhancement module and direction post-processing module can improve the recall rate of small UAVs under complex backgrounds.","PeriodicalId":160149,"journal":{"name":"2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133139830","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}

引用次数: 0

Method of Extracting Airport Curbside Vehicle Operation Data Based on Point Cloud Data 基于点云数据的机场路边车辆运行数据提取方法

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101422

Chenjing Zhou, X. Cui, Xiafei Song, Xin-rui Nie, Yacong Gao

{"title":"Method of Extracting Airport Curbside Vehicle Operation Data Based on Point Cloud Data","authors":"Chenjing Zhou, X. Cui, Xiafei Song, Xin-rui Nie, Yacong Gao","doi":"10.1109/ICITE56321.2022.10101422","DOIUrl":"https://doi.org/10.1109/ICITE56321.2022.10101422","url":null,"abstract":"The aviation hub curbside is the interface between airside and landside transportation systems. Microscopic traffic simulation technology is the most common method to analyze the characteristics of curbside operation. For scientific use of microscopic traffic simulation tools, the operation characteristics of simulation objects should be mastered in detail. In this paper, airport curbside operation characteristic parameter detection method based on radar equipment is proposed. The method is divided into four steps, background point segmentation, trajectory point extraction, trajectory tracking, and traffic information extraction. Firstly, a coordinate system correction is performed by Random Sample Consensus (RANSAC) algorithm. Secondly, the data are clustered and the trajectory points of the vehicle are obtained by Density-Based Spatial Clustering of Application with Noise-Oriented bounding box (DBSCAN-OBB) algorithm, and the trajectory points generated by the same vehicle are tracked to obtain the original vehicle trajectory chain. And remove the outliers in the data sequence and optimize the original trajectory chain by combining median filtering and Kalman filtering. Finally, the vehicle running speed and acceleration parameters are extracted from the trajectory data. In this study, the proposed method was used to obtain a set of curbside parameters for researchers to use, which include the layout of the facilities along the curbside and the operation characteristics data of vehicles and pedestrians.","PeriodicalId":160149,"journal":{"name":"2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134614907","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}

引用次数: 0

CLSD: Continual Learning for Lane Line Segmentation Across Domains CLSD:跨域车道线分割的持续学习

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101413

Y. Wu, Yujun Liao, Wei Jiang, Junqiao Zhao, Feilin Liu, Y. Mo

{"title":"CLSD: Continual Learning for Lane Line Segmentation Across Domains","authors":"Y. Wu, Yujun Liao, Wei Jiang, Junqiao Zhao, Feilin Liu, Y. Mo","doi":"10.1109/ICITE56321.2022.10101413","DOIUrl":"https://doi.org/10.1109/ICITE56321.2022.10101413","url":null,"abstract":"Lane line segmentation is a fundamental task in the field of autonomous driving, and it’s intuitive that automatic vehicles should have the ability of processing data from different domains. The usual assumption is that training data of all the domains is available at a time, however, it’s more common to collect data continually and train the visual system incrementally. To date, many works focus on segmenting lane line in a single domain, but no work considers continually segmenting lane line across domains. To tackle with this task, we presents a method, named as CLSD1 which leverages data from new domain while avoiding catastrophic forgetting. The core of CLSD are a training framework that effectively transfer knowledge from the previous model to the new model and a frustrating simple yet useful self-training strategy. We conduct extensive experiments based on TSD datasets and showcase that on daytime our training framework increases the miou by 10% on the fog domain data, and the self-straining increases the miou by 11% on the fog domain data and 47% in night domain data.1Continual Learning for Lane Line Segmentation Across Domains","PeriodicalId":160149,"journal":{"name":"2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116440375","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}

引用次数: 0

An Edge Computing-Based Paltform of Railway Signalling System On-site Digital Smart Test 基于边缘计算的铁路信号系统现场数字智能测试平台

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101475

Ping Gao, Mingxi Zhao, Shengmao Xie, Kui Qiu, Tengfei Wang, Zhiping Yang

{"title":"An Edge Computing-Based Paltform of Railway Signalling System On-site Digital Smart Test","authors":"Ping Gao, Mingxi Zhao, Shengmao Xie, Kui Qiu, Tengfei Wang, Zhiping Yang","doi":"10.1109/ICITE56321.2022.10101475","DOIUrl":"https://doi.org/10.1109/ICITE56321.2022.10101475","url":null,"abstract":"The railway and urban rail signalling system is a safety-related system with extremely high safety integrity level requirements. The completeness and correctness of the on-site test after installation are indispensable for the guarantee of the safety function of the signalling system. At current the signalling system site test and the post installation check all been done by the site test engineers manually, which may not well recorded digital evidence, and the efficiency is low. Somehow even if the test engineer is not competent and they are not performing the test rightly or even they are not performing the site test but only directly marked in the test record. The paper shows an edge computing-based platform which can perform the railway signalling system on-site test which can perform the on-site test and record the site results and logs automatically. All the on-site test and test records can restore and show for the safety assessment and quality assessment to make sure the safety integrity of the railway signalling system is fulfilled the requirement.","PeriodicalId":160149,"journal":{"name":"2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131071260","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}

