相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Review
Engineering, Civil
Yaodong Cui et al.
Summary: The development of autonomous vehicles has been rapid in recent years, yet achieving full autonomy poses challenges due to the complex and dynamic driving environments. The fusion of camera and LiDAR sensors using deep learning is an emerging research theme. Despite the lack of critical reviews on deep-learning-based camera-LiDAR fusion methods, recent research has focused on leveraging image and point cloud data processing for improved environmental perception and object detection.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Jin Xie et al.
Summary: This paper introduces a novel approach termed as PSC-Net for occluded pedestrian detection, which captures co-occurrence information of different pedestrian body parts through a graph convolutional network. The proposed PSC-Net achieves significant performance improvement over MGAN in heavy occlusion scenarios on three challenging datasets.
SCIENCE CHINA-INFORMATION SCIENCES
(2021)
Article
Chemistry, Analytical
Fangyu Li et al.
Summary: The paper introduces a new backbone network that completes the cross-layer fusion of multi-scale bird's eye view feature maps, enhancing the performance of object detection.
Article
Green & Sustainable Science & Technology
Zihao Wen et al.
Summary: This study aimed to identify safety-critical events related to accidents on mountain roads using naturalistic-driving data. Support vector machine (SVM) was found to yield optimal performance, with an identification accuracy of 90.64% and reduced false positive and false negative rates compared to traditional methods. The improved SVM method can accurately and efficiently identify safety-critical events on mountain roads.
Article
Construction & Building Technology
Zhanwen Liu et al.
Summary: Traffic signs detection is crucial for autonomous driving, yet challenges remain due to uneven distribution of training samples and appearance variations of signs. The proposed cascade saccade network in this paper shows promising results in detecting small size traffic signs and meets real-time driving safety application requirements.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Computer Science, Artificial Intelligence
Alireza Taheri Tajar et al.
Summary: The paper presents a lightweight real-time vehicle detection model that can run on common computing devices and has advantages in terms of accuracy and speed. The system is capable of detecting and classifying six different types of vehicles at a speed of 17 fps, with an accuracy of 95.05%, making it about two times faster than the original Tiny-YOLOv3 network.
JOURNAL OF REAL-TIME IMAGE PROCESSING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Lizhe Liu et al.
Summary: This work proposes a novel top-to-down lane detection framework, CondLaneNet, which dynamically predicts lane instances and line shapes, achieving real-time efficiency and excellent detection accuracy.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Article
Computer Science, Information Systems
Agus Mulyanto et al.
Summary: This study evaluated the YOLOv4 model for traffic obstacle detection and proposed a new dataset containing unique obstacles found on Indonesian roads.
JOURNAL OF ICT RESEARCH AND APPLICATIONS
(2021)
Article
Urban Studies
Juan Lu et al.
Summary: This research focuses on the influence mechanism of city-scale expansion on air pollution, indicating that city-scale expansion can directly impact air pollution as well as affect it through traffic mode and congestion. The impact of city-scale expansion on air quality is double-edged, as it can both mitigate and exacerbate air pollution.
Article
Automation & Control Systems
Mahmut Dirik et al.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2020)
Article
Construction & Building Technology
Liyong Wang et al.
ADVANCES IN CIVIL ENGINEERING
(2020)
