Mukesh Kumar Rohil
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mukesh Kumar Rohil has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Indranil Misra
Signal and Image Processing Group, Space Applications Centre, Indian Space Research Organisation (ISRO), Ahmedabad, India
5 shared publications - Manthira Moorthi Subbiah
India Space Research Organization
5 shared publications Debajyoti Dhar
3 shared publications- Trishna Paul
BITS Pilani, Pilani Campus
3 shared publications Yemineni Ashok
Department of Computer Science & Information Systems, Birla Institute of Technology and Science, Pilani, Pilani, India
3 shared publications- Debajyoti Dhar
India Space Research Organization
2 shared publications
Latest Publications
- Open Access
- 30 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 19852
An instance-aware segmentation and optical flow based DVI-SLAM for dynamic environments
Simultaneous Localisation and Mapping (SLAM) is a fundamental building block for markerless Augmented Reality systems. However, most conventional SLAM systems exhibit poor performance in real-time environments because of the influence of dynamic objects in unstructured surroundings. We are proposing a new Dynamic Visual Inertial SLAM system called DVI-SLAM to address the challenges of dynamic content presented in complex urban scenes. Leveraging instance-aware segmentation and optical flow methods, our system can detect and exclude actively moving objects from the tracking process. In addition to excluding features of moving objects from the pose estimation process, the system also detects, tracks, and generates static-map of the surrounding environment. This helps develop a robust AR system or mobile robot system to effectively handle complex outdoor urban scene scenarios. The proposed DVI-SLAM framework was tested on the TUM RGB-D and TUM-VI datasets as well as in real-world environments. The results showed an improvement in ATE’s Root Mean Square Error (RMSE) up to 24.80 and 32.34% compared with ORB-SLAM3, on monocular-inertial and stereo-inertial sequences of the TUM-VI dataset, respectively. Similarly, an improvement up to 64.89 and 73.75% was achieved for real-time monocular and RGB-D inertial sequences of real-time environments. Further, the sequence with a lot of dynamic content, such as the TUM-RGBD dynamic dataset, showed up to 99.4% improvement in ATE RMSE. The results demonstrated that DVI-SLAM significantly enhances Absolute Trajectory Error accuracy as compared to the state-of-the-art ORB-SLAM3 method. Extensive experiments evaluation shows that DVI-SLAM performs robustly across both static and dynamic scenarios, while maintaining competitive performance in static and low-dynamic scenes, it delivers significant improvements in highly dynamic environments.
- 30 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 19852
Open AccessAn instance-aware segmentation and optical flow based DVI-SLAM for dynamic environments
Simultaneous Localisation and Mapping (SLAM) is a fundamental building block for markerless Augmented Reality systems. However, most conventional SLAM systems exhibit poor performance in real-time environments because of the influence of dynamic objects in unstructured surroundings. We are proposing a new Dynamic Visual Inertial SLAM system called DVI-SLAM to address the challenges of dynamic content presented in complex urban scenes. Leveraging instance-aware segmentation and optical flow methods, our system can detect and exclude actively moving objects from the tracking process. In addition to excluding features of moving objects from the pose estimation process, the system also detects, tracks, and generates static-map of the surrounding environment. This helps develop a robust AR system or mobile robot system to effectively handle complex outdoor urban scene scenarios. The proposed DVI-SLAM framework was tested on the TUM RGB-D and TUM-VI datasets as well as in real-world environments. The results showed an improvement in ATE’s Root Mean Square Error (RMSE) up to 24.80 and 32.34% compared with ORB-SLAM3, on monocular-inertial and stereo-inertial sequences of the TUM-VI dataset, respectively. Similarly, an improvement up to 64.89 and 73.75% was achieved for real-time monocular and RGB-D inertial sequences of real-time environments. Further, the sequence with a lot of dynamic content, such as the TUM-RGBD dynamic dataset, showed up to 99.4% improvement in ATE RMSE. The results demonstrated that DVI-SLAM significantly enhances Absolute Trajectory Error accuracy as compared to the state-of-the-art ORB-SLAM3 method. Extensive experiments evaluation shows that DVI-SLAM performs robustly across both static and dynamic scenarios, while maintaining competitive performance in static and low-dynamic scenes, it delivers significant improvements in highly dynamic environments.
