Shah Ariful Hoque Chowdhury
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shah Ariful Hoque Chowdhury has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Richard Hartley
Australian National University, Australia
2 shared publications Al-Hadith Moon
Department of Electrical and Electronic Engineering, Rajshahi University of Engineering and Technology, Rajshahi, Bangladesh
1 shared publication- Chuong Nguyen
Australian National University 1 Data61 CSIRO
1 shared publication D. K. Mondal
Dept. of Electronics & Telecommunication Engineering, Rajshahi University of Engineering & Technology, 6204, Bangladesh
1 shared publication- Hengjia Li
University College London, London, England
1 shared publication - Hongdong Li
School of Computing, Australian National University, Canberra, Australia
1 shared publication
Latest Publications
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 11314-11330
Weakly-Supervised Depth Estimation and Image Deblurring via Dual-Pixel Sensors
Dual-pixel (DP) imaging sensors are getting more popularly adopted by modern cameras. A DP camera captures a pair of images in a single snapshot by splitting each pixel in half. Several previous studies show how to recover depth information by treating the DP pair as an approximate stereo pair. However, dual-pixel disparity occurs only in image regions with defocus blur which is unlike classic stereo disparity. Heavy defocus blur in DP pairs affects the performance of depth estimation approaches based on matching. Therefore, we treat the blur removal and the depth estimation as a joint problem. We investigate the formation of the DP pair, which links the blur and depth information, rather than blindly removing the blur effect. We propose a mathematical DP model that can improve depth estimation by the blur. This exploration motivated us to propose our previous work, an end-to-end DDDNet (DP-based Depth and Deblur Network), which jointly estimates depth and restores the image in a supervised fashion. However, collecting the ground-truth (GT) depth map for the DP pair is challenging and limits the depth estimation potential of the DP sensor. Therefore, we propose an extension of the DDDNet, called WDDNet (Weakly-supervised Depth and Deblur Network), which includes an efficient reblur solver that does not require GT depth maps for training. To achieve this, we convert all-in-focus images into supervisory signals for unsupervised depth estimation in our WDDNet. We jointly estimate an all-in-focus image and a disparity map, then use a Reblur and Fstack module to regularize the disparity estimation and image restoration. We conducted extensive experiments on synthetic and real data to demonstrate the competitive performance of our method when compared to state-of-the-art (SOTA) supervised approaches.
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 11314-11330
Weakly-Supervised Depth Estimation and Image Deblurring via Dual-Pixel Sensors
Dual-pixel (DP) imaging sensors are getting more popularly adopted by modern cameras. A DP camera captures a pair of images in a single snapshot by splitting each pixel in half. Several previous studies show how to recover depth information by treating the DP pair as an approximate stereo pair. However, dual-pixel disparity occurs only in image regions with defocus blur which is unlike classic stereo disparity. Heavy defocus blur in DP pairs affects the performance of depth estimation approaches based on matching. Therefore, we treat the blur removal and the depth estimation as a joint problem. We investigate the formation of the DP pair, which links the blur and depth information, rather than blindly removing the blur effect. We propose a mathematical DP model that can improve depth estimation by the blur. This exploration motivated us to propose our previous work, an end-to-end DDDNet (DP-based Depth and Deblur Network), which jointly estimates depth and restores the image in a supervised fashion. However, collecting the ground-truth (GT) depth map for the DP pair is challenging and limits the depth estimation potential of the DP sensor. Therefore, we propose an extension of the DDDNet, called WDDNet (Weakly-supervised Depth and Deblur Network), which includes an efficient reblur solver that does not require GT depth maps for training. To achieve this, we convert all-in-focus images into supervisory signals for unsupervised depth estimation in our WDDNet. We jointly estimate an all-in-focus image and a disparity map, then use a Reblur and Fstack module to regularize the disparity estimation and image restoration. We conducted extensive experiments on synthetic and real data to demonstrate the competitive performance of our method when compared to state-of-the-art (SOTA) supervised approaches.
