Sing Yee Chua

Sing Yee Chua

Auto-generated profile, based on publicly available information

Sing Yee Chua

Department of Electrical and Electronic Engineering, Universiti Tunku Abdul Rahman, Kajang, Malaysia

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 April 2016 in Journal of the European Optical Society-Rapid Publications
Verified
Journal Article
Open access
PDF file
SCS. Y. Chua
S. Y. Chua
Xin WangXin Wang
Xin Wang
NGN. Guo
N. Guo
CTC. S. Tan
C. S. Tan
TCTong Yuen Chai
Tong Yuen Chai
GSG. L. Seet
G. L. Seet
This paper performs an experimental investigation on the TOF imaging profile which strongly influences the quality of reconstruction to accomplish accurate range sensing. From our analysis, the reflected intensity profile recorded appears to deviate from Gaussian model which is commonly assumed and can be perceived as a mixture of noises and actual reflected signal. Noise-weighted Average range calculation is therefore proposed to alleviate noise influence based on the signal detection threshold and system noises. From our experimental result, this alternative range solution demonstrates better accuracy as compared to the conventional weighted average method and proven as a para-axial correction to improve range reconstruction in 3D gated imaging system.

5 September 2017 in Sensors
Verified
Journal Article
Open access
PDF file
SCSing Yee Chua
Sing Yee Chua
NGNingqun Guo
Ningqun Guo
CTCS Tan
CS Tan
Xin WangXin Wang
Xin Wang
Accuracy is an important measure of system performance and remains a challenge in 3D range gated reconstruction despite the advancement in laser and sensor technology. The weighted average model that is commonly used for range estimation is heavily influenced by the intensity variation due to various factors. Accuracy improvement in term of range estimation is therefore important to fully optimise the system performance. In this paper, a 3D range gated reconstruction model is derived based on the operating principles of range gated imaging and time slicing reconstruction, fundamental of radiant energy, Laser Detection And Ranging (LADAR), and Bidirectional Reflection Distribution Function (BRDF). Accordingly, a new range estimation model is proposed to alleviate the effects induced by distance, target reflection, and range distortion. From the experimental results, the proposed model outperforms the conventional weighted average model to improve the range estimation for better 3D reconstruction. The outcome demonstrated is of interest to various laser ranging applications and can be a reference for future works.

23 December 2015 in Applied Optics
Verified
Journal Article
Closed access
PDF file
SCSing Yee Chua
Sing Yee Chua
Xin WangXin Wang
Xin Wang
NGNingqun Guo
Ningqun Guo
CTChing Seong Tan
Ching Seong Tan
Range determination has crucial dependency of intensity over distance due to the fact that output of a range gated system is the reflectivity and range information expressed in term of intensity. From our experimental study, the analyzed trend line of reflected intensity versus range agrees with the theoretical model where it underlies an inverse range-squared dependency. Considering the energy attenuation factor for a better three-dimensional (3D) solution, a range compensation model is derived based on time slicing technique to compensate the effect imposed by distance beyond an optimum range. A range gated imaging system with pulse profile feedback is proposed in order to apply the range compensation model. Experimental results show noticeable improvement as compared to the conventional weighted average method for reflected laser pulse data across different ranges and 3D surface reconstruction using the proposed range compensation model.

8 September 2021 in Journal of Signal Processing Systems
Verified
Journal Article
Closed access
PDF file
ZSZhenyong Shin
Zhenyong Shin
TCTong Yuen Chai
Tong Yuen Chai
CPChang Hong Pua
Chang Hong Pua
Xin WangXin Wang
Xin Wang
SCSing Yee Chua
Sing Yee Chua

1 January 2024 in Journal of Communications Software and Systems
Verified
Journal Article
Open access
PDF file
NTNathaniel Yang Tan
Nathaniel Yang Tan
MTMau-Luen Tham
Mau-Luen Tham
SCSing Chua
Sing Chua
YLYing Loong Lee
Ying Loong Lee
Catastrophic occurrences induced by disasters often lead to fatalities, extensive damage, and societal disruptions. In pursuit of realizing disaster-resilient smart cities, video surveillance systems incorporating artificial intelligence (AI) can automatically process and classify the disaster content in real-time. This advancement is fueled by the recent progress in computer vision and AI algorithms, specifically deep learning neural networks, which can be leveraged for disaster categorization tasks. However, minimizing the complexity of AI models while preserving accurate disaster classification remains a formidable challenge. In this paper, we propose a convolutional neural network-long short-term memory (CNN-LSTM) model capable of discerning four types of natural disasters and a non-disaster event. Contrary to prior research that treats input video as a sequence of independent frames, we demonstrate the significance of spatio-temporal characteristics in reaping high prediction accuracy. Furthermore, conventional methods rely on resource-intensive hardware to boost AI model performance, which may not suit real-time monitoring. To facilitate real-time disaster monitoring applications, the trained model is further optimized by utilizing a neural network acceleration platform known as OpenVINO. Our findings reveal that the optimized version of the proposed CNN-LSTM model sustains 100% accuracy while boosting throughput by 25% in terms of frames per second (FPS).

11 August 2016 in Applied Optics
Verified
Journal Article
Closed access
PDF file
SCSing Yee Chua
Sing Yee Chua
Xin WangXin Wang
Xin Wang
NGNingqun Guo
Ningqun Guo
CTChing Seong Tan
Ching Seong Tan
The range gated technique is a promising laser ranging method that is widely used in different fields such as surveillance, industry, and military. In a range gated system, a reflected laser pulse returned from the target scene contains key information for range reconstruction, which directly affects the system performance. Therefore, it is necessary to study the characteristics and effects of the target reflection factor. In this paper, theoretical and experimental analyses are performed to investigate the influence of target reflection on three-dimensional (3D) range gated reconstruction. Based on laser detection and ranging (LADAR) and bidirectional reflection distribution function (BRDF) theory, a 3D range gated reconstruction model is derived and the effect on range accuracy is analyzed from the perspectives of target surface reflectivity and angle of laser incidence. Our theoretical and experimental study shows that the range accuracy is proportional to the target surface reflectivity, but it decreases when the angle of incidence increases to adhere to the BRDF model. The presented findings establish a comprehensive understanding of target reflection in 3D range gated reconstruction, which is of interest to various applications such as target recognition and object modeling. This paper provides a reference for future improvement to perform accurate range compensation or correction.