Ali Aghagolzadeh
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
Ali Aghagolzadeh has a total of 125 co-authors. Here are the top co-authors by number of shared publications:
- Hadi Seyedarabi
Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran
27 shared publications - Mostafa Amin Naji
Department of Health Technology, Center for Fast Ultrasound Imaging, Technical University of Denmark, Lyngby, Denmark
8 shared publications - Mehdi Ezoji
Faculty of Electrical and Computer Engineering, Babol Noshirvani University of Technology, Babol, Iran
7 shared publications Mehdi Ezoji
Faculty of Electrical and Computer Engineering, Babol Noshirvani University of Technology, Babol, Iran
6 shared publications- Nasser Eslahi
Faculty of Electrical and Computer Engineering, Babol University of Technology, Babol, Iran
6 shared publications - Seyed Mehdi Hosseini Andargoli
Electrical and Computer Engineering Faculty, Babol Noshirvani University of Technology, Babol, Iran
6 shared publications
Latest Publications
- 1 July 2025
- Published byĀ SPIE-Intl Soc Optical EngĀ inĀ Journal of Applied Remote Sensing
- Vol.Ā 19 Ā (03) , 038504-18
Triple-discriminator generative adversarial network with structural enhancement for unsupervised remote sensing image pansharpening
It is our goal to address the challenge of fusing satellite images. The currently available pansharpening models fail to strike a balance between clear boundaries and rich spatialāspectral details. We propose an unsupervised remote sensing image pansharpening model based on a triple-discriminator generative adversarial network (TDP-GAN) that combines low-resolution multispectral (LRMS), panchromatic (PAN), and structural gradient (SG) images. This is the first attempt to produce pansharpened images using triple-discriminator adversarial networks. TDP-GAN trains directly on full-resolution images without downsampling and achieves the balance. First, the SG image is generated by superposition of the structural information in the horizontal and vertical directions from the PAN image using the first-order forward differential operator. Then, we input SG images along with PAN and LRMS images into the multistream generator. Finally, a special nonreference loss function is designed to improve image generation effects by reducing the loss of spatial structural information and spectral detail in generated images. The proposed model can optimize training processes, accelerate network convergence, and deepen the gradient information exchange between the generator and discriminators. Experiments conducted on publicly available datasets show that TDP-GAN performs better than state-of-the-art methods on both quantitative and qualitative metrics.
- 1 July 2025
- Published byĀ SPIE-Intl Soc Optical EngĀ inĀ Journal of Applied Remote Sensing
- Vol.Ā 19 Ā (03) , 038504-18
Triple-discriminator generative adversarial network with structural enhancement for unsupervised remote sensing image pansharpening
It is our goal to address the challenge of fusing satellite images. The currently available pansharpening models fail to strike a balance between clear boundaries and rich spatialāspectral details. We propose an unsupervised remote sensing image pansharpening model based on a triple-discriminator generative adversarial network (TDP-GAN) that combines low-resolution multispectral (LRMS), panchromatic (PAN), and structural gradient (SG) images. This is the first attempt to produce pansharpened images using triple-discriminator adversarial networks. TDP-GAN trains directly on full-resolution images without downsampling and achieves the balance. First, the SG image is generated by superposition of the structural information in the horizontal and vertical directions from the PAN image using the first-order forward differential operator. Then, we input SG images along with PAN and LRMS images into the multistream generator. Finally, a special nonreference loss function is designed to improve image generation effects by reducing the loss of spatial structural information and spectral detail in generated images. The proposed model can optimize training processes, accelerate network convergence, and deepen the gradient information exchange between the generator and discriminators. Experiments conducted on publicly available datasets show that TDP-GAN performs better than state-of-the-art methods on both quantitative and qualitative metrics.
- Open Access
- 1 May 2025
- Published byĀ International Digital Organization for Scientific Information (IDOSI)Ā inĀ International Journal of Engineering
- Vol.Ā 38 Ā (5) , 1042-1055
Super-resolution Augmentation of Large Images with Architecture Treatment of Deeply Recursive Convolutional Network
Modifications in the architecture of deeply recursive convolutional networks (DRCN) are implemented and modified DRCN (MDRCN) is introduced to attain super-resolution (SR) in relatively large images (256Ć256) and RGB space. Identical components with the expressed baseline (including the embedding, inference, and reconstruction steps) are utilized in this research. The reconstruction stage is divided into two parts: a) Concat. A and b) Concat. B. A particular number of the Div2k and Yang T91 images (891) are utilized in the training phase. High-resolution (HR) and low-resolution (LR) images have been created with bicubic interpolation in the training and test phases. Datasets of Set5, Set14, B100, and Urban100 are used for the testing phase. The criteria of PSNR and SSIM are utilized to examine the attained results in the testing phase that have improved in MDRCN relative to the investigated algorithms in 2Ć scaling and all datasets. The amounts of these criteria significantly were improved in MDRCN by augmenting the scaling factor to 4Ć, especially in the Urban100 dataset. According to the observed outcomes, it can be concluded that MDRCN has proper efficiency in the low-scaling compared to the intended models.
