Zeyu Fu
Improving data association in online human tracking.
Email: z.fu2@ncl.ac.uk
Project title
Novel data association methods for online multiple human tracking
Supervisors
Project description
Video-based multiple human tracking plays a crucial role in many applications such as:
- intelligent video surveillance
- human behaviour analysis
- health-care systems
The detection based tracking framework has become the dominant paradigm in this research field. The major task is accurate data association between detections across the frames.
Online multiple human tracking relies on detection in real time for data association. It becomes more challenging with noisy detections, missed detections, and occlusions.
We will address existing challenges in human tracking. We will explore various signal processing, machine learning and information fusion methods.
Interests
Machine learning, video processing, information fusion and medical image analysis.
Publications
- Fu Z, Feng P, Naqvi M, Chambers JA. Particle PhD Filter Based Multi-Target Tracking Using Discriminative Group-Structured Dictionary Learning. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017). 2017, New Orleans: IEEE.
- Fu Z, Feng P, Angelini F, Chambers JC, Naqvi SM. Particle PHD Filter Based Multiple Human Tracking using Online Group-Structured Dictionary Learning. IEEE Access 2018, 6, 14764-14778.
- Fu Z, Naqvi SM, Chambers JA. Enhanced GM-PHD Filter Using CNN-Based Weight Penalization for Multi-Target Tracking. In: Sensor Signal Processing for Defence Conference (SSPD 2017). 2017, London: IEEE.
- Fu Z, Xin L, Naqvi SM. Enhanced Detection Reliability for Human Tracking Based Video Analytics. In: 22nd International Conference on Information Fusion (FUSION). 2019, Ottawa, Canada.
- FU Z, Chambers JA, Naqvi MN. GM-PHD Filter Based Online Multiple Human Tracking Using Deep Discriminative Correlation Matching. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018). 2018, Calgary, Alberta, Canada: IEEE.
- Fu Z, Naqvi SM, Chambers JA. Collaborative Detector Fusion of Data-Driven PHD Filter for Online Multiple Human Tracking. In: 2018 21st International Conference on Information Fusion, FUSION 2018. 2018, Cambridge, UK: IEEE.
- Fu Z, Angelini F, Chambers JC, Naqvi SM. Multi-Level Cooperative Fusion of GM-PHD Filters for Online Multiple Human Tracking. IEEE Transactions on Multimedia 2019, 21(9), 2277-2291.
- Fu Z, Feng P, Mohsen Naqvi S, Chambers JA. Robust particle PHD filter with sparse representation for multi-Target tracking. In: International Conference on Digital Signal Processing (DSP). 2017, Beijing, China: IEEE.
Qualifications
- BEng in Electrical and Electronics Engineering (1st class), Newcastle University, UK.