Kavinder Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kavinder Singh has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Anil Singh Parihar
Machine Learning Research Laboratory, Department of Computer Science and Engineering, Delhi Technological University, Delhi, India
7 shared publications Anil Singh Parihar
3 shared publicationsAshutosh Pandey
Machine Learning Research Laboratory, Department of Computer Science and Engineering, Delhi Technological University, Delhi, India
1 shared publicationGul Asnani
Department of Computer Science and Engineering Delhi Technological University Bawana New Delhi India
1 shared publicationHasnat Hosen Arafat
1 shared publication- Hasnat Hosen Arafat
Machine Learning Research Laboratory, Department of Computer Science and Engineering, Delhi Technological University, Delhi, India
1 shared publication
Latest Publications
- 13 March 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 173
Frame-wise Learned Offset Network with localized loss for video summarization
- 13 March 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 173
Frame-wise Learned Offset Network with localized loss for video summarization
- 22 May 2025
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 110
QLight-Net: Quaternion based low light image enhancement network
- 22 May 2025
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 110
QLight-Net: Quaternion based low light image enhancement network
- 18 March 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41 (11) , 8219-8234
Capturing spatiotemporal dependencies with competitive set attention for video summarization
- 18 March 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41 (11) , 8219-8234
Capturing spatiotemporal dependencies with competitive set attention for video summarization
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (1) , 378-389
Uncertainty and Noise Aware Decision Making for Autonomous Vehicles: A Bayesian Approach
In the evolving domain of autonomous vehicles, the importance of decision-making cannot be overstated. Deep Reinforcement Learning (DRL) emerges as a pivotal tool in this landscape. However, existing DRL algorithms suffer from inaccurate Q-value estimation, predominantly due to system noise and function approximation errors. This coupled with real-world unpredictabilities, often misdirects autonomous vehicles, leading to sub-optimal actions and safety hazards. This work introduces a novel DRL algorithm tailored for uncertainty and noise-aware decision-making in autonomous vehicles. Our approach harnesses Bayesian Neural Networks and skew-geometric Jensen-Shannon divergence, to rectify the aforementioned limitations. Evaluated on the OpenAI gymnasium environment, our algorithm has clear advantages over existing methods in terms of cumulative rewards and convergence speed.
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (1) , 378-389
Uncertainty and Noise Aware Decision Making for Autonomous Vehicles: A Bayesian Approach
In the evolving domain of autonomous vehicles, the importance of decision-making cannot be overstated. Deep Reinforcement Learning (DRL) emerges as a pivotal tool in this landscape. However, existing DRL algorithms suffer from inaccurate Q-value estimation, predominantly due to system noise and function approximation errors. This coupled with real-world unpredictabilities, often misdirects autonomous vehicles, leading to sub-optimal actions and safety hazards. This work introduces a novel DRL algorithm tailored for uncertainty and noise-aware decision-making in autonomous vehicles. Our approach harnesses Bayesian Neural Networks and skew-geometric Jensen-Shannon divergence, to rectify the aforementioned limitations. Evaluated on the OpenAI gymnasium environment, our algorithm has clear advantages over existing methods in terms of cumulative rewards and convergence speed.
- 23 January 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (4) , 3097-3107
Bff: Bi-stream feature fusion for object detection in hazy environment
- 23 January 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (4) , 3097-3107
Bff: Bi-stream feature fusion for object detection in hazy environment
- 17 January 2023
- Published by Springer Nature in The Visual Computer
- Vol. 40 (1) , 121-136
Illumination estimation for nature preserving low-light image enhancement
- 17 January 2023
- Published by Springer Nature in The Visual Computer
- Vol. 40 (1) , 121-136
Illumination estimation for nature preserving low-light image enhancement
- 1 August 2021
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 79
Variational optimization based single image dehazing
- 1 August 2021
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 79
Variational optimization based single image dehazing
- Open Access
- 24 December 2020
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 15 (7) , 1410-1423
Fusion‐based simultaneous estimation of reflectance and illumination for low‐light image enhancement
Low‐light image enhancement is a challenging field in image processing. Retinex‐based methods perform well for low‐light images. However, reflectance and illumination estimation is an ill‐posed problem. This paper presents a new framework for the simultaneous estimation of reflectance and illumination for low‐light image enhancement. The algorithm estimates multiple instances of illumination and reflectance and blends them to estimate the final components. The proposed approach uses multi‐scale fusion for illumination estimation and naive fusion for reflectance estimation. Extensive experimentation and analysis with a large set of low‐light images validates the performance of the proposed approach. The comparison shows the superiority of the proposed approach over most of the existing low‐light image enhancement methods. The proposed method provides colour constancy in low‐light image enhancement and preserves the naturalness of the image.
