Jingtao Zhong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jingtao Zhong has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Baoshan Huang
Univ. of Tennessee
11 shared publications Yuetan Ma
7 shared publications- Guantao Cheng
Graduate Research Assistant, Dept. of Civil and Environmental Engineering, Univ. of Tennessee, Knoxville, TN 37996. ORCID:
5 shared publications Rui Xiao
4 shared publicationsMiaomiao Zhang
3 shared publications- Rui Xiao
Institute for Carbon Management (ICM), University of California, Los Angeles, USA
3 shared publications
Latest Publications
- 1 September 2026
- Published by Elsevier in Construction and Building Materials
- Vol. 542
Benchmarking tennessee surface asphalt mixtures using superpave- and Marshall-compatible tests for balanced mix design
- 1 September 2026
- Published by Elsevier in Construction and Building Materials
- Vol. 542
Benchmarking tennessee surface asphalt mixtures using superpave- and Marshall-compatible tests for balanced mix design
- Open Access
- 25 November 2025
- Published by MDPI AG in Electronics
- Vol. 14 (23) , 4620
A Novel Anti-UAV Detection Method for Airport Safety Based on Style Transfer Learning and Deep Learning
Unmanned aerial vehicle (UAV) intrusions cause flight delays and disrupt airport operations, so accurate monitoring is essential for safety. To address the scarcity and mismatch of real-world training data in small-target detection, an anti-UAV approach is proposed that integrates style transfer learning (STL) with deep learning. An airport monitoring platform is established to acquire a real UAV dataset, and a Cycle-Consistent Generative Adversarial Network (CycleGAN) is employed to synthesize multi-scene images that simulate diverse airport backgrounds, thereby enriching the training distribution. Using these simulated scenes, a controlled comparison of YOLOv5/YOLOv6/YOLOv7/YOLOv8 is conducted, in which YOLOv5 achieves the best predictive performance with AP values of 93.95%, 98.09%, and 97.07% across three scenarios. On public UAV datasets, the STL-enhanced model (YOLOv5_STL) is further compared with other small-object detectors and consistently exhibits superior performance, indicating strong cross-scene generalization. Overall, the proposed method provides an economical, real-time solution for airport UAV intrusion prevention while maintaining high accuracy and robustness.
- 25 November 2025
- Published by MDPI AG in Electronics
- Vol. 14 (23) , 4620
Open AccessA Novel Anti-UAV Detection Method for Airport Safety Based on Style Transfer Learning and Deep Learning
Unmanned aerial vehicle (UAV) intrusions cause flight delays and disrupt airport operations, so accurate monitoring is essential for safety. To address the scarcity and mismatch of real-world training data in small-target detection, an anti-UAV approach is proposed that integrates style transfer learning (STL) with deep learning. An airport monitoring platform is established to acquire a real UAV dataset, and a Cycle-Consistent Generative Adversarial Network (CycleGAN) is employed to synthesize multi-scene images that simulate diverse airport backgrounds, thereby enriching the training distribution. Using these simulated scenes, a controlled comparison of YOLOv5/YOLOv6/YOLOv7/YOLOv8 is conducted, in which YOLOv5 achieves the best predictive performance with AP values of 93.95%, 98.09%, and 97.07% across three scenarios. On public UAV datasets, the STL-enhanced model (YOLOv5_STL) is further compared with other small-object detectors and consistently exhibits superior performance, indicating strong cross-scene generalization. Overall, the proposed method provides an economical, real-time solution for airport UAV intrusion prevention while maintaining high accuracy and robustness.
- 29 September 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (2) , 680-695
Traffic Input for Mechanistic-Empirical Pavement Design in Tennessee
Truck traffic is an important input for pavement design and analysis. Proper characterization of traffic patterns contributes to the design of reliable and cost-effective pavement structures. In this study, data from nine weigh-in-motion (WIM) sites in the Long-Term Pavement Performance database were utilized to develop the regional traffic input (level 2) for the implementation of mechanistic-empirical pavement design in Tennessee, U.S. Hierarchical clustering was performed to characterize the traffic patterns among the analyzed WIM sites, followed by the sensitivity analysis to evaluate the impact of generated traffic inputs. Three levels of traffic inputs—level 1 (site-specific), level 2 (statewide average and specific cluster-based), and level 3 (nationwide default)—were compared on both new pavement and pavement overlay design for typical pavement structures in Tennessee. Results demonstrate that the cluster-based level 2 provides the closest performance predictions compared with that from the site-specific level 1 data. Specifically, for new flexible pavements across eight WIM sites, the root mean square errors (RMSEs) achieved using level 2 data for fatigue cracking, asphalt concrete (AC) rutting, and International Roughness Index (IRI) are 0.491%, 0.023in., and 2.452 in./mi, respectively. For pavement overlays at nine WIM sites, the RMSEs for fatigue cracking, AC rutting, and IRI are 0.011%, 0.027 in., and 1.5 in./mi, respectively. It is recommended to adopt the cluster-based traffic input for pavement design when site-specific level 1 data is unavailable.
