Jian Zhao | Image processing | Best Researcher Award

Dr. Jian Zhao | Image processing | Best Researcher Award

Lecturer at Nanjing Institute of Technology, China

Dr. Jian Zhao is a Lecturer at the School of Computer Engineering, Nanjing Institute of Technology. He earned his PhD in Physical Electronics from Southeast University (2019) and was a visiting scholar at Newcastle University, UK, specializing in Stereoscopic Vision. His research focuses on light field displays, deep learning for micro-expression analysis, and ultrafast spatial light modulation. He has secured multiple grants, including from the National Natural Science Foundation of China. Dr. Zhao has published in OPTICS EXPRESS, IEEE Photonics Journal, and IET Image Processing, contributing significantly to computational imaging and display technologies. πŸ“‘πŸ“Έ

Publication Profile

Orcid

Educational Background πŸŽ“πŸ“š

Dr. Jian Zhao holds a Doctoral Degree in Physical Electronics from Southeast University (2012-2019), where he specialized in advanced optical and electronic systems. To enhance his expertise, he pursued a research stay as a visiting student at Newcastle University, UK (2017-2018), focusing on stereoscopic vision. His academic journey reflects a strong foundation in optics, imaging, and display technologies, equipping him with the skills to innovate in light field displays and computational imaging. His international experience has further broadened his research perspective, enabling him to contribute to cutting-edge developments in visual perception and display systems. πŸŒπŸ”¬

Research and Academic Work Experience πŸ”¬πŸ“‘

Dr. Jian Zhao has led multiple research projects in cutting-edge imaging and display technologies. He has secured funding from the National Natural Science Foundation of China for projects on deep network models for micro-expression analysis in complex environments and ultrafast phase-type spatial light modulation using disordered structure metasurfaces. Additionally, his work, supported by the Natural Science Foundation of Jiangsu Province, explores near-eye light field imaging with polarization volume holographic gratings. He also received funding from the Jiangsu Provincial Department of Education to study near-eye display systems based on human visual perception. His research contributes significantly to computational imaging advancements. πŸŽ₯πŸ“Š

Research Focus Areas

Dr. Jian Zhao specializes in computational imaging, display technology, and deep learning applications. His research spans autostereoscopic displays πŸ–₯️, light field imaging πŸ“Έ, and human visual perception πŸ‘€. He applies AI and deep learning πŸ€– to urban waterlogging detection 🌊, visual fatigue assessment πŸ‘“, and surface defect detection πŸ“±. His expertise extends to virtual avatars πŸ§‘β€πŸ’» and photonic nanotechnology πŸ”¬. Dr. Zhao contributes significantly to metasurface optics, spatial light modulation, and advanced display systems. His interdisciplinary work impacts computer vision, optoelectronics, and smart imaging technologies. πŸš€βœ¨

Publication Top Notes

  • 2025: “Urban Waterlogging Monitoring and Recognition in Low-Light Scenarios Using Surveillance Videos and Deep Learning”

  • 2024: “A Multimodal Visual Fatigue Assessment Model Based on Back Propagation Neural Network and XGBoost”

  • 2023: “Study on Random Generation of Virtual Avatars Based on Big Data”

  • 2023: “Viewing Zone Expansion of Autostereoscopic Display With Composite Lenticular Lens Array and Saddle Lens Array”

  • 2023: “Mobile Phone Screen Surface Scratch Detection Based on Optimized YOLOv5 Model (OYm)”

  • 2019: “Spatial Loss Factor for the Analysis of Accommodation Depth Cue on Near-Eye Light Field Displays”

  • 2019: “Tilted LCD Pixel With Liquid Crystal GRIN Lens for Two-Dimensional/Three-Dimensional Switchable Display”

  • 2019: “Hybrid Computational Near-Eye Light Field Display”

  • 2019: “Switchable Photonic Nanojet by Electro-Switching Nematic Liquid Crystals”

 

