主要从事“基于视频大数据分析的安全化、智慧化城市建设”这一交叉前沿领域的研究，作为骨干科研人员参与了荷兰国家经济开发（FES）、美国国家科学基金会（NSF）和美国海军研究中心（ONR）、新加坡智慧城市建设（POLCAM 2.0）等多个项目。近年来，围绕图像去噪、运动估计、目标分割和基于深度学习的视频大数据分析，申请人发表学术论文30余篇，其中近20篇发表在图像处理和人工智能领域的国际权威SCI期刊（如IEEE TIP、Pattern Recognition、IEEE T-CSVT）和国际顶级会议（如CVPR、ACM Multimedia）上。研究成果被BBC、Dutch TV、新加坡最权威的《海峡时报》等国际主流媒体广泛报道。

      其中主持开发的基于视频大数据的异常事件检测系统被世界500强企业埃森哲（Accenture）商业推广，受到新加坡警方高度认可并用于新加坡智慧城市建设，已有超过7万个基于该系统的智能摄像头被安装于新加坡的大街小巷。担任多个人工智能、图像处理、计算机视觉领域的国际SCI期刊(如TIP, PR, TCSVT,TMM等)和知名会议(如ACM MM, ACCV, ICPR等)的审稿专家。担任2017年国际知名遥感大会 ISPRS  workshop on Image and Data Fusion的区域主席(Area  Chair)。担任全球最大的国际图像处理大会 ICIP2018 的专家组审稿委员。

2019

• Zhigang Tu, Dejun Zhang, Michael Hoy, Justin Dauwels, Baoxin Li, and Junsong Yuan. Action-Stage Emphasized Spatio-Temporal VLAD for Video Action Recognition, IEEE Transactions on Image Processing (TIP), May, 2019.

2018

•  Zhigang Tu, Wei Xie, Justin Dauwels, Baoxin Li, and Junsong Yuan. Semantic Cues Enhanced Multi-modality Multi-Stream CNN for Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), DOI: 10.1109/TCSVT.2018.2830102, 2018.

•  Zhigang Tu, Wei Xie, Qianqing Qin, Remco C. Veltkamp, Baoxin Li, and Junsong Yuan. Multi-Stream CNN: Learning Representations Based on Human-Related Regions for Action Recognition. Pattern Recognition, vol.79, pp.32–43, 2018.

•  Shizheng Wang, Wenjuan Liao, Phil Surman, Zhigang Tu, Yuanjin Zheng, and Junsong Yuan. Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display. In Proc. Comput. Vis. Pattern Recogn. (CVPR), 2018.

2017

•  Zhigang Tu, Zuwei Guo, Wei Xie, Mengjia Yan, Remco. C. Veltkamp, Baoxin Li, and Junsong Yuan. Fusing disparate object signatures for salient object detection in video. Pattern Recognition, vol.72, pp.285–299, 2017.

•  Zhigang Tu, Wei Xie, C. Gemeren, and Remco C. Veltkamp. Variational Method for Joint Optical Flow Estimation and Edge-aware Image Restoration. Pattern Recognition, vol.65, pp.11–25, 2017.

2016

• Zhigang Tu, Ronald Poppe, and Remco C. Veltkamp. Weighted Local Intensity Fusion Method for Variational Optical Flow Estimation. Pattern Recognition, vol.50, pp.223–232, 2016.

• Zhigang Tu, Ronald Poppe, and Remco C. Veltkamp. Adaptive Guided Image Filter for Warping in Variational Optical Flow. Signal Processing, vol.127, pp.253–265, 2016.

2015

• Zhigang Tu, Coert Van Gemeren, and Remco C. Veltkamp. Improved color patch similarity measure based weighted median filter. In Proc. Asian Conf. Comput. Vis. (ACCV), vol.9007, pp.413–427, 2015.

2014

•  Zhigang Tu, Nico. Aa, C. Gemeren, and Remco C. Veltkamp. A combined post-filtering method to improve accuracy of variational optical flow estimation. Pattern Recognition, vol.47, no.5, pp.1926–1940, 2014.