- 1 May 2025
- Published byĀ International Digital Organization for Scientific Information (IDOSI)Ā inĀ International Journal of Engineering
- Vol.Ā 38 Ā (5) , 1042-1055
Open AccessSuper-resolution Augmentation of Large Images with Architecture Treatment of Deeply Recursive Convolutional Network
Modifications in the architecture of deeply recursive convolutional networks (DRCN) are implemented and modified DRCN (MDRCN) is introduced to attain super-resolution (SR) in relatively large images (256Ć256) and RGB space. Identical components with the expressed baseline (including the embedding, inference, and reconstruction steps) are utilized in this research. The reconstruction stage is divided into two parts: a) Concat. A and b) Concat. B. A particular number of the Div2k and Yang T91 images (891) are utilized in the training phase. High-resolution (HR) and low-resolution (LR) images have been created with bicubic interpolation in the training and test phases. Datasets of Set5, Set14, B100, and Urban100 are used for the testing phase. The criteria of PSNR and SSIM are utilized to examine the attained results in the testing phase that have improved in MDRCN relative to the investigated algorithms in 2Ć scaling and all datasets. The amounts of these criteria significantly were improved in MDRCN by augmenting the scaling factor to 4Ć, especially in the Urban100 dataset. According to the observed outcomes, it can be concluded that MDRCN has proper efficiency in the low-scaling compared to the intended models.
- 25 July 2024
- Published byĀ Springer NatureĀ inĀ Multimedia Tools and Applications
- Vol.Ā 84 Ā (19) , 20917-20942
Camera management in wireless visual sensor networks based on a quality aware resource allocation scheme
- 25 July 2024
- Published byĀ Springer NatureĀ inĀ Multimedia Tools and Applications
- Vol.Ā 84 Ā (19) , 20917-20942
Camera management in wireless visual sensor networks based on a quality aware resource allocation scheme
- Open Access
- 9 July 2024
- Published byĀ Springer NatureĀ inĀ Journal of Intelligent & Robotic Systems
- Vol.Ā 110 Ā (3) , 1-15
Stereo-RIVO: Stereo-Robust Indirect Visual Odometry
Mobile robots and autonomous systems rely on advanced guidance modules which often incorporate cameras to enable key functionalities. These modules are equipped with visual odometry (VO) and visual simultaneous localization and mapping (VSLAM) algorithms that work by analyzing changes between successive frames captured by cameras. VO/VSLAM-based systems are critical backbones for autonomous vehicles, virtual reality, structure from motion, and other robotic operations. VO/VSLAM systems encounter difficulties when implementing real-time applications in outdoor environments with restricted hardware and software platforms. While many VO systems target achieving high accuracy and speed, they often exhibit high degree of complexity and limited robustness. To overcome these challenges, this paper aims to propose a new VO system called Stereo-RIVO that balances accuracy, speed, and computational cost. Furthermore, this algorithm is based on a new data association module which consists of two primary components: a scene-matching process that achieves exceptional precision without feature extraction and a key-frame detection technique based on a model of scene movement. The performance of this proposed VO system has been tested extensively for all sequences of KITTI and UTIAS datasets for analyzing efficiency for outdoor dynamic and indoor static environments, respectively. The results of these tests indicate that the proposed Stereo-RIVO outperforms other state-of-the-art methods in terms of robustness, accuracy, and speed. Our implementation code of stereo-RIVO is available at: https://github.com/salehierfan/Stereo-RIVO.