Zhidan Ran | Computer Vision | Best Researcher Award

Dr. Zhidan Ran | Computer Vision | Best Researcher Award

Dr. Zhidan Ran, Southeast University, China

Dr. Zhidan Ran is a Ph.D. candidate in Control Science and Engineering at Southeast University, specializing in computer vision, person re-identification, and image retrieval. With multiple high-impact publications in IEEE Transactions and Pattern Recognition, he focuses on advancing security technologies through person re-identification and anomaly detection. He holds several patents, including methods for oil stain detection in vehicles. Dr. Ran has received notable awards, such as the Jiangsu College Student Electronic Design Competition (First Prize). His contributions to AI and automation continue to push boundaries in both theory and application. 🧠✨

 

Publication Profile

Scopus

Education πŸŽ“

Dr. Zhidan Ran has pursued all levels of his higher education at Southeast University, Nanjing, China, showcasing his dedication to academic excellence. He is currently a Ph.D. candidate in Control Science and Engineering (2021–present), under the guidance of Dr. Xiaobo Lu, focusing on advanced technologies in computer vision and automation. Previously, he completed his Master’s degree (2019–2021) in the same field, mentored by Dr. Haikun Wei, where he deepened his expertise in innovative control systems. Dr. Ran earned his Bachelor’s degree in Automation (2015–2019), laying the foundation for his impactful career in automation and engineering. πŸŒŸπŸ“š

 

Research Interests

Dr. Zhidan Ran is a dedicated researcher specializing in computer vision, person re-identification, and image retrieval. His work focuses on leveraging advanced technologies to improve security and automation systems. As a Ph.D. candidate in Control Science and Engineering at Southeast University, he has contributed to several cutting-edge projects and high-impact publications. His expertise in developing innovative solutions for image-based recognition and retrieval demonstrates his commitment to advancing AI and machine learning applications. Dr. Ran’s research aims to bridge theoretical advancements and real-world implementations, driving progress in smart systems and intelligent automation. 🧠✨

 

Awards and Achievements

Dr. Zhidan Ran has been honored with numerous prestigious awards, showcasing his exceptional talent in technology and innovation. He secured first prize in the Jiangsu College Student Electronic Design Competition (2018) and achieved third prize in both the China College Students Computer Design Competition and the Jiangsu Mathematical Contest in Modeling (2017). His ingenuity was further recognized with an Excellence Award at the Southeast University Smart Car Competition (2017). Additionally, he earned the coveted Southeast University President Scholarship for 2016-2017. These accolades reflect his dedication to pushing the boundaries of automation and engineering. πŸ₯‡πŸ€–

 

Research Focus

Dr. Zhidan Ran specializes in cutting-edge research areas, including computer vision, person re-identification, and image retrieval. His work extends to video-based anomaly detection and camera domain adaptation, as evident in studies like Multiscale Aligned Spatial-Temporal Interaction and Camera Domain Adaptation Using Transformers. Additionally, he contributes to transportation safety, focusing on oil stain detection for high-speed trains through advanced networks like MFANet and PCCN. With innovations in top-view fisheye cameras and adaptive frameworks, Dr. Ran’s interdisciplinary expertise bridges automation and visual intelligence, pushing the boundaries of smart systems and transport technologies. πŸš‰πŸ“·πŸ’‘

 

Publication Top Notes Β 

πŸ“ Anomaly-Aware Semantic Self-Alignment Framework for Video-Based Person Re-Identification (2024) – Cited by: 0
πŸ“ Multiscale Aligned Spatial-Temporal Interaction for Video-Based Person Re-Identification (2024) – Cited by: 0
πŸ›€οΈ MFANet: Multifaceted Feature Aggregation Network for Oil Stains Detection of High-Speed Trains (2023) – Cited by: 2
πŸ“· DCPB: Deformable Convolution Based on the PoincarΓ© Ball for Top-view Fisheye Cameras (2023) – Cited by: 0
πŸ› οΈ PCCN: Progressive Context Comprehension Network for Oil Stains Detection of High-Speed Trains (2023) – Cited by: 2
πŸŽ₯ Camera Domain Adaptation Based on Cross-Patch Transformers for Person Re-Identification (2022) – Cited by: 7