Chang Liu

Chang Liu


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 October 2025 in Sensors
Verified
Journal Article
Open access
PDF file
XFXiaofan Feng
Xiaofan Feng
LPLu Peng
Lu Peng
YTYu Tang
Yu Tang
CLChang Liu
Chang Liu
HAHuazhen An
Huazhen An
With the strict requirements of national policies on truck dimensions, axle loads, and weight limits, along with the implementation of tolls based on vehicle types, rapid and accurate identification of vehicle axle types has become essential for toll station management. To address the limitations of existing methods in distinguishing between drive and driven axles, complex equipment setup, and image evidence retention, this article proposes a panoramic image detection technology for vehicle chassis based on enhanced ORB and YOLOv11. A portable vehicle chassis image acquisition system, based on area array cameras, was developed for rapid on-site deployment within 20 min, eliminating the requirement for embedded installation. The FeatureBooster (FB) module was employed to optimize the ORB algorithm’s feature matching, and combined with keyframe technology to achieve high-quality panoramic image stitching. After fine-tuning the FB model on a domain-specific area scan dataset, the number of feature matches increased to 151 ± 18, substantially outperforming both the pre-trained FB model and the baseline ORB. Experimental results on axle type recognition using the YOLOv11 algorithm combined with ORB and FB features demonstrated that the integrated approach achieved superior performance. On the overall test set, the model attained an mAP@50 of 0.989 and an mAP@50:95 of 0.780, along with a precision (P) of 0.98 and a recall (R) of 0.99. In nighttime scenarios, it maintained an mAP@50 of 0.977 and an mAP@50:95 of 0.743, with precision and recall both consistently at 0.98 and 0.99, respectively. The field verification shows that the real-time and accuracy of the system can provide technical support for the axle type recognition of toll stations.

1 March 2024 in Journal of Highway and Transportation Research and Development (English Edition)
Verified
Journal Article
Open access
PDF file
CLChang Liu
Chang Liu
HXHongwen Xia
Hongwen Xia
XMXingkai Meng
Xingkai Meng
XWXueran Wang
Xueran Wang
WLWenhui Luo
Wenhui Luo
CWChuna Wu
Chuna Wu
Long-distance passenger lines exceeding 800 kilometers are a crucial component of highway passenger transport. This paper analyzes the causes of traffic accidents on long-distance passenger routes exceeding 800 kilometers from 2014 to 2020. This paper conducts a causal analysis and researches accident-prone scenarios for long-distance passenger lines exceeding 800 km. It selects key characteristics to establish an index system based on human factors, road conditions, and the environment. This paper analyzes the characteristics of humans, roads, and the environment in the traffic system when accidents occur. The Decision Tree model is utilized to investigate the internal relationships among key factors in accident scenarios, such as operating time, human factors, weather, quarter, accident region, holidays, spring transportation, road alignment, and road condition. The results show that the run time, human factors, and weather conditions are important influencing factors for accidents on long-distance passenger lines over 800 km. They have a coupling relationship with factors such as quarter, accident region, road alignment, and road condition. Holidays, spring transportation, highway technical grade, and highway administrative grade are not the important factors affecting the occurrence of accidents on long-distance passenger lines over 800 km. This paper provides a theoretical basis for reducing the potential for accidents and promoting safety within enterprises operating long-distance passenger lines over 800 km. In the future, road transport management departments and road transport enterprises should strengthen safety management, standardize drivers' safe driving behavior, and promote defensive driving knowledge in accident-prone situations.

10 April 2024 in E3S Web of Conferences
Verified
Conference Paper
Open access
PDF file
CLChang Liu
Chang Liu
MXMeng Xingkai
Meng Xingkai
WCWu Chuna
Wu Chuna
WXWang Xueran
Wang Xueran
ZMZhang Mo
Zhang Mo
ZYZhu Yanhong
Zhu Yanhong
Traffic accidents are closely related to the level of drivers’ safe driving skills. Many countries will add the evaluation of drivers’ safe driving quality to the evaluation of driving suitability. Safe driving quality refers to the driver’s own ideological quality, psychological quality and innate physiological quality which have an important impact on the safety of driving work. Including: awareness of compliance with traffic laws and regulations, strong sense of safety responsibility, agility in responding to sudden dangerous situations, whether the ability to judge road conditions is keen, character, personality, emotion, emotion, ability, attention, willpower, self-control, road rage, road rage, etc. At present, many countries in the world will test the safe driving level of drivers. Therefore, this paper combs the safe driving detection technology and methods of typical countries to explore the effective means and methods of safe driving and ensure traffic safety from the source.