 |
Jian Li
School of Electronic
Engineering and Computer
Science
Queen Mary University of London Mile End Road, London, E1 4NS. UK. Email: jianli@dcs.qmul.ac.uk |
From August 2007 to August 2010, I was a research assistant in School of Electronic Engineering and Computer Science, Queen Mary University of London. I worked with Prof. Shaogang Gong and Dr. Tao Xiang on the BEWARE project, to develop computer vision solutions to enchance global situation awareness in wide area by analysing visual behaviours from multiple camera views. My research interests include behaviour profiling, scene context modelling, action recognition and behaviour retrieval. Before joining Queen Mary University of London, I was a PhD student at University of Bristol. My PhD project was for developing models to estimate and fuse optical flow information from multi-modality cameras and study human vision perception for visual surveillance applications. I was awarded full scholarship from University of Bristol and General Dynamics for my PhD research. |
| Education: Ph.D in Computer Vision and Experimental Psychology, University of Bristol, 2008 Supervisors: Dr. Chris Benton, Dr. Stavri Nikolov, Dr. Nick Scott-Samuel Thesis: Fusing motion information with spatial structure for surveillance applications M.Sc in Control Systems, Imperial College London, 2003 Supervisor: Dr. J.M.C. Clark Dissertation: Data association for multiple target tracking B.Eng in Automatic Control, Harbin Engineering University, 2002 |
| Data
Set: The Computer Vision Group releases three videos monitoring crowded traffic scenes. To download, click here. |
| Current Research: |
 | Discriminative Topics Modelling for Action Feature Selection and Recognition This
paper presents a framework for recognising realistic human actions
captured from unconstrained environments. The novelties of this work
lie in three aspects. First, we propose a new action representation
based on computing a rich set of descriptors from key point
trajectories. Second, in order to cope with drastic changes in motion
characteristics with and without camera movements, we develop an
adaptive feature fusion method to combine different local motion
descriptors for improving model robustness against feature noise and
background clutters. Finally, we propose a novel Multi-Class Delta
Latent Dirichlet Allocation model for feature selection. The most
informative features in a high dimensional feature space are selected
collaboratively, rather than independently as by existing feature
selection methods. Extensive experiments on challenging public datasets
demonstrate the effectiveness of the proposed framework. M. Bregonzio, J. Li, S. Gong and T. Xiang, Discriminative Topics Modelling for Action Feature Selection and Recognition, in Proceedings of British Machine Vision Conference (BMVC), Aberystwyth, UK, 31st August - 3rd September, 2010. |
 |
Discovering
Multi-Camera Behaviour Correlations for On-the-Fly Global Activity
Prediction and Anomaly Detection We
propose a unified framework using Latent Dirichlet Allocation (LDA) for
discovering behaviour global correlations over a distributed camera
network. We explore LDA for categorising object motion patterns as
local behaviours in each camera view before correlating these local
behaviours globally over different physical locations in multi-camera
views. In particular, a Temporal Order Sensitive
LDA (TOS-LDA) is formulated to discover behaviour global temporal correlations of different durations among all camera views simultaneously. In addition, a novel online global activity prediction method is proposed based on which global anomalies can be detected on the fly. J. Li, S. Gong, T. Xiang, Discovering Multi-Camera Behaviour Correlations for On-the-Fly Global Activity Prediction and Anomaly Detection, IEEE International Workshop on Visual Surveillance, Kyoto, Japan, 3rd October, 2009. |
 |
Global Behaviour Inference using
Probabilistic Latent Semantic Analysis We
present a novel framework for inferring global behaviour patterns
through modelling behaviour correlations in a wide-area scene and
detecting any anomaly in behaviours occurring both locally and
globally. Specifically, we propose a semantic scene segmentation model
to decompose a wide-area scene into regions where behaviours share
similar characteristic and are represented as classes of video events
bearing similar features. To model behavioural correlations globally,
we investigate both a probabilistic Latent Semantic Analysis (pLSA)
model and a two-stage hierarchical pLSA model for global behaviour
inference and anomaly detection.
J. Li, S. Gong, T. Xiang, Global Behaviour Inference using Probabilistic Latent Semantic Analysis, in Proceedings of British Machine Vision Conference (BMVC), Leeds, UK, 1-4 September, 2008. |
 |
Scene Decomposition for Behaviour
Correlation In
this work, we developed an approach for learning spatial context and
correlational context for abnormal behaviour detection. Without
employing tracking, low-level motion and shape features are extracted
and clustered to represent local video events. An unsupervised spectral
clustering is applied to determine the number of scene segments and
perform decomposition. In each of the regions, representation for video
events is further refined and global concurrence matrix is learned to
perform abnormal behaviour detection.