- 9 July 2024
- Published byĀ Springer NatureĀ inĀ Journal of Intelligent & Robotic Systems
- Vol.Ā 110 Ā (3) , 1-15
Open AccessStereo-RIVO: Stereo-Robust Indirect Visual Odometry
Mobile robots and autonomous systems rely on advanced guidance modules which often incorporate cameras to enable key functionalities. These modules are equipped with visual odometry (VO) and visual simultaneous localization and mapping (VSLAM) algorithms that work by analyzing changes between successive frames captured by cameras. VO/VSLAM-based systems are critical backbones for autonomous vehicles, virtual reality, structure from motion, and other robotic operations. VO/VSLAM systems encounter difficulties when implementing real-time applications in outdoor environments with restricted hardware and software platforms. While many VO systems target achieving high accuracy and speed, they often exhibit high degree of complexity and limited robustness. To overcome these challenges, this paper aims to propose a new VO system called Stereo-RIVO that balances accuracy, speed, and computational cost. Furthermore, this algorithm is based on a new data association module which consists of two primary components: a scene-matching process that achieves exceptional precision without feature extraction and a key-frame detection technique based on a model of scene movement. The performance of this proposed VO system has been tested extensively for all sequences of KITTI and UTIAS datasets for analyzing efficiency for outdoor dynamic and indoor static environments, respectively. The results of these tests indicate that the proposed Stereo-RIVO outperforms other state-of-the-art methods in terms of robustness, accuracy, and speed. Our implementation code of stereo-RIVO is available at: https://github.com/salehierfan/Stereo-RIVO.
- Open Access
Accuracy Improvement in Differentially Private Logistic Regression: A Pre-training Approach
Machine learning (ML) models can memorize training datasets. As a result, training ML models over private datasets can lead to the violation of individuals' privacy. Differential privacy (DP) is a rigorous privacy notion to preserve the privacy of underlying training datasets. Yet, training ML models in a DP framework usually degrades the accuracy of ML models. This paper aims to boost the accuracy of a DP logistic regression (LR) via a pre-training module. In more detail, we initially pre-train our LR model on a public training dataset that there is no privacy concern about it. Then, we fine-tune our DP-LR model with the private dataset. In the numerical results, we show that adding a pre-training module significantly improves the accuracy of the DP-LR model.
Open AccessAccuracy Improvement in Differentially Private Logistic Regression: A Pre-training Approach
Machine learning (ML) models can memorize training datasets. As a result, training ML models over private datasets can lead to the violation of individuals' privacy. Differential privacy (DP) is a rigorous privacy notion to preserve the privacy of underlying training datasets. Yet, training ML models in a DP framework usually degrades the accuracy of ML models. This paper aims to boost the accuracy of a DP logistic regression (LR) via a pre-training module. In more detail, we initially pre-train our LR model on a public training dataset that there is no privacy concern about it. Then, we fine-tune our DP-LR model with the private dataset. In the numerical results, we show that adding a pre-training module significantly improves the accuracy of the DP-LR model.
- 26 December 2023
- Published byĀ Springer NatureĀ inĀ Signal, Image and Video Processing
- Vol.Ā 18 Ā (3) , 1983-1991
Gaussian mixture-based generative approach for H.265/HEVC error concealment
- 26 December 2023
- Published byĀ Springer NatureĀ inĀ Signal, Image and Video Processing
- Vol.Ā 18 Ā (3) , 1983-1991
Gaussian mixture-based generative approach for H.265/HEVC error concealment
- 11 December 2023
- Published byĀ Springer NatureĀ inĀ The Visual Computer
- Vol.Ā 40 Ā (9) , 5901-5919
Stereo-RSSF: stereo robust sparse scene-flow estimation
- 11 December 2023
- Published byĀ Springer NatureĀ inĀ The Visual Computer
- Vol.Ā 40 Ā (9) , 5901-5919
Stereo-RSSF: stereo robust sparse scene-flow estimation
- 28 August 2023
- Published byĀ Springer NatureĀ inĀ Multimedia Tools and Applications
- Vol.Ā 83 Ā (9) , 26107-26130
Low rank and sparse decomposition based on extended ${LL}_{p}$ norm- 28 August 2023
- Published byĀ Springer NatureĀ inĀ Multimedia Tools and Applications
- Vol.Ā 83 Ā (9) , 26107-26130
Low rank and sparse decomposition based on extended ${LL}_{p}$ norm- 5 August 2023
- Published byĀ Springer NatureĀ inĀ Multimedia Tools and Applications
- Vol.Ā 83 Ā (7) , 20997-21017
PCA-based hierarchical clustering approach for motion vector estimation in H.265/HEVC video error concealment
- 5 August 2023
- Published byĀ Springer NatureĀ inĀ Multimedia Tools and Applications
- Vol.Ā 83 Ā (7) , 20997-21017
PCA-based hierarchical clustering approach for motion vector estimation in H.265/HEVC video error concealment
- 17 April 2022
- Published byĀ Springer NatureĀ inĀ Pattern Analysis and Applications
- Vol.Ā 25 Ā (4) , 773-793
Mutual neighborhood and modified majority voting based KNN classifier for multi-categories classification
- 17 April 2022
- Published byĀ Springer NatureĀ inĀ Pattern Analysis and Applications
- Vol.Ā 25 Ā (4) , 773-793
Mutual neighborhood and modified majority voting based KNN classifier for multi-categories classification