Anupam Sobti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anupam Sobti has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Akshay Nambi
Microsoft Research India
1 shared publication - Aman Sa
Plaksha University, India
1 shared publication - Anshika Srivastava
Plaksha University, India
1 shared publication - Dinesh Kumar
Plaksha University, India
1 shared publication - Rajiv Ranjan
Plaksha University
1 shared publication - Sambal Shikhar
Plaksha University, India
1 shared publication
Latest Publications
- Open Access
- 21 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 585-596
Geospatial Active Learning for Efficient Data Annotation: A case study on cool roof detection
- 21 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 585-596
Open AccessGeospatial Active Learning for Efficient Data Annotation: A case study on cool roof detection
- Open Access
- 28 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Journal on Computing and Sustainable Societies
- Vol. 2 (4) , 1-26
What’s Up On The Roof: Tracking Cool Roofs in India with Satellite Imaging
With rapid pace of urbanization, the increase in built up area is leading to urban heat islands which absorb a lot of the heat received through solar radiation. To reduce this effect, reflective coatings on top of building roofs, known as cool roofs are installed. Cool roofs reflect light back through the atmosphere to minimize the heat radiation within the urban space. In this article, we introduce a cool roof tracker. The tracker provides building level information of whether a roof is cool or not, thus indicating if an urban heat island is likely to develop in a region. This information helps policymakers identify the vulnerable regions in a city and track the progress of cool roof implementation in all areas. There are three key components of the system: building polygon extraction, reflectance features extraction from roof images; and classification into cool vs. non cool buildings. There are a number of satellites operational today which offer different strengths - high resolution, high revisit time, multiple spectral bands, and so on. In this work, we do a mix of quantitative and qualitative evaluation of the efficacy of different satellite modalities for each of the system components, build robust models with extensive experimentation on color space, augmentations, and generalization achieving an F1-score of 97% on our test set. We also develop a prototype dashboard as a demonstration for supporting data-driven decision making for state level heat mitigation plans as well as regulatory and compliance tool for measuring roof reflectance.
- 28 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Journal on Computing and Sustainable Societies
- Vol. 2 (4) , 1-26
Open AccessWhat’s Up On The Roof: Tracking Cool Roofs in India with Satellite Imaging
With rapid pace of urbanization, the increase in built up area is leading to urban heat islands which absorb a lot of the heat received through solar radiation. To reduce this effect, reflective coatings on top of building roofs, known as cool roofs are installed. Cool roofs reflect light back through the atmosphere to minimize the heat radiation within the urban space. In this article, we introduce a cool roof tracker. The tracker provides building level information of whether a roof is cool or not, thus indicating if an urban heat island is likely to develop in a region. This information helps policymakers identify the vulnerable regions in a city and track the progress of cool roof implementation in all areas. There are three key components of the system: building polygon extraction, reflectance features extraction from roof images; and classification into cool vs. non cool buildings. There are a number of satellites operational today which offer different strengths - high resolution, high revisit time, multiple spectral bands, and so on. In this work, we do a mix of quantitative and qualitative evaluation of the efficacy of different satellite modalities for each of the system components, build robust models with extensive experimentation on color space, augmentations, and generalization achieving an F1-score of 97% on our test set. We also develop a prototype dashboard as a demonstration for supporting data-driven decision making for state level heat mitigation plans as well as regulatory and compliance tool for measuring roof reflectance.
- Open Access
- 8 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 238-247
Evaluation of computer vision pipeline for farm-level analytics: A case study in Sugarcane
Analyzing agricultural imagery for farm level insights has been an active area of research in the recent times. For providing the necessary information to stakeholders - be it farmers, financial institutions or governments, various computer vision tasks have to come together. For example, to provide information to a farmer about crop stress in their farm, accurate localization of the farm, identification of the crop type and a monitoring of the field’s micro-climate must be done together. In this work, we set performance benchmarks for three computer vision tasks - farm boundary detection, crop classification and sub-field stress estimation with different modalities of images - Sentinel2, PlanetScope and Drone Imagery. We use public dataset benchmarks for farm boundaries and crop classification and do a controlled field study on a large sugarcane farm in Uttar Pradesh, India for the stress estimation. Our work benchmarks farm boundary detection for small farms with state of the art deep learning algorithms achieving a dice score of 67%, improves the sugarcane classification accuracy by 10% coming to 98% and demonstrates an accuracy of 72% for water and nitrogen stress estimation.
- 8 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 238-247
Open AccessEvaluation of computer vision pipeline for farm-level analytics: A case study in Sugarcane
Analyzing agricultural imagery for farm level insights has been an active area of research in the recent times. For providing the necessary information to stakeholders - be it farmers, financial institutions or governments, various computer vision tasks have to come together. For example, to provide information to a farmer about crop stress in their farm, accurate localization of the farm, identification of the crop type and a monitoring of the field’s micro-climate must be done together. In this work, we set performance benchmarks for three computer vision tasks - farm boundary detection, crop classification and sub-field stress estimation with different modalities of images - Sentinel2, PlanetScope and Drone Imagery. We use public dataset benchmarks for farm boundaries and crop classification and do a controlled field study on a large sugarcane farm in Uttar Pradesh, India for the stress estimation. Our work benchmarks farm boundary detection for small farms with state of the art deep learning algorithms achieving a dice score of 67%, improves the sugarcane classification accuracy by 10% coming to 98% and demonstrates an accuracy of 72% for water and nitrogen stress estimation.
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 463-467
PressureML: Modelling Pressure Waves to Generate Large-Scale Water-Usage Insights in Buildings
Several studies have indicated that delivering insights and feedback on water usage has been effective in curbing water consumption, making it a pivotal component in achieving long-term sustainability objectives. Despite a significant proportion of water consumption originating from large residential and commercial buildings, there is a scarcity of cost-effective and easy-to-integrate solutions that provide water usage insights at a reasonable spatio-temporal granularity in such structures. Furthermore, existing methods for disaggregating water usage necessitate training data and rely on frequent data sampling to capture patterns, both of which pose challenges when scaling up and adapting to new environments. In this work, we aim to solve these challenges through a novel end-to-end approach which records data from pressure sensors and uses time-series classification by DNN models to determine room-wise water consumption in a building. This consumption data is then fed to a novel water disaggregation algorithm which can suggest a set of water-usage events, and has a flexible requirement of training data and sampling granularity. We conduct experiments using our approach and demonstrate its potential as a promising avenue for in-depth exploration, offering valuable insights into water usage on a large scale.
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 463-467
Open AccessPressureML: Modelling Pressure Waves to Generate Large-Scale Water-Usage Insights in Buildings
Several studies have indicated that delivering insights and feedback on water usage has been effective in curbing water consumption, making it a pivotal component in achieving long-term sustainability objectives. Despite a significant proportion of water consumption originating from large residential and commercial buildings, there is a scarcity of cost-effective and easy-to-integrate solutions that provide water usage insights at a reasonable spatio-temporal granularity in such structures. Furthermore, existing methods for disaggregating water usage necessitate training data and rely on frequent data sampling to capture patterns, both of which pose challenges when scaling up and adapting to new environments. In this work, we aim to solve these challenges through a novel end-to-end approach which records data from pressure sensors and uses time-series classification by DNN models to determine room-wise water consumption in a building. This consumption data is then fed to a novel water disaggregation algorithm which can suggest a set of water-usage events, and has a flexible requirement of training data and sampling granularity. We conduct experiments using our approach and demonstrate its potential as a promising avenue for in-depth exploration, offering valuable insights into water usage on a large scale.