J. Li, S. Gong and T. Xiang, Scene Segmentation for Behaviour Correlation, in Proceedings of European Conference on Computer Vision (ECCV), Marseille, France, 2008. |
| Previous Research: |
 | Adaptive Summarisation of Surveillance Video Sequences We
describe our studies on summarising surveillance videos using optical
flow information. The proposed method incorporates motion analysis into
a video skimming scheme in which the playback speed is determined by
the detectability of interesting motion behaviours according to prior
information. A psycho-visual experiment was conducted to compare human
performance and viewing strategy for summarised videos using standard
video skimming techniques and a proposed motion-based adaptive summarisation technique. J. Li, S. G. Nikolov, C. P. Benton, N. E. Scott-Samuel, Adaptive Summarisation of Surveillance Video Sequences, in the International Conference on Advanced Visual Surveillance Systems (AVSS), 5-7, London, UK, 5-7 September, 2007. |
 | Adaptive Multiscale Optical Flow Estimation We
present a novel adaptive multiscale scheme to estimate optical flow
from image sequences. The scheme models estimation uncertainties which
are used to reduce the influence of unreliable intermediate estimates
on accuracy. The experimental results show that the proposed method
provides more accurate estimates for both small and large motions than
a standard multiscale scheme in which an increment is added to an
intermediate estimate regardless of estimation certainty. J. Li, C. P. Benton, S. G. Nikolov, N. E. Scott-Samuel, Adaptive Multiscale Optical Flow Estimation, in the International Conference on Image Processing (ICIP), San Antonio, Texas, USA, 16-19 September, 2007. |
 | Motion-Based Video Fusion Using Optical Flow Information Multi-sensor
information fusion aims at extracting and combining useful information
from different sensors. This work addresses the problem of estimating
and visualising motion information from a pair of visible and infrared
cameras, using an optical flow technique. Videos from cameras sensitive
to visible light are rich in texture and colour information such that a
moving target can readily be positioned. On the other hand, videos from
infrared cameras provide extra information which cannot be detected in
the visible-light spectrum. In this paper we introduce a stochastic
rule for combining optical flow computed from two (or more) sources. We
also propose a novel motion-contingent selection method for the fusion
of the co-registered visible and infrared video sources. J. Li, S. G. Nikolov, C. P. Benton, N. E. Scott-Samuel, Motion-Based Video Fusion using Optical Flow Information, in the 9th International Conference on Information Fusion (Fusion 2006), Florence, Italy, 10-13 July, 2006. |
 | Reliable Real-Time Optical Flow Estimation for Surveillance Applications We present a reliable real-time optical flow estimation framework which can be used in surveillance applications and video analysis. In normal imaging environments, reliability can be achieved by combining an extended optical flow constraint with a smoothing procedure and a masking procedure. In noisy environments, total least squares is adopted to ensure accuracy. The proposed system is able to recover up to 31 frames of dense optical flow per second using a Xeon 3.06GHz workstation, which makes it very useful in a range of surveillance systems that are based on standard PC hardware. J. Li, S. G. Nikolov, N. E. Scott-Samuel, C. P. Benton, Reliable Real-Time Optical Flow Estimation for Surveillance Applications, in the Proceedings of the IEE Conference on Crime and Security: Imaging for Crime Detection and Prevention (ICDP), London, UK, 13-14 June, 2006. |
| Publications: |
| Journal
Articles: J. Li, S. Gong and T. Xiang, Learning Behavioural Context, accepted to International Journal of Computer Vision (IJCV), 2011
T. Hospedales, J. Li, S. Gong and T. Xiang, Identifying Rare and Subtle Behaviours: A weakly Supervised Joint Topic Model, to appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE PAMI), 2011. T. D. Dixon, S. G. Nikolov, J. J. Lewis, J. Li, E. F. Canga, J. M. Noyes, T. Troscianko, D. R. Bull, C. N. Canagarajah, Task-based scanpath assessment of multi-sensor video fusion in complex scenarios, Information Fusion, Vol. 11, Issue 1, page 51-65, 2010. T. D. Dixon, S. G. Nikolov, J. Lewis, J. Li, E. F. Canga, J. M. Noyes, T. Troscianko, D. R. Bull, C. N. Canagarajah, Assessment of Fused Video Using Scanpaths: A Comparison of Data Analysis Methods, Spatial Vision, Volume 20, Number 5, pp. 437-466(30), 2007. |
| Conference
Articles: J. Li, T. M. Hospedales, S. Gong and
T. Xiang, Learning Rare Behaviours, Asian Conference on Computer Vision
(ACCV), Queenstown, New Zealand, 8-12 November, 2010.
