Subir 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
Subir Chowdhury has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Jakaria Rabbi
Department of Computer Science and Engineering, Khulna University of Engineering and Technology, Khulna, Bangladesh
3 shared publications Todd C. Shipman
3 shared publicationsDennis Chao
2 shared publications- Dennis Chao
Alberta Geological Survey Alberta Energy Regulator Edmonton Alberta Canada
2 shared publications Dennis K. Chao
2 shared publications- Matthias Schubert
LMU Munich
2 shared publications
Latest Publications
- Open Access
- 1 February 2021
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 94
Estimation of land-use/land-cover changes associated with energy footprints and other disturbance agents in the Upper Peace Region of Alberta Canada from 1985 to 2015 using Landsat data
- 1 February 2021
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 94
Open AccessEstimation of land-use/land-cover changes associated with energy footprints and other disturbance agents in the Upper Peace Region of Alberta Canada from 1985 to 2015 using Landsat data
- 24 December 2020
- Published by Springer Nature
- p. 291-305
The Role of Landsat-8 Multispectral Data in Spill Response: Three Case Studies
- 24 December 2020
- Published by Springer Nature
- p. 291-305
The Role of Landsat-8 Multispectral Data in Spill Response: Three Case Studies
- Top Cited PapersOpen Access
- 1 May 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (9) , 1432
Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network
The detection performance of small objects in remote sensing images has not been satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) showed remarkable image enhancement performance, but reconstructed images usually miss high-frequency edge information. Therefore, object detection performance showed degradation for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we applied a new edge-enhanced super-resolution GAN (EESRGAN) to improve the quality of remote sensing images and used different detector networks in an end-to-end manner where detector loss was backpropagated into the EESRGAN to improve the detection performance. We proposed an architecture with three components: ESRGAN, EEN, and Detection network. We used residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we used a faster region-based convolutional network (FRCNN) (two-stage detector) and a single-shot multibox detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) dataset and another self-assembled (oil and gas storage tank) satellite dataset showed superior performance of our method compared to the standalone state-of-the-art object detectors.
- 1 May 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (9) , 1432
Top Cited PapersOpen AccessSmall-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network
The detection performance of small objects in remote sensing images has not been satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) showed remarkable image enhancement performance, but reconstructed images usually miss high-frequency edge information. Therefore, object detection performance showed degradation for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we applied a new edge-enhanced super-resolution GAN (EESRGAN) to improve the quality of remote sensing images and used different detector networks in an end-to-end manner where detector loss was backpropagated into the EESRGAN to improve the detection performance. We proposed an architecture with three components: ESRGAN, EEN, and Detection network. We used residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we used a faster region-based convolutional network (FRCNN) (two-stage detector) and a single-shot multibox detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) dataset and another self-assembled (oil and gas storage tank) satellite dataset showed superior performance of our method compared to the standalone state-of-the-art object detectors.
- Open Access
- 29 April 2020
- Published by MDPI AG in Preprints.org
Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network
The detection performance of small objects in remote sensing images has not been satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) showed remarkable image enhancement performance, but reconstructed images usually miss high-frequency edge information. Therefore, object detection performance showed degradation for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we applied a new edge-enhanced super-resolution GAN (EESRGAN) to improve the quality of remote sensing images and used different detector networks in an end-to-end manner where detector loss was backpropagated into the EESRGAN to improve the detection performance. We proposed an architecture with three components: ESRGAN, EEN, and Detection network. We used residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we used a faster region-based convolutional network (FRCNN) (two-stage detector) and a single-shot multibox detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) dataset and another self-assembled (oil and gas storage tank) satellite dataset showed superior performance of our method compared to the standalone state-of-the-art object detectors.
- 29 April 2020
- Published by MDPI AG in Preprints.org
Open AccessSmall-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network
The detection performance of small objects in remote sensing images has not been satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) showed remarkable image enhancement performance, but reconstructed images usually miss high-frequency edge information. Therefore, object detection performance showed degradation for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we applied a new edge-enhanced super-resolution GAN (EESRGAN) to improve the quality of remote sensing images and used different detector networks in an end-to-end manner where detector loss was backpropagated into the EESRGAN to improve the detection performance. We proposed an architecture with three components: ESRGAN, EEN, and Detection network. We used residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we used a faster region-based convolutional network (FRCNN) (two-stage detector) and a single-shot multibox detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) dataset and another self-assembled (oil and gas storage tank) satellite dataset showed superior performance of our method compared to the standalone state-of-the-art object detectors.