- Open Access
- 7 March 2024
- Published by Science Publishing Group in American Journal of Networks and Communications
- Vol. 13 (1) , 64-74
Trajectory Optimization and Power Allocation Scheme for a UAV Relay-aided Network in the Presence of an Eavesdropper
The information theoretical security for a cellular network in the presence of an eavesdropper is investigated in this research. The network is single-input-single-output (SISO) in nature. A small unmanned aerial vehicle (UAV) is aiding the network as a relay that follows the decode-and-forward (DF) protocol. The relay decodes the transmitted signal and retransmits it to the destination while repositioning itself if required. The allotted power of the UAV may not be enough for long-distance and long-duration travel. This article deals with the power needed for the data transmission so that the UAV can operate as a relay with less transmit power. However, the confidential data transmission between a base station and a mobile device is being intercepted by a passive eavesdropper. The security issue affects the transmit power and the outage situation. The theory of physical layer security is employed to ensure a secure wireless transmission. The secrecy parameters, namely, the secrecy capacity and the secrecy outage probability are investigated via mathematical derivations and computer programming. Additionally, optimizing the trajectory and allocation of the transmit power budget of the UAV will increase the network’s reliability. Our results show that the UAV relay can handle a secure transmission with its limited resources if a budget power allocation can be achieved along with an optimized trajectory.
- 7 March 2024
- Published by Science Publishing Group in American Journal of Networks and Communications
- Vol. 13 (1) , 64-74
Open AccessTrajectory Optimization and Power Allocation Scheme for a UAV Relay-aided Network in the Presence of an Eavesdropper
The information theoretical security for a cellular network in the presence of an eavesdropper is investigated in this research. The network is single-input-single-output (SISO) in nature. A small unmanned aerial vehicle (UAV) is aiding the network as a relay that follows the decode-and-forward (DF) protocol. The relay decodes the transmitted signal and retransmits it to the destination while repositioning itself if required. The allotted power of the UAV may not be enough for long-distance and long-duration travel. This article deals with the power needed for the data transmission so that the UAV can operate as a relay with less transmit power. However, the confidential data transmission between a base station and a mobile device is being intercepted by a passive eavesdropper. The security issue affects the transmit power and the outage situation. The theory of physical layer security is employed to ensure a secure wireless transmission. The secrecy parameters, namely, the secrecy capacity and the secrecy outage probability are investigated via mathematical derivations and computer programming. Additionally, optimizing the trajectory and allocation of the transmit power budget of the UAV will increase the network’s reliability. Our results show that the UAV relay can handle a secure transmission with its limited resources if a budget power allocation can be achieved along with an optimized trajectory.
- 6 April 2021
- Published by Springer Nature in Neural Computing and Applications
- Vol. 33 (13) , 7421-7440
Fixed-Lens camera setup and calibrated image registration for multifocus multiview 3D reconstruction
- 6 April 2021
- Published by Springer Nature in Neural Computing and Applications
- Vol. 33 (13) , 7421-7440
Fixed-Lens camera setup and calibrated image registration for multifocus multiview 3D reconstruction
- 1 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 14, 99-102
Cross-correlation based approach of underwater network size estimation with unequal sensor separation
It is very difficult to estimate the number and location of the operational nodes in underwater network using conventional protocol based techniques due to long propagation delay, strong background noise, non-negligible capture effect, high absorption and dispersion of underwater environment. So, a unique approach based on cross-correlation is applied for underwater network size estimation. In three-sensor case of this approach, network size is obtained by cross-corelating the Gaussian signals received at equidistant pair of sensors. The assumption of equidistant sensors poses some limitations and requires further investigation. The aim of this work is to obtain a more flexible estimation process by removing this assumption. For this purpose, three-sensor case of cross-correlation based underwater network size estimation technique is investigated in this paper with unequal sensor separation.
- 1 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 14, 99-102
Cross-correlation based approach of underwater network size estimation with unequal sensor separation
It is very difficult to estimate the number and location of the operational nodes in underwater network using conventional protocol based techniques due to long propagation delay, strong background noise, non-negligible capture effect, high absorption and dispersion of underwater environment. So, a unique approach based on cross-correlation is applied for underwater network size estimation. In three-sensor case of this approach, network size is obtained by cross-corelating the Gaussian signals received at equidistant pair of sensors. The assumption of equidistant sensors poses some limitations and requires further investigation. The aim of this work is to obtain a more flexible estimation process by removing this assumption. For this purpose, three-sensor case of cross-correlation based underwater network size estimation technique is investigated in this paper with unequal sensor separation.