publications
2025
- IEEE ANTS 2025Network-Aware Path Planning for Autonomous Mobile Robots in Industrial EnvironmentsOm Kathalkar, Houssam Hajj Hassan, Ajay Kattepur, and 1 more authorIEEE International Conference on Advanced Networks and Telecommunications Systems, India, Oct 2025
Autonomous Mobile Robots (AMRs) in industrial environments require reliable wireless connectivity for coordination, control, and safety operations. Traditional path planning algorithms focus solely on geometric constraints, often leading robots through areas with poor network coverage that can compromise mission-critical operations. This paper presents a comprehensive framework for network-aware path planning that incorporates wireless network quality metrics as path constraints. We validate our Sionna-based ray-tracing simulations against real-world measurements from the Hernangomez et al. iV2I+ dataset, achieving strong correlation between simulated and real-world measurements (R² = 0.87 for SNR, 0.82 for throughput). Using this validated simulation framework, we implement three novel path planning algorithms: A* with network constraints, conditional variational autoencoder (CVAE)-based neural path planning, and Graph neural network-based multi-path (GraphMP) planning. Our evaluation demonstrates trade-offs between network quality requirements and path efficiency, with CVAE achieving 95.2% constraint satisfaction and GraphMP showing 23% shorter planning times. We provide practical guidelines for selecting appropriate algorithms and network quality thresholds based on application requirements, enabling more reliable AMR operations in industrial settings.
@article{Kathalkar2025network_aware, title = {Network-Aware Path Planning for Autonomous Mobile Robots in Industrial Environments}, author = {{Om Kathalkar} and Hassan, Houssam Hajj and Kattepur, Ajay and Bouloukakis, Georgios}, year = {2025}, month = oct, publisher = {IEEE}, journal = {IEEE International Conference on Advanced Networks and Telecommunications Systems, India}, doi = {-}, } - ICVGIP 2025AQIFormer: A Transformer-Based Multi-View Architecture for Cross-City Air Quality ClassificationOm Kathalkar, Nitin Nilesh, Sachin Chaudhari, and 1 more author16th Indian Conference on Computer Vision Graphics and Image Processing, Mandi, India, Oct 2025
Air pollution represents one of the most critical environmental and public health challenges globally, with traditional sensor-based monitoring systems facing significant scalability and economic constraints. Image-based air quality estimation has emerged as a promising alternative, leveraging the visual characteristics of atmospheric pollutants in traffic scenes. However, existing methods suffer from limited cross-city generalization and inadequate exploitation of multi-view perspectives. We present AQIFormer, a novel transformer-based ensemble architecture that addresses these fundamental limitations through innovative dual-view integration, weather-aware attention mechanisms, and comprehensive multi-task learning. Our approach uniquely combines front and rear traffic imagery with meteorological parameters to achieve robust air quality classification across diverse urban environments. Extensive evaluation on a dataset of 26,678 synchronized front–rear image pairs demonstrates 89.96% accuracy, representing a 14.96% improvement over state-of-the-art methods. Most importantly, our model maintains exceptional cross-city generalization capabilities, achieving 81.67% accuracy on an independent dataset collected in Nagpur, India, with only 8.29% performance degradation using few-shot adaptation and minimal training samples.
@article{Kathalkar2025AQIFormer, title = {AQIFormer: A Transformer-Based Multi-View Architecture for Cross-City Air Quality Classification}, author = {{Om Kathalkar} and Nilesh, Nitin and Chaudhari, Sachin and Namboodiri, Anoop}, year = {2025}, month = oct, publisher = {Association for Computing Machinery}, journal = {16th Indian Conference on Computer Vision Graphics and Image Processing, Mandi, India}, doi = {-}, dataset = {https://india-data.org/dataset-details/4965db32-3676-427f-86f0-c8ed678dad2b}, } - Patent202541073518 - System for Determining Air Quality Index (AQI) in Urban EnvironmentsOm Kathalkar, Ansh Shah, Sachin Chaudhari, and 1 more authorIndian Patent Office, Jul 2025
A system 100 for accurately determining Air Quality Index (AQI) in urban environments exhibiting high spatial and temporal variability is disclosed. The system includes a mobile platform 102 equipped with a multi-camera data acquisition system 108 and an array of environmental sensors 104. The multi-camera data acquisition system 108 includes front-facing camera 110, rear-facing camera 112, and 360-degree camera 114 configured to capture real-time environmental imagery. The environmental sensors 104 include particulate matter (PM2.5 and PM10) sensors 116, noise sensors 118, and contextual sensors 120 for collecting weather and temporal data. An edge computing device 106, operatively connected to the cameras and sensors, processes the acquired data using deep learning-based feature extraction pipelines 126. The system performs visual and contextual feature fusion through cross-view alignment and modality concatenation, followed by encoding with a transformer-based encoder 128 incorporating multi-head attention.
2024
- Patent202441043706 - System and Method for Determining Air Quality by Processing Environmental and Traffic-Related Visual DataOm Kathalkar, Nitin Nilesh, Sachin Chaudhari, and 1 more authorIndian Patent Office, Jun 2024
A system 100 and method are disclosed for automated air quality determination using multimodal data fusion and a transformer-based deep learning architecture. The system (100) receives synchronized video streams from a first camera (104) and a second camera (106) along with environmental sensor data from an air quality monitoring device (108). Images are sampled at defined intervals, annotated with sensor data and contextual metadata, and processed using a frozen convolutional neural network to extract feature vectors. These visual features are combined with standardized sensor readings and encoded contextual information to form a unified feature representation. A custom transformer model projects this representation into a token sequence with positional encoding. The final classification is performed using the transformer’s last token output, which captures attention-weighted spatial-temporal correlations between visual indicators and environmental factors. The system outputs a six-category air quality index (AQI) classification, including good, satisfactory, moderate, poor, very poor, or severe.
- ICVGIP 2024TRAQID - Traffic-Related Air Quality Image DatasetOm Kathalkar, Nitin Nilesh, Sachin Chaudhari, and 1 more author15th Indian Conference on Computer Vision Graphics and Image Processing, Bengaluru, India, Oct 2024
Air quality estimation through sensor-based methods is widely used. Nevertheless, their frequent failures and maintenance challenges constrain the scalability of air pollution monitoring efforts. Recently, it has been demonstrated that air quality estimation can be done using image-based methods. These methods offer several advantages including ease of use, scalability, and low cost. However, the accuracy of these methods hinges significantly on the diversity and magnitude of the dataset utilized. The advancement of air quality estimation through image analysis has been limited due to the lack of available datasets. Addressing this gap, we present TRAQID - Traffic-Related Air Quality Image Dataset, a novel dataset capturing 26,678 front and rear images of traffic alongside co-located weather parameters, multiple levels of Particulate Matters (PM) and Air Quality Index (AQI) values. Spanning over multiple seasons, with over 70 hours of data collection in the twin cities of Hyderabad and Secunderabad, India, the TRAQID offers diverse day and night imagery amid unstructured traffic conditions, encompassing six AQI categories ranging from “Good” to “Severe”. State-of-the-art air quality estimation techniques, which were trained on a smaller and less-diverse dataset, showed poor results on the dataset presented in this paper. TRAQID models various uncertainty types, including seasonal changes, unstructured traffic patterns, and lighting conditions. The information from the two views (front and rear) of the traffic can be combined to improve the estimation performance in such challenging conditions. As such, the TRAQID serves as a benchmark for image-based air quality estimation tasks and AQI prediction, given its diversity and magnitude.
@article{Kathalkar2024TRAQID, title = {TRAQID - Traffic-Related Air Quality Image Dataset}, author = {{Om Kathalkar} and Nilesh, Nitin and Chaudhari, Sachin and Namboodiri, Anoop}, year = {2024}, month = oct, publisher = {Association for Computing Machinery}, journal = {15th Indian Conference on Computer Vision Graphics and Image Processing, Bengaluru, India}, doi = {10.1145/3702250.3702260}, dataset = {https://india-data.org/dataset-details/4965db32-3676-427f-86f0-c8ed678dad2b}, } - PatentSystem and Method for Implementing an Experiment Remotely and Determining an Output Using a Computer Vision ModelSachin Chaudhari, Om Rajendra Kathalkar, Viswanadh Savita Kandala, and 1 more authorUnited States Patent and Trademark Office, Mar 2024
A system and method for implementing an experiment remotely and determining an output using a computer-vision model is provided. The system includes an image capturing device, an experiment setup, a microcontroller, a user device, and a relay unit. The microcontroller (i) receives the input of the experiment from the image capturing device, (ii) extracts one or more frames from the input data, (iii) pre-process the one or more frames to obtain a binary image, (iv) obtain a closed curve around the binary image to locate the experiment, (v) determine the coordinates of the experiment to track the experiment in each frame, (vi) determine an output of the experiment from every two consecutive frames of the one or more frames, and (vii) optimize the determined output of the experiment using a linear regression model.
2023
- EnvSys 2023Protocol for hunting PM2.5 emission hot spots in citiesSara Spanddhana, Andrew Rebeiro-Hargrave, Om Kathalkar, and 3 more authorsProceedings of the 1st International Workshop on Advances in Environmental Sensing Systems for Smart Cities, Mar 2023
Particulate Matter (PM) is a major air pollutant that has the potential for adversely affecting human health. Actionable data on the spatial distribution of temporal variability of PM2.5 emission hot spots in large cities are sparse. The main objective of this research is to provide a protocol for using search agents to hunt for PM2.5 emission hot spots in urban environments. We propose short-range identification of variability of harmful PM2.5 concentrations can be achieved using IoT devices mounted on a mobile platform. We propose that long-range identification of the PM2.5 emission hot spots can be attained by searching through the city on different days. We applied this approach to Hyderabad, India by fixing a mobile platform on a street car. We corrected the IoT device measurement errors by calibrating the sensing component data against a reference instrument co-located on the mobile platform. We identified that random forest regression was the most suitable technique to reduce the variability between the IoT devices. The spatial variability of PM2.5 harmful emission hot spots at industrial settings and congested roads were identified. The temporal variability based on image processing shows a weak correlation between PM2.5 concentrations and the number of vehicles, and PM2.5 and visibility. The Hyderabad PM2.5 emission hot spots findings demonstrate a clear need to inform people with heart and lung conditions when it is unhealthy to be outside, and when it is unhealthy for children and elderly people to be outside for prolonged periods. Our emission hunting approach can be applied to any mobile platform carried by people walking, cycling, or by drones and robots in any city.
@article{hunting_PM25_hot_spots, title = {Protocol for hunting PM2.5 emission hot spots in cities}, author = {Spanddhana, Sara and Rebeiro-Hargrave, Andrew and {Om Kathalkar} and Varjonen, Samu and Chaudhari, Sachin and Tarkoma, Sasu}, year = {2023}, publisher = {Association for Computing Machinery}, journal = {Proceedings of the 1st International Workshop on Advances in Environmental Sensing Systems for Smart Cities}, url = {https://doi.org/10.1145/3597064.3597322}, doi = {10.1145/3597064.3597322} }
2022
- FiCloud 2022CV and IoT-based Remote Triggered Labs: Use Case of Conservation of Mechanical EnergyK. S. Viswanadh, Om Kathalkar, Nitin Nilesh, and 2 more authors9th International Conference on Future Internet of Things and Cloud (FiCloud), Rome, Italy, Mar 2022
Remote Triggered Labs (RTL) are helpful for students to work on laboratory experiments virtually anytime, anywhere. Such setups can facilitate distance learning and are helpful during pandemics. In this paper, the use of Computer Vision (CV) is demonstrated for RTL experiments. For this, a use-case of the Conservation of Mechanical Energy experiment is considered. A CV-based approach is used to estimate an object’s velocity whose setup primarily consists of a microprocessor, a camera and infrared (IR) sensors. The experiment is recorded, and various CV techniques are employed to estimate the object’s velocity. This paper also compares a CV-based and an IR sensor-based approach to estimate the object’s velocity. Linear regression applied to the CV-based implementation resulted in an optimal mean-squared error (MSE), nearly 10 times better than IR-based implementation.
@article{ficloud2022, title = {CV and IoT-based Remote