- 24 December 2020
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 15 (7) , 1410-1423
Open AccessFusion‐based simultaneous estimation of reflectance and illumination for low‐light image enhancement
Low‐light image enhancement is a challenging field in image processing. Retinex‐based methods perform well for low‐light images. However, reflectance and illumination estimation is an ill‐posed problem. This paper presents a new framework for the simultaneous estimation of reflectance and illumination for low‐light image enhancement. The algorithm estimates multiple instances of illumination and reflectance and blends them to estimate the final components. The proposed approach uses multi‐scale fusion for illumination estimation and naive fusion for reflectance estimation. Extensive experimentation and analysis with a large set of low‐light images validates the performance of the proposed approach. The comparison shows the superiority of the proposed approach over most of the existing low‐light image enhancement methods. The proposed method provides colour constancy in low‐light image enhancement and preserves the naturalness of the image.
- Open Access
- 4 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Illumination Estimation for Nature Preserving low-light image enhancement
In this paper, we proposed a new low-light image enhancementapproach to overcome the above limitations. Theproposed algorithm is named as Nature Preserving LowlightImage Enhancement (NPLIE). NPLIE estimates initialillumination and performs optimal refinement. The proposedalgorithm computes the reflectance component through anelement-wise division of input image by illumination. The enhanced image is obtained as a product of adjusted illumination and reflectance component. In this work, we estimate initialilluminance from structure-aware smoothening of a low-lightimage using guided filters of variable box sizes. We computerefined illumination by solving the proposed multi-objective
- 4 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessIllumination Estimation for Nature Preserving low-light image enhancement
In this paper, we proposed a new low-light image enhancementapproach to overcome the above limitations. Theproposed algorithm is named as Nature Preserving LowlightImage Enhancement (NPLIE). NPLIE estimates initialillumination and performs optimal refinement. The proposedalgorithm computes the reflectance component through anelement-wise division of input image by illumination. The enhanced image is obtained as a product of adjusted illumination and reflectance component. In this work, we estimate initialilluminance from structure-aware smoothening of a low-lightimage using guided filters of variable box sizes. We computerefined illumination by solving the proposed multi-objective
- 1 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A comparative analysis of illumination estimation based Image Enhancement techniques
Computer vision has gathered the attention of several researchers due to the incremental use of it in almost every field. The performance of computer vision systems is many times limited by input image quality. Thus, image enhancement becomes an essential step in these systems. Retinex based algorithms have proven performance in enhancement of low light images. Many Retinex-based algorithms focus on illumination estimation to perform image enhancement. This paper presents a comparative analysis of state-of-the-art image enhancement algorithms based on illumination estimation. In Retinex based approaches, computation of illumination and reflectance is a challenging task. In early approaches, a smooth image is considered as the illumination. However, in the last decade, various methods for estimation of illumination and reflectance have evolved up to a great extent. In this work, we analyze these image enhancement techniques based on illumination estimation. We perform extensive experimentation on a large set of images with varying illumination. The performance is analyzed both quantitatively and qualitatively. This analysis aims to assist researchers and ignite research to develop new efficient algorithms in this field.
- 1 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A comparative analysis of illumination estimation based Image Enhancement techniques
Computer vision has gathered the attention of several researchers due to the incremental use of it in almost every field. The performance of computer vision systems is many times limited by input image quality. Thus, image enhancement becomes an essential step in these systems. Retinex based algorithms have proven performance in enhancement of low light images. Many Retinex-based algorithms focus on illumination estimation to perform image enhancement. This paper presents a comparative analysis of state-of-the-art image enhancement algorithms based on illumination estimation. In Retinex based approaches, computation of illumination and reflectance is a challenging task. In early approaches, a smooth image is considered as the illumination. However, in the last decade, various methods for estimation of illumination and reflectance have evolved up to a great extent. In this work, we analyze these image enhancement techniques based on illumination estimation. We perform extensive experimentation on a large set of images with varying illumination. The performance is analyzed both quantitatively and qualitatively. This analysis aims to assist researchers and ignite research to develop new efficient algorithms in this field.