引用次数: 1

Temporary Parking Reservation for Trucks in Urban Commercial Districts Based on Improved Greedy Algorithm 基于改进贪婪算法的城市商业区货车临时停车预约

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101415

Yi Wang, Xiang Wang, Yuyao Zan, Ronghuan Gao, Lingyi Miao

{"title":"Temporary Parking Reservation for Trucks in Urban Commercial Districts Based on Improved Greedy Algorithm","authors":"Yi Wang, Xiang Wang, Yuyao Zan, Ronghuan Gao, Lingyi Miao","doi":"10.1109/ICITE56321.2022.10101415","DOIUrl":"https://doi.org/10.1109/ICITE56321.2022.10101415","url":null,"abstract":"Urban commercial districts rely heavily on trucks for transportation of goods. The parking demand generated by trucks loading and unloading goods is high. Insufficient temporary parking spaces can cause trucks to park randomly while loading and unloading goods. This situation is susceptible to a variety of traffic problems, such as road congestion and occupied pedestrian paths. This study uses automatic vehicle identification (AVI) data to realize the perception of truck parking behavior in commercial districts. A time-sharing reservation method for truck parking in commercial districts based on improved greedy algorithm is proposed according to characteristics of concentrated truck parking demand and short parking duration. Parking space turnover rate improves by adjusting the time point of truck start parking within an acceptable time threshold. An urban commercial district is chosen for validation. Results showed that the total number of trucks in the district is 1,200 per day on weekdays and 1,000 per day on weekends. Heavy and light trucks are dominant and account for about 40% of the total number respectively, while medium-sized trucks account for 20%. Peak hour of truck parking is around 15:00 and the maximum volume can reach 102 vehicles/hour. The average parking time is 31 mins. Taking a weekday as example, 46 temporary parking spaces were needed before optimization, and it was reduced to 20 after optimization, saving 56% of the total temporary parking spaces. This study can effectively enhance the turnover rate of truck parking and save temporary parking space in urban commercial districts.","PeriodicalId":160149,"journal":{"name":"2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130206010","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}

引用次数: 0

A Method to Elicit User Needs of MaaS Based on Activity Theory 基于活动理论的MaaS用户需求提取方法

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101462

Lai Zheng, Wenfan Xu, Wei Wei

引用次数: 0

Traffic Violation Detection via Depth and Gradient Angle Change 基于深度和梯度角度变化的交通违章检测

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101435

Yan-Tsung Peng, Chen-Yu Liu, He-Hao Liao, Wei-Cheng Lien, G. Hsu

引用次数: 0

An Effective Practical Approach for LDM in China’s Cooperative Intelligent Transportation System 中国协同智能交通系统中LDM的有效实践方法

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101434

Changlong Zhang, Jimin Wei, P. Fu, Jingang Dai, Xianning She, Shibo Qu

引用次数: 0

Research on Traffic Behavior in the Presence of Lane Merging Using Traffic Simulation 基于交通仿真的车道合并交通行为研究

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101384

Yuchu Liu

引用次数: 0

Research on Cyberattack Detection of Connected Automated Vehicles Based on Support Vector Machine 基于支持向量机的网联自动驾驶汽车网络攻击检测研究

2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE) Pub Date : 2022-11-11 DOI: 10.1109/ICITE56321.2022.10101470

Runzhe Liu, Xin Peng, Zhanbo Sun, Zhihang Huang, Hai Hu

{"title":"Research on Cyberattack Detection of Connected Automated Vehicles Based on Support Vector Machine","authors":"Runzhe Liu, Xin Peng, Zhanbo Sun, Zhihang Huang, Hai Hu","doi":"10.1109/ICITE56321.2022.10101470","DOIUrl":"https://doi.org/10.1109/ICITE56321.2022.10101470","url":null,"abstract":"Connected automated vehicles (CAVs) are facing the threat of cyberattacks while exchanging state information. Most of the existing research focuses on the communication technologies and the network security technologies, with the purpose of providing corresponding preventive solutions for the specific technical means of attack behavior, which are highly targeted but weak in universality of application. In this paper, a type of adversary model based on attack effects, namely, disturbance attack, was established. A numerical simulation platform for CAVs cyberattack experiment was built to quantitatively analyze the impacts of CAVs cyberattacks on traffic. 9 measurement indicators were constructed based on traffic safety indicators and traffic flow parameters for the characteristic impacts of various attacks. Using the cyberattack experiment simulation platform to generate attack feature datasets, A cyberattack detection model of CAVs on the basis of nonlinear Support Vector Machine was established. The model showed a sound classification performance, with a detection rate of more than 95% within 3s of the attack. The research method in this paper has a universal reference value for cyberattacks detection of CAVs. The results help better understand the effects of CAV-related cyberattacks and shed light on proactive defense against such attacks.","PeriodicalId":160149,"journal":{"name":"2022 IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125171593","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}

引用次数: 0