Sankha Deb
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sankha Deb has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Debashis Sen
Indian Institute of Technology Kharagpur
5 shared publications - Sainul Islam Ansary
Institute of Robotics and Machine Intelligence, Poznan University of Technology, Pozna, Poland
5 shared publications - Sudipta Bhuyan
Department of Mechanical Engineering, Advanced Technology Development Centre, Indian Institute of Technology at Kharagpur, Kharagpur, West Bengal, India
4 shared publications - Alok Kanti Deb
Department of Electrical Engineering, IIT Kharagur, Kharagpur-721302, India
3 shared publications - Suman Saha
Pennsylvania State University, University Park, PA, USA
3 shared publications Atul Mishra
IIT Kharagpur
2 shared publications
Latest Publications
- 31 March 2026
- Published by Springer Nature in Intelligent Service Robotics
- Vol. 19 (3) , 52
Occlusion-resilient pose estimation of textureless components in cluttered environment and its implementation in robotic bin-picking
- 31 March 2026
- Published by Springer Nature in Intelligent Service Robotics
- Vol. 19 (3) , 52
Occlusion-resilient pose estimation of textureless components in cluttered environment and its implementation in robotic bin-picking
- 4 September 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (22) , 25865-25894
A framework for robotic grasping of 3D objects in a tabletop environment
- 4 September 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (22) , 25865-25894
A framework for robotic grasping of 3D objects in a tabletop environment
- 6 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (16) , 25879-25890
Consistent Features From Varied Contexts and Ordered Multiple Attention Forms for RGB-D Salient Object Detection
Attention-based fusion and sophisticated multi-modal feature extraction are the key components of many state-of-the-art RGB-D salient object detection (SOD) methods. In this regard, different forms of attention providing a variety of emphasis during fusion in an appropriate order, and extraction of consistent features at multiple levels from a variety of contexts can be leveraged to improve the SOD performance further. To this end, this paper proposes an RGB-D SOD technique that learns multi-level features considering a variety of local and global contexts along with long-range dependencies. The learning also involves consistency evaluation of saliency features from pixel to region level using cascaded capsule networks to facilitate faithful preservation of intricate salient object details. The fusion of multi-modal features leading to the SOD is performed using cross-modal interactions through multiple attention forms ordered in a favorable way. Quantitative and qualitative experimental results using multiple standard datasets and measures demonstrate the effectiveness of the proposed SOD framework in comparison with the state-of-the-art. An ablation study establishes the utility of the various components of the proposed approach.
- 6 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (16) , 25879-25890
Consistent Features From Varied Contexts and Ordered Multiple Attention Forms for RGB-D Salient Object Detection
Attention-based fusion and sophisticated multi-modal feature extraction are the key components of many state-of-the-art RGB-D salient object detection (SOD) methods. In this regard, different forms of attention providing a variety of emphasis during fusion in an appropriate order, and extraction of consistent features at multiple levels from a variety of contexts can be leveraged to improve the SOD performance further. To this end, this paper proposes an RGB-D SOD technique that learns multi-level features considering a variety of local and global contexts along with long-range dependencies. The learning also involves consistency evaluation of saliency features from pixel to region level using cascaded capsule networks to facilitate faithful preservation of intricate salient object details. The fusion of multi-modal features leading to the SOD is performed using cross-modal interactions through multiple attention forms ordered in a favorable way. Quantitative and qualitative experimental results using multiple standard datasets and measures demonstrate the effectiveness of the proposed SOD framework in comparison with the state-of-the-art. An ablation study establishes the utility of the various components of the proposed approach.
- 12 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (7) , 3638-3652
RGB-D Fusion Through Zero-Shot Fuzzy Membership Learning for Salient Object Detection
Significant improvement has been achieved lately in color and depth data based salient object detection on images from varied datasets, which is mainly due to RGB-D 1 1RGB-D represents Color-Depth. fusion using modern machine learning techniques. However, little emphasis has been given recently on performing RGB-D fusion for salient object detection in the absence of ground truth data for training. This paper proposes a zero-shot deep RGB-D fusion approach based on the novel concept of fuzzy membership learning, which does not require any data for training. The constituent salient object maps to be fused are represented using parametric fuzzy membership functions and the optimal parameter values are estimated through our zero-shot fuzzy membership learning (Z-FML) network. The optimal parameter values are used in a fuzzy inference system along with the constituent salient object maps to perform the fusion. A measure called the membership similarity measure (MSM) is proposed, and the Z-FML network is trained using it to devise a loss function that maximizes the similarity between the constituent salient object maps and the fused salient object map. The deduction of MSM and its properties are shown theoretically, and the gradients involved in the training of the Z-FML network are derived. Qualitative and quantitative evaluations using several datasets signify the effectiveness of our RGB-D fusion and our fusion based RGBD salient object detection in comparison to the state-of-the-art. We also empirically demonstrate the advantage of employing the novel MSM for training our Z-FML network.
- 12 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (7) , 3638-3652
RGB-D Fusion Through Zero-Shot Fuzzy Membership Learning for Salient Object Detection
Significant improvement has been achieved lately in color and depth data based salient object detection on images from varied datasets, which is mainly due to RGB-D 1 1RGB-D represents Color-Depth. fusion using modern machine learning techniques. However, little emphasis has been given recently on performing RGB-D fusion for salient object detection in the absence of ground truth data for training. This paper proposes a zero-shot deep RGB-D fusion approach based on the novel concept of fuzzy membership learning, which does not require any data for training. The constituent salient object maps to be fused are represented using parametric fuzzy membership functions and the optimal parameter values are estimated through our zero-shot fuzzy membership learning (Z-FML) network. The optimal parameter values are used in a fuzzy inference system along with the constituent salient object maps to perform the fusion. A measure called the membership similarity measure (MSM) is proposed, and the Z-FML network is trained using it to devise a loss function that maximizes the similarity between the constituent salient object maps and the fused salient object map. The deduction of MSM and its properties are shown theoretically, and the gradients involved in the training of the Z-FML network are derived. Qualitative and quantitative evaluations using several datasets signify the effectiveness of our RGB-D fusion and our fusion based RGBD salient object detection in comparison to the state-of-the-art. We also empirically demonstrate the advantage of employing the novel MSM for training our Z-FML network.
- 4 December 2023
- Published by Springer Nature
- p. 523-531
RGB-D Fusion Based on Fuzzy Optimization for Salient Object Detection
- 4 December 2023
- Published by Springer Nature
- p. 523-531
RGB-D Fusion Based on Fuzzy Optimization for Salient Object Detection
- 31 August 2023
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 109 (1) , 1-21
Design and Development of an Adaptive Robotic Gripper
- 31 August 2023
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 109 (1) , 1-21
Design and Development of an Adaptive Robotic Gripper
- 31 December 2022
- Published by Elsevier in International Journal of Mechanical Sciences
- Vol. 245
Tool wear induced burr formation and concomitant reduction in MQL wetting capability in micro-milling
- 31 December 2022
- Published by Elsevier in International Journal of Mechanical Sciences
- Vol. 245
Tool wear induced burr formation and concomitant reduction in MQL wetting capability in micro-milling
- 13 September 2022
- Published by Springer Nature
- p. 119-128
Dependency of Machining Forces on Process Parameters During Sustainable MQL-Based Micro-milling of D2 Steel
- 13 September 2022
- Published by Springer Nature
- p. 119-128
Dependency of Machining Forces on Process Parameters During Sustainable MQL-Based Micro-milling of D2 Steel