- Open Access
Horizontal slicing-based frontal view gait recognition under occlusion with Augmented Reality Annotations
- 3 March 2026
- Published by Elsevier in Advances In Space Research
- Vol. 77 (9) , 8884-8911
Feature-based image processing in remote sensing: future prospects and research directions
- 3 March 2026
- Published by Elsevier in Advances In Space Research
- Vol. 77 (9) , 8884-8911
Feature-based image processing in remote sensing: future prospects and research directions
- 25 January 2026
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 22 (1) , 42
Deep learning for object detection: state of the art, challenges, and future directions
- 25 January 2026
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 22 (1) , 42
Deep learning for object detection: state of the art, challenges, and future directions
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 97003-97013
Two-Stage Temporal Graph Neural Network for Web API Recommendation in Mashup Creation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 97003-97013
Open AccessTwo-Stage Temporal Graph Neural Network for Web API Recommendation in Mashup Creation
- 29 July 2025
- Published by Springer Nature
- p. 647-661
Virtual Labs and Augmented Reality Applications in Work-Integrated Learning: A Comparison, Challenges, and Insights
- 29 July 2025
- Published by Springer Nature
- p. 647-661
Virtual Labs and Augmented Reality Applications in Work-Integrated Learning: A Comparison, Challenges, and Insights
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 6521-6534
Enhanced Multispectral Band-to-Band Registration Using Co-Occurrence Scale Space and Spatial Confined RANSAC Guided Segmented Affine Transformation
Band-to-Band Registration (BBR) is a pre-requisite image processing operation essential for specific remote sensing multispectral sensors. BBR aims to align spectral wavelength channels at sub-pixel level accuracy over each other. The paper presents a novel BBR technique utilizing Co-occurrence Scale Space (CSS) for feature point detection and Spatial Confined RANSAC (SC-RANSAC) for removing outlier matched control points. Additionally, the Segmented Affine Transformation (SAT) model reduces distortion and ensures consistent BBR. The methodology developed is evaluated with Nano-MX multispectral images onboard the Indian Nano Satellite (INS-2B) covering diverse landscapes. BBR performance using the proposed method is also verified visually at a 4X zoom level on satellite scenes dominated by cloud pixels. The band misregistration effect on the Normalized Difference Vegetation Index (NDVI) from INS-2B is analyzed and cross-validated with the closest acquisition Landsat-9 OLI NDVI map before and after BBR correction. The experimental evaluation shows that the proposed BBR approach outperforms the state-of-the-art image registration techniques.
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 6521-6534
Enhanced Multispectral Band-to-Band Registration Using Co-Occurrence Scale Space and Spatial Confined RANSAC Guided Segmented Affine Transformation
Band-to-Band Registration (BBR) is a pre-requisite image processing operation essential for specific remote sensing multispectral sensors. BBR aims to align spectral wavelength channels at sub-pixel level accuracy over each other. The paper presents a novel BBR technique utilizing Co-occurrence Scale Space (CSS) for feature point detection and Spatial Confined RANSAC (SC-RANSAC) for removing outlier matched control points. Additionally, the Segmented Affine Transformation (SAT) model reduces distortion and ensures consistent BBR. The methodology developed is evaluated with Nano-MX multispectral images onboard the Indian Nano Satellite (INS-2B) covering diverse landscapes. BBR performance using the proposed method is also verified visually at a 4X zoom level on satellite scenes dominated by cloud pixels. The band misregistration effect on the Normalized Difference Vegetation Index (NDVI) from INS-2B is analyzed and cross-validated with the closest acquisition Landsat-9 OLI NDVI map before and after BBR correction. The experimental evaluation shows that the proposed BBR approach outperforms the state-of-the-art image registration techniques.
- 14 August 2024
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (3) , 3279-3308
An architecture to intertwine augmented reality and intelligent tutoring systems: towards realizing technology-enabled enhanced learning
- 14 August 2024
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (3) , 3279-3308
An architecture to intertwine augmented reality and intelligent tutoring systems: towards realizing technology-enabled enhanced learning
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-5
EgoCentric+: A Multipurpose Data Set for Head-Mounted Wearable Computing Devices
Detecting the user’s action, anticipating his or her needs and performing realistic virtual and physical world mapping are the major modules for wearable computing devices. However, the wearable computing community lacks a multipurpose dataset to develop all these methods. In this work, we employed a ZED camera to generate a novel, challenging benchmark dataset that can be used to develop hand detection, hand gesture estimation (egocentric), stereo visual odometry/ SLAM trajectory estimation and disparity estimation methods. Our "EgoCentric+" dataset comprises 231 stereo image pair sequences along with ground truth trajectory values, hand gesture annotations and 2D bounding boxes for hand detection. We designed 20 continuous and 15 static hand gestures focused on interactions with virtual content in head-mounted wearable computers. Furthermore, the dataset is collected with a head-mounted camera under diverse backgrounds and illumination settings to resemble the wearable glasses environment. These settings can help researchers to develop appropriate and robust methodologies for head-mounted wearable devices and to thoroughly test and evaluate their models and applications.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessEgoCentric+: A Multipurpose Data Set for Head-Mounted Wearable Computing Devices
Detecting the user’s action, anticipating his or her needs and performing realistic virtual and physical world mapping are the major modules for wearable computing devices. However, the wearable computing community lacks a multipurpose dataset to develop all these methods. In this work, we employed a ZED camera to generate a novel, challenging benchmark dataset that can be used to develop hand detection, hand gesture estimation (egocentric), stereo visual odometry/ SLAM trajectory estimation and disparity estimation methods. Our "EgoCentric+" dataset comprises 231 stereo image pair sequences along with ground truth trajectory values, hand gesture annotations and 2D bounding boxes for hand detection. We designed 20 continuous and 15 static hand gestures focused on interactions with virtual content in head-mounted wearable computers. Furthermore, the dataset is collected with a head-mounted camera under diverse backgrounds and illumination settings to resemble the wearable glasses environment. These settings can help researchers to develop appropriate and robust methodologies for head-mounted wearable devices and to thoroughly test and evaluate their models and applications.