M. Bregonzio, J. Li, S. Gong and T. Xiang, Discriminative Topics Modelling for Action Feature Selection and Recognition, in Proceedings of British Machine Vision Conference (BMVC), Aberystwyth, UK, 31st August - 3rd September, 2010. J. Li, S. Gong, T. Xiang, Discovering Multi-Camera Behaviour Correlations for On-the-Fly Global Activity Prediction and Anomaly Detection, IEEE International Workshop on Visual Surveillance, Kyoto, Japan, 3rd October, 2009. J. Li, S. Gong, T. Xiang, Scene Segmentation for Behaviour Correlation, in Proceedings of European Conference on Computer Vision (ECCV), Marseille, France, 12-18 October, 2008. J. Li, S. Gong, T. Xiang, Global Behaviour Inference using Probabilistic Latent Semantic Analysis, in Proceedings of British Machine Vision Conference (BMVC), Leeds, UK, 1-4 September, 2008. J. Li, C. P. Benton, S. G. Nikolov, N. E. Scott-Samuel, Adaptive Multiscale Optical Flow Estimation, in the International Conference on Image Processing (ICIP), San Antonio, Texas, USA, 16-19 September, 2007. J. Li, S. G. Nikolov, C. P. Benton, N. E. Scott-Samuel, Adaptive Summarisation of Surveillance Video Sequences, in the International Conference on Advanced Visual Surveillance Systems (AVSS), 5-7, London, UK, 5-7 September, 2007. T. Dixon, S. G. Nikolov, J. Li, E. F. Canga, J. J. Lewis, T. Troscianko, J. Noyes, C. N. Canagarajah, D. R. Bull, Scanpath Assessment of Visible and Infrared Side-by-Side and Fused Video Displays, in the Proceedings of the 10th International Conference on Information Fusion, (Fusion 2007), Quebec City, Canada, 9-12 July 2007 J. Li, S. G. Nikolov, C. P. Benton, N. E. Scott-Samuel, Motion-Based Video Fusion using Optical Flow Information, in the 9th International Conference on Information Fusion (Fusion 2006), Florence, Italy, 10-13 July, 2006. J. Li, S. G. Nikolov, N. E. Scott-Samuel, C. P. Benton, Reliable Real-Time Optical Flow Estimation for Surveillance Applications, in the Proceedings of the IEE Conference on Crime and Security: Imaging for Crime Detection and Prevention (ICDP), London, UK, 13-14 June, 2006. T. D. Dixon, S. G. Nikolov, J. J. Lewis, J. Li, E. F. Canga, J. Noyes, T. Troscianko, D. R. Bull, C. N. Canagarajah, Scanpath Analysis of Fused Multi-Sensor Images with Luminance Change: A Pilot Study, in the 9th International Conference on Information Fusion (Fusion 2006), Florence, Italy, 10-13 July, 2006. L. Mihaylova, A. Loza, S. G. Nikolov, J. J. Lewis, E.-F. Canga, J. Li, C. N. Canagarajah and D. R. Bull, The Influence of Multi-Sensor Video Fusion on Object Tracking Using a Particle Filter, in the Proceedings of the 2nd Workshop Multiple Sensor Data Fusion: Trends, Solutions, Applications, Dresden, Germany, 2-6 October, 2006. T. D. Dixon, S. G. Nikolov, J. Lewis, J. Li, E. F. Canga, J. M. Noyes, T. Troscianko, D. R. Bull, C. N. Canagarajah, Multi-Sensor Fused Video Assessment Using Scanpath Analysis, in the Proceedings of the Biologically Inspired Information Fusion Workshop, Sussex, pp 14-19, August, 2006. |
| Technical
Reports: J.
Li, S. G. Nikolov, C. P. Benton, N. E. Scott-Samuel, Multi-Sensor
Motion Computation, Analysis and Fusion, University of Bristol
Technical Report, March 2006.
J. Li, S. G. Nikolov, C. P. Benton, N. E. Scott-Samuel, Video Summarisation Through Fusion of Motion and Spatial Information. University of Bristol Technical Report, September 2006. L. Mihaylova, A. Loza, S. G. Nikolov, J. J. Lewis, J. Li, et al, Object Tracking in Multi-Sensor Video, University of Bristol Technical Report, March 2006. S. G. Nikolov, J. Li, J. J. Lewis, et al, Spatio-Temporal Video Fusion, University of Bristol Technical Report, September 2006. J. J. Lewis, S. G. Nikolov, J. Li, et al, Techniques for Multi-Sensor Video Fusion, University of Bristol Technical Report, September 2006. J. J. Lewis, S. G. Nikolov, J. Li et al, The Eden Project Multi-Sensor Data Set, University of Bristol Technical Report, September 2005. |