图像清晰度是保障视频监控系统可靠应用的关键性前提之一。由于区域性雾霾、雨雪、低照度的干扰,使得监控系统中光学传感器的成像精确性减弱,进而导致所捕获图像/视频的可视性急剧下降。针对恶劣天气所导致的低画质问题,本人一直从事于图像处理与人工智能跨学科交叉领域研究,致力于探索高鲁棒且低功耗的场景复原理论与方法,同时也为监控及其智能系统的可靠性应用提供重要理论和关键技术支撑。
主持的科研项目包括:
[1]
国家自然科学基金面上项目:兼顾人眼感知与机器认知的非限定退化图像增强理论与方法研究
[2]
国家自然科学基金青年项目:面向实时视频去雾的关键技术研究
[3]
江苏省自然科学基金青年项目:面向实时性视频去雾的若干关键技术研究
[4]
江苏省高校自然科学基金面上项目:恶劣环境下非限定退化图像增强技术研究
[5]
中国博士后面上基金:基于时空相关性的视频去雾关键技术研究
[6]
江苏省博士后科研资助计划基金:视频去雾中参数估计理论与方法研究
[7]
大疆科技横向基金:面向无人机的航拍视频清晰化研究
[8]
OPPO研究院-AI ISP横向基金:面向手机影像的场景重建
[9]
南京邮电大学科研启动基金:基于深度学习的图像去雾理论与方法研究
[10] 南京邮电大学项目孵化基金:非限定退化图像增强技术研究
发表的代表性论文包括:
[1]
M.
Ju, C. Ding, Y. jay Guo,
and D. Zhang, “IDGCP: Image Dehazing Based on Gamma Correction Prior,” IEEE Transactions on Image Processing,
vol. 29, pp. 3104-3118, 2020. (SCI中科院一区,
IF=11.041, ESI高被引,CCF-A)
[2]
M.
Ju, C. Ding, W. Ren, Y.
Yang, D. Zhang and Y. J. Guo, "IDE: Image Dehazing and Exposure Using an
Enhanced Atmospheric Scattering Model," IEEE Transactions on Image Processing, vol. 30, pp. 2180-2192, 2021.
(SCI中科院一区,
IF=11.041, ESI高被引,CCF-A)
[3]
M.
Ju, C. Ding, Charles A.
Guo, W. Ren, and D. Tao, "IDRLP: Image Dehazing Using Region Line
Prior," IEEE Transactions on Image
Processing, vol. 30, pp. 9043-9057, 2022. (SCI中科院一区, IF=11.041, CCF-A)
[4]
M.
Ju, C. He, C. Ding, W.
Ren, L. Zhang and K. -K. Ma, "All-Inclusive Image Enhancement for Degraded
Images Exhibiting Low-Frequency Corruption," IEEE Transactions on
Circuits and Systems for Video Technology, vol. 35, no. 1, pp. 838-856,
Jan. 2025. (SCI中科院一区,
IF=8.4, CCF-B)
[5]
M.
Ju, C. Ding, W. Ren, and
Y. Yang, “IDBP: Image Dehazing Using Blended Priors Including Non-local, Local,
and Global Priors," IEEE
Transactions on Circuits and Systems for Video Technology, vol. 32, no. 7,
pp. 4867-4871, July 2022. (SCI中科院一区,
IF=8.4, CCF-B)
[6]
M.
Ju, C. He, J. Liu, B.
Kang, J. Su, D. Zhang, “IVF-Net: An Infrared and Visible Data Fusion Deep
Network for Traffic Object Enhancement in Intelligent Transportation Systems.
vol. 24, no. 1, pp. 1220-1234, Jan. 2023. IEEE Transactions on Intelligent Transportation Systems. (SCI中科院一区,
IF=8.5, CCF-B)
[7]
M.
Ju, C. Ding, D. Zhang, and
Y. jay Guo, “BDPK: Bayesian Dehazing Using Prior Knowledge,” IEEE Transactions on Circuits and Systems
for Video Technology, vol. 29, no. 8, pp. 2349-2362, Aug. 2019. (SCI中科院一区,
IF=8.4, CCF-B)
[8]
M.
Ju, S. Xie and F. Li,
"Semantic-Aware Low-Light Image Enhancement Network for Recognizing
Semantics in Intelligent Transportation Systems," IEEE Transactions on Intelligent
Transportation Systems,Early Access 2025. (SCI中科院一区,
IF=8.5, CCF-B)
[9]
M.
Ju, S. Xie and F. Li,
"Improving Skip Connection in U-Net through Fusion Perspective With Mamba
for Image Dehazing," IEEE Transactions on Consumer Electronics,vol. 70, no. 4, pp. 7505-7514, Nov. 2024. (SCI中科院二区,
IF=4.3)
[10] M. Ju, F. Li and S. Xie, "FGN: A Fully Guided Network
for Image Dehazing," IEEE Signal Processing Letters, vol. 31, pp.
1870-1874, 2024. (SCI中科院二区)
本人每年将在全校范围内遴选并指导本科生2-5名(包含贝尔学院2名),指导物联网学院研究生3-5名。研究生在完成指定学业的前提下也可派遣相关企业实习,欢迎志同道合的本科生或研究生与我联系(Jumingye@njupt.edu.cn)。
已毕业的学生深造或就业情况:
何春明(本科生),已保研至清华大学,现杜克大学读博。
陈楚恒(本科生),已保研至中科院信工所直博。
陈 凯(本科生),已保研至东南大学。
王 欣(研究生),南京联通研究院
王时巨(研究生),山东省公务员
刘昊然(研究生),苏州电信设计研究院
张 林(研究生),江苏农村信用社银监会