- 29 September 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (2) , 680-695
Traffic Input for Mechanistic-Empirical Pavement Design in Tennessee
Truck traffic is an important input for pavement design and analysis. Proper characterization of traffic patterns contributes to the design of reliable and cost-effective pavement structures. In this study, data from nine weigh-in-motion (WIM) sites in the Long-Term Pavement Performance database were utilized to develop the regional traffic input (level 2) for the implementation of mechanistic-empirical pavement design in Tennessee, U.S. Hierarchical clustering was performed to characterize the traffic patterns among the analyzed WIM sites, followed by the sensitivity analysis to evaluate the impact of generated traffic inputs. Three levels of traffic inputs—level 1 (site-specific), level 2 (statewide average and specific cluster-based), and level 3 (nationwide default)—were compared on both new pavement and pavement overlay design for typical pavement structures in Tennessee. Results demonstrate that the cluster-based level 2 provides the closest performance predictions compared with that from the site-specific level 1 data. Specifically, for new flexible pavements across eight WIM sites, the root mean square errors (RMSEs) achieved using level 2 data for fatigue cracking, asphalt concrete (AC) rutting, and International Roughness Index (IRI) are 0.491%, 0.023in., and 2.452 in./mi, respectively. For pavement overlays at nine WIM sites, the RMSEs for fatigue cracking, AC rutting, and IRI are 0.011%, 0.027 in., and 1.5 in./mi, respectively. It is recommended to adopt the cluster-based traffic input for pavement design when site-specific level 1 data is unavailable.
- 26 June 2025
- Published by Elsevier in Measurement
- Vol. 256
Texture-image coupled fusion analysis for pavement skid resistance measurement
- 26 June 2025
- Published by Elsevier in Measurement
- Vol. 256
Texture-image coupled fusion analysis for pavement skid resistance measurement
- 27 February 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2679 (5) , 291-301
Compatibilization Strategy and Mechanism for Co-stabilizing Commingled Plastics and Pyrolyzed Rubber in Asphalt
Hot mix asphalt mixture is considered the ideal approach to reuse waste plastics in high-value applications because of its very high amount of usage in highway construction. However, the differences in polarity and density between polymers and asphalt lead to polymer coalescence and therefore the poor storage stability of modified asphalt. These challenges are exalted when recycling commingled plastics. This study introduced an innovative compatibilization strategy and mechanism for co-stabilizing commingled plastics and pyrolyzed rubber in asphalt. Commingled plastics were first grafted with maleic anhydride for surface activation, followed by reactive kneading with pyrolyzed rubber and crosslinking agent to form an integrated thermoplastic elastomer (ITPE) for asphalt modification. The mechanical, thermal, and interfacial behaviors of the ITPE were evaluated through tensile testing, thermogravimetric analysis, and scanning electron microscopy. The storage stability and rheological properties of the modified binder blends were evaluated through the cigar tube test and dynamic shear rheometer testing. Results demonstrated a successful formation of imide bonds in the ITPE, which can improve the strength, ductility, and thermal stability of rubber–plastic composites. Appropriate utilization of crosslinking agents can improve both rutting and fatigue resistance of ITPE-modified asphalt with good storage stability because of the co-existence of rigid plastic and soft rubbery regimes and the formation of a crosslink network. However, excessive content of crosslinker led to severe phase separation and reduced storage stability of modified binder blends. Extra crosslinker tended to float in asphalt because of its low density and caused an excessive formation of the crosslink network in the top section of the asphalt.