- Open Access
Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network
The detection performance of small objects in remote sensing images is not satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) shows remarkable image enhancement performance, but reconstructed images miss high-frequency edge information. Therefore, object detection performance degrades for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance. We propose an architecture with three components: ESRGAN, Edge Enhancement Network (EEN), and Detection network. We use residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we use the faster region-based convolutional network (FRCNN) (two-stage detector) and single-shot multi-box detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) and a self-assembled (oil and gas storage tank) satellite dataset show superior performance of our method compared to the standalone state-of-the-art object detectors.
Open AccessSmall-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network
The detection performance of small objects in remote sensing images is not satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) shows remarkable image enhancement performance, but reconstructed images miss high-frequency edge information. Therefore, object detection performance degrades for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance. We propose an architecture with three components: ESRGAN, Edge Enhancement Network (EEN), and Detection network. We use residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we use the faster region-based convolutional network (FRCNN) (two-stage detector) and single-shot multi-box detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) and a self-assembled (oil and gas storage tank) satellite dataset show superior performance of our method compared to the standalone state-of-the-art object detectors.
- 19 April 2017
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 54 (5) , 700-720
Utilization of Landsat data to quantify land-use and land-cover changes related to oil and gas activities in West-Central Alberta from 2005 to 2013
Land use and land cover (LULC) change detection associated with oil and gas activities plays an important role in effective sustainable management practices, compliance monitoring, and reclamation assessment. In this study, a mapping methodology is presented for quantifying pre- and post-disturbance LULC types with annual Landsat Best-Available-Pixel multispectral data from 2005 to 2013. Annual LULC and land disturbance maps were produced for one of the major conventional oil and gas production areas in West-Central Alberta with an accuracy of 78% and 87%, respectively. The highest rate of vegetation loss (178 km2/year) was observed in coniferous forest compared to broadleaf forest, mixed forest, and native vegetation. Integration of ancillary oil and gas geospatial data with annual land disturbances indicated that less than 20% of the total land disturbances were attributable to oil and gas activities. In 2013, approximately 44% of oil and gas disturbances from 2005 to 2013 showed evidence of vegetation recovery. In the future, geospatial data related to wildfire, logging activities, insect defoliation, and other natural and anthropogenic factors can be integrated to quantify other causes of land disturbances.
- 19 April 2017
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 54 (5) , 700-720
Utilization of Landsat data to quantify land-use and land-cover changes related to oil and gas activities in West-Central Alberta from 2005 to 2013
Land use and land cover (LULC) change detection associated with oil and gas activities plays an important role in effective sustainable management practices, compliance monitoring, and reclamation assessment. In this study, a mapping methodology is presented for quantifying pre- and post-disturbance LULC types with annual Landsat Best-Available-Pixel multispectral data from 2005 to 2013. Annual LULC and land disturbance maps were produced for one of the major conventional oil and gas production areas in West-Central Alberta with an accuracy of 78% and 87%, respectively. The highest rate of vegetation loss (178 km2/year) was observed in coniferous forest compared to broadleaf forest, mixed forest, and native vegetation. Integration of ancillary oil and gas geospatial data with annual land disturbances indicated that less than 20% of the total land disturbances were attributable to oil and gas activities. In 2013, approximately 44% of oil and gas disturbances from 2005 to 2013 showed evidence of vegetation recovery. In the future, geospatial data related to wildfire, logging activities, insect defoliation, and other natural and anthropogenic factors can be integrated to quantify other causes of land disturbances.
- 10 February 2016
- Published by Wiley
- p. 341-366
Making Better Decisions Faster: Sequential Application of Robust Engineering to Math‐Models, CAE Simulations, and Accelerated Testing
- 10 February 2016
- Published by Wiley
- p. 341-366
Making Better Decisions Faster: Sequential Application of Robust Engineering to Math‐Models, CAE Simulations, and Accelerated Testing
- 1 July 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21536996,p. 258-261
Daytime gas flare detection using Landsat-8 multispectral data
Daytime flaring detection using Landsat-8 multispectral data was inspired by the Visible Infrared Imaging Radiometer Suite (VIIRS) nightfire detection work. A fast and semi-automated endmember extraction algorithm was employed to detect gas flares in several locations of Alberta. Most of the detected flaring locations matched with the flaring reports, Bing Maps Aerial, and Google Maps images. To our knowledge, this is the only advanced technique for detecting daytime gas flares.
