Hongda Tian received the B.Sc. and M.En. degrees from Beijing University of Posts and Telecommunications, China in 2006 and 2009, respectively, and the Ph.D. degree from the University of Wollongong, Australia in 2015. Before joining UTS, he was a Postdoctoral Fellow with DATA61 | CSIRO, a Computer Vision Scientist with Kandao Australia Pty Ltd. and an Associate Research Fellow with the University of Wollongong. Dr. Tian's research interests spread across data science, machine learning, computer vision, pattern recognition, and image and video processing. His research work appears in highly-regarded venues in these fields including International Journal of Computer Vision (IJCV), IEEE Transactions on Image Processing (IEEE TIP), etc. Due to his excellence in research, he received the Chinese Government Award for Outstanding Self-financed Students Abroad in 2013. Dr. Tian serves as a technical program committee member or reviewer for 10+ peer-reviewed journals and conferences.
- Highly Commended Award in Canon Extreme Imaging Competition (2014)
- Chinese Government Award for Outstanding Self-financed Students Abroad (2013)
- International Postgraduate Tuition Award and Matching Scholarship (2010-2013)
- Excellent Thesis Award for Master’s Degree (2009) (17 out of 2700 graduates)
- Chinese Government Scholarship for Postgraduate (2006-2009)
Program Committee Member
- IEEE International Conference on Multimedia Big Data
- IEEE Transactions on Image Processing
- IEEE Transactions on Cybernetics
- IEEE Transactions on Multimedia
- IEEE Transactions on Circuits and Systems for Video Technology
- IEEE Transactions on Intelligent Transportation Systems
- Journal of Visual Communication and Image Representation
- Signal, Image and Video Processing
- Fire Technology
- IPSJ Transactions on Computer Vision and Applications
- IEEE International Conference on Robotics and Automation
- ACM International Conference on Multimedia
- IEEE Winter Conference on Applications of Computer Vision
Can supervise: YES
Current Research Interests
- Knowledge Representation and Machine Learning
- Computer Vision
- Pattern Recognition and Data Mining
- Artificial Intelligence and Image Processing
Previous Research Interests
- Photonics, Optoelectronics and Optical Communications
Tian, H, Li, W, Ogunbona, PO & Wang, L 2018, 'Detection and Separation of Smoke From Single Image Frames', IEEE TRANSACTIONS ON IMAGE PROCESSING, vol. 27, no. 3, pp. 1164-1177.View/Download from: UTS OPUS or Publisher's site
Liu, S, Li, W, Davis, S, Ritz, C & Tian, H 2016, 'Planogram compliance checking based on detection of recurring patterns', IEEE MultiMedia, vol. 23, no. 2, pp. 54-63.View/Download from: Publisher's site
© 1994-2012 IEEE. In this article, the authors propose a novel method for automatic planogram compliance checking in retail chains that doesn't require product template images for training. Product layout is extracted from an input image by means of unsupervised recurring pattern detection and matched via graph matching, with the expected product layout specified by a planogram to measure the level of compliance. A divide-and-conquer strategy is employed to improve the speed. Specifically, the input image is divided into several regions based on the planogram. Recurring patterns are detected in each region, respectively, and then merged together to estimate the product layout.
Tian, H, Li, W, Wang, L & Ogunbona, P 2014, 'Smoke Detection in Video: An Image Separation Approach', INTERNATIONAL JOURNAL OF COMPUTER VISION, vol. 106, no. 2, pp. 192-209.View/Download from: Publisher's site
Yan, H-F, Yu, Z-Y, Liu, Y-M, Tian, H-D & Han, L-H 2011, 'Novel Propagation Properties of Total Internal Reflection Photonic Crystal Fibres with Rhombic Air Holes', CHINESE PHYSICS LETTERS, vol. 28, no. 11.View/Download from: Publisher's site
Yan, HF, Yu, ZY, Tian, HD, Liu, YM & Han, LH 2010, 'Investigation on propagation and nonlinearity of an octagonal photonic crystal fiber', Wuli Xuebao/Acta Physica Sinica, vol. 59, no. 5, pp. 3273-3277.
The finite element method is used to investigate the propagation and nonlinearity of octagonal photonic crystal fibers of total internal reflection type. We changed the structural parameters of the fibers and obtained the curves of relations about the propagation and nonlinearity. At last, we found another structure of photonic crystal fiber. It is demonstrated that it is possible to design a low-loss dispersion-flattened PCF at 1.55 micrometer wavelength. © 2010 Chin. Phys. Soc.
JIA, BY, YU, ZY, LIU, YM & TIAN, HD 2010, 'Calculation of valence band structures of InAs/GaAs quantum ring and quantum dot: using numerical Fourier transform method', Journal of China Universities of Posts and Telecommunications, vol. 17, no. 1, pp. 106-110.View/Download from: Publisher's site
This article puts forward a new method in calculating the band structures of low-dimensional semiconductor structures. In this study, the valence band structures of InAs/GaAs quantum ring and lens-shaped quantum dot are calculated with four-band model, in the framework of effective-mass envelope function theory. To determine the Hamiltonian matrix elements, this article develops the numerical Fourier transform method instead of the widely used analytical integral method. The valence band mixing is considered. The hole energy levels change dramatically with the geometrical parameters of the quantum ring and quantum dot. It is demonstrated that numerical Fourier transform method can be adopted in low-dimensional structures with any shape. The results of Fourier transform method are consistent with the ones of analytical integral in literature; and they are helpful for studying and fabricating optoelectronic devices. © 2010 The Journal of China Universities of Posts and Telecommunications.
Feng, H, Yu, ZY, Liu, YM, Lu, PF, Jia, BY, Yao, WJ, Tian, HD, Zhao, W & Xu, ZH 2010, 'Theoretical study on strain compensation layer for growth of quantum dots', Wuli Xuebao/Acta Physica Sinica, vol. 59, no. 2, pp. 765-770.
The optical properties of quantum dots have a close relationship with the size fluctuation, density, strain filed distribution of the dots and the spacer layer thickness. InAs/GaAs quantum dot with GaN X As 1-X strain compensation layers (SCL) is theoretically investigated for improving the crystal quality. The reduction effects of the spacer thickness are discussed quantitatively. The influence of the location and the N concentration of the GaN X As 1-X SCL on compensation of the strain formed on quantum dots (QDs) and the system is also discussed. The reduction effect of SCL on strain of system is analyzed and the vertical alignment probability between the adjacent layers is calculated. Our results can provide a theoretical basis for finding the optimal properties of SCL to realize the high quality multi-QD layer. © 2010 Chin. Phys. Soc.
TIAN, HD, YU, ZY, HAN, LH & LIU, YM 2009, 'Effect of the structural parameters of photonic crystal fibers on propagation characteristics', Journal of China Universities of Posts and Telecommunications, vol. 16, no. 2.View/Download from: Publisher's site
Using a full-vector finite-difference time-domain (FDTD) method, this article explores the propagation characteristics of photonic crystal fiber (PCF) theoretically. The dependence of structural parameters on the effective index of the fundamental guided mode, effective index of the fundamental cladding mode, mode field diameter, confinement loss, effective mode area, and chromatic dispersion in PCF have been studied, respectively. The research presents a reference for designing of PCF with a specific purpose. © 2009 The Journal of China Universities of Posts and Telecommunications.
Tian, H-D, Yu, Z-Y, Han, L-H & Liu, Y-M 2009, 'Lateral stress-induced propagation characteristics in photonic crystal fibres', CHINESE PHYSICS B, vol. 18, no. 3, pp. 1109-1115.
Liu, S & Tian, H 2015, 'Planogram Compliance Checking using Recurring Patterns', 2015 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), IEEE International Symposium on Multimedia (ISM), IEEE, Miami, FL, pp. 27-32.View/Download from: Publisher's site
Tian, H, Li, W, Ogunbona, P & Wang, L 2014, 'Single Image Smoke Detection', COMPUTER VISION - ACCV 2014, PT II, 12th Asian Conference on Computer Vision (ACCV), SPRINGER-VERLAG BERLIN, Singapore, SINGAPORE, pp. 87-101.View/Download from: Publisher's site
Tian, H, Li, W, Wang, L & Ogunbona, P 2012, 'A novel video-based smoke detection method using image separation', Proceedings - IEEE International Conference on Multimedia and Expo, pp. 532-537.View/Download from: Publisher's site
In the state-of-the-art video-based smoke detection methods, the representation of smoke mainly depends on the visual information in the current image frame. In the case of light smoke, the original background can be still seen and may deteriorate the characterization of smoke. The core idea of this paper is to demonstrate the superiority of using smoke component for smoke detection. In order to obtain smoke component, a blended image model is constructed, which basically is a linear combination of background and smoke components. Smoke opacity which represents a weighting of the smoke component is also defined. Based on this model, an optimization problem is posed. An algorithm is devised to solve for smoke opacity and smoke component, given an input image and the background. The resulting smoke opacity and smoke component are then used to perform the smoke detection task. The experimental results on both synthesized and real image data verify the effectiveness of the proposed method. © 2012 IEEE.
Tian, H, Li, W, Ogunbona, P, Nguyen, DT & Zhan, C 2011, 'Smoke detection in videos using non-redundant local binary pattern-based features', MMSP 2011 - IEEE International Workshop on Multimedia Signal Processing.View/Download from: Publisher's site
This paper presents a novel and low complexity method for real-time video-based smoke detection. As a local texture operator, Non-Redundant Local Binary Pattern (NRLBP) is more discriminative and robust to illumination changes in comparison with original Local Binary Pattern (LBP), thus is employed to encode the appearance information of smoke. Non-Redundant Local Motion Binary Pattern (NRLMBP), which is computed on the difference image of consecutive frames, is introduced to capture the motion information of smoke. Experimental results show that NRLBP outperforms the original LBP in the smoke detection task. Furthermore, the combination of NRLBP and NRLMBP, which can be considered as a spatial-temporal descriptor of smoke, can lead to remarkable improvement on detection performance. © 2011 IEEE.