- 27 February 2025
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2679 (5) , 291-301
Compatibilization Strategy and Mechanism for Co-stabilizing Commingled Plastics and Pyrolyzed Rubber in Asphalt
Hot mix asphalt mixture is considered the ideal approach to reuse waste plastics in high-value applications because of its very high amount of usage in highway construction. However, the differences in polarity and density between polymers and asphalt lead to polymer coalescence and therefore the poor storage stability of modified asphalt. These challenges are exalted when recycling commingled plastics. This study introduced an innovative compatibilization strategy and mechanism for co-stabilizing commingled plastics and pyrolyzed rubber in asphalt. Commingled plastics were first grafted with maleic anhydride for surface activation, followed by reactive kneading with pyrolyzed rubber and crosslinking agent to form an integrated thermoplastic elastomer (ITPE) for asphalt modification. The mechanical, thermal, and interfacial behaviors of the ITPE were evaluated through tensile testing, thermogravimetric analysis, and scanning electron microscopy. The storage stability and rheological properties of the modified binder blends were evaluated through the cigar tube test and dynamic shear rheometer testing. Results demonstrated a successful formation of imide bonds in the ITPE, which can improve the strength, ductility, and thermal stability of rubber–plastic composites. Appropriate utilization of crosslinking agents can improve both rutting and fatigue resistance of ITPE-modified asphalt with good storage stability because of the co-existence of rigid plastic and soft rubbery regimes and the formation of a crosslink network. However, excessive content of crosslinker led to severe phase separation and reduced storage stability of modified binder blends. Extra crosslinker tended to float in asphalt because of its low density and caused an excessive formation of the crosslink network in the top section of the asphalt.
- 13 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (10) , 13350-13363
A Pavement Crack Translator for Data Augmentation and Pixel-Level Detection Based on Weakly Supervised Learning
Recent state-of-the-art pavement crack detection algorithms are data-driven and domain-sensitive due to their heavy reliance on datasets. Establishing a high-quality pavement crack dataset with various scenarios could help improve the robustness and generality of detection models. Therefore, this study presented the crack translator structure to achieve image style transfer, which can generate pavement crack images with different backgrounds for data augmentation. To get a better translation performance, we proposed two crack translators for comparison. The crack translator v2 was designed with attention blocks whereas crack translator v1 did not. The proposed crack translator v1 and v2 served as the weakly supervised method that was used to achieve pixel-level pavement crack detection and image transfer. Additionally, the crack translators were used to establish the dataset with various crack images and corresponding labels. Moreover, U-Net, SegNet, and W-segnet were compared to evaluate the effectiveness of data augmentation by using crack translators. Two open-source datasets were used to demonstrate the generalization of the proposed models. Results demonstrate that the proposed crack translator v2 outperforms crack translator v1 and other state-of-the-art methods in terms of evaluation metrics for image translation from normal background to shadow, wet, night, and grooved backgrounds. Crack translator (v2)-based augmentation contributes to a greater improvement than conventional augmentation for crack segmentation where F1 has increased by 5% for U-Net, SegNet, and 7% for W-segnet. The crack translator v2 yields equivalent results compared with U-Net on holdout EdmCrack600 and CRKWH100 datasets. Therefore, the proposed crack translator v2 can be effectively used to augment pavement crack images and it shows great potential for pixel-level pavement crack detection. Proposed crack translator v2 provides an integrated model for both data augmentation and pixel-level segmentation.
- 13 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (10) , 13350-13363
A Pavement Crack Translator for Data Augmentation and Pixel-Level Detection Based on Weakly Supervised Learning
Recent state-of-the-art pavement crack detection algorithms are data-driven and domain-sensitive due to their heavy reliance on datasets. Establishing a high-quality pavement crack dataset with various scenarios could help improve the robustness and generality of detection models. Therefore, this study presented the crack translator structure to achieve image style transfer, which can generate pavement crack images with different backgrounds for data augmentation. To get a better translation performance, we proposed two crack translators for comparison. The crack translator v2 was designed with attention blocks whereas crack translator v1 did not. The proposed crack translator v1 and v2 served as the weakly supervised method that was used to achieve pixel-level pavement crack detection and image transfer. Additionally, the crack translators were used to establish the dataset with various crack images and corresponding labels. Moreover, U-Net, SegNet, and W-segnet were compared to evaluate the effectiveness of data augmentation by using crack translators. Two open-source datasets were used to demonstrate the generalization of the proposed models. Results demonstrate that the proposed crack translator v2 outperforms crack translator v1 and other state-of-the-art methods in terms of evaluation metrics for image translation from normal background to shadow, wet, night, and grooved backgrounds. Crack translator (v2)-based augmentation contributes to a greater improvement than conventional augmentation for crack segmentation where F1 has increased by 5% for U-Net, SegNet, and 7% for W-segnet. The crack translator v2 yields equivalent results compared with U-Net on holdout EdmCrack600 and CRKWH100 datasets. Therefore, the proposed crack translator v2 can be effectively used to augment pavement crack images and it shows great potential for pixel-level pavement crack detection. Proposed crack translator v2 provides an integrated model for both data augmentation and pixel-level segmentation.