- 1 July 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21536996,p. 258-261
Daytime gas flare detection using Landsat-8 multispectral data
Daytime flaring detection using Landsat-8 multispectral data was inspired by the Visible Infrared Imaging Radiometer Suite (VIIRS) nightfire detection work. A fast and semi-automated endmember extraction algorithm was employed to detect gas flares in several locations of Alberta. Most of the detected flaring locations matched with the flaring reports, Bing Maps Aerial, and Google Maps images. To our knowledge, this is the only advanced technique for detecting daytime gas flares.
- 1 June 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21586268,p. 1-4
Spectral mixture analysis of hyperspectral data using Genetic Algorithm and Spectral Angle Constraint (GA-SAC)
A Genetic Algorithm and Spectral Angle Constraint (GA-SAC) abundance estimation method is presented to improve the accuracy of abundance maps affected by illumination effects and sensor noise. As an improved version of the Spectral Angle Constraint (SAC), the GA-SAC was compared against several existing techniques. Preliminary results showed advantages of the proposed GA-SAC method from tests involving a simulated hyperspectral data set as well as for mapping mineral abundances using AVIRIS data over Cuprite, Nevada.
- 1 June 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21586268,p. 1-4
Spectral mixture analysis of hyperspectral data using Genetic Algorithm and Spectral Angle Constraint (GA-SAC)
A Genetic Algorithm and Spectral Angle Constraint (GA-SAC) abundance estimation method is presented to improve the accuracy of abundance maps affected by illumination effects and sensor noise. As an improved version of the Spectral Angle Constraint (SAC), the GA-SAC was compared against several existing techniques. Preliminary results showed advantages of the proposed GA-SAC method from tests involving a simulated hyperspectral data set as well as for mapping mineral abundances using AVIRIS data over Cuprite, Nevada.
- Open Access
- 14 August 2009
- Published by Copernicus GmbH in Natural Hazards and Earth System Sciences
- Vol. 9 (4) , 1433-1443
A web-based GIS for managing and assessing landslide data for the town of Peace River, Canada
Assessment of geological hazards in urban areas must integrate geospatial and temporal data, such as complex geology, highly irregular ground surface, fluctuations in pore-water pressure, surface displacements and environmental factors. Site investigation for geological hazard studies frequently produces surface maps, geological information from borehole data, laboratory test results and monitoring data. Specialized web-based GIS tools were created to facilitate geospatial analyses of displacement data from inclinometers and pore pressure data from piezometers as well as geological information from boreholes and surface mapping. A variety of visual aids in terms of graphs or charts can be created in the web page on the fly, e.g. displacement vector, time displacement and summaries of geotechnical testing results. High-resolution satellite or aerial images and LiDAR data can also be effectively managed, facilitating fast and preliminary hazard assessment. A preliminary geohazard assessment using the web based tools was carried out for the Town of Peace River.
- 14 August 2009
- Published by Copernicus GmbH in Natural Hazards and Earth System Sciences
- Vol. 9 (4) , 1433-1443
Open AccessA web-based GIS for managing and assessing landslide data for the town of Peace River, Canada
Assessment of geological hazards in urban areas must integrate geospatial and temporal data, such as complex geology, highly irregular ground surface, fluctuations in pore-water pressure, surface displacements and environmental factors. Site investigation for geological hazard studies frequently produces surface maps, geological information from borehole data, laboratory test results and monitoring data. Specialized web-based GIS tools were created to facilitate geospatial analyses of displacement data from inclinometers and pore pressure data from piezometers as well as geological information from boreholes and surface mapping. A variety of visual aids in terms of graphs or charts can be created in the web page on the fly, e.g. displacement vector, time displacement and summaries of geotechnical testing results. High-resolution satellite or aerial images and LiDAR data can also be effectively managed, facilitating fast and preliminary hazard assessment. A preliminary geohazard assessment using the web based tools was carried out for the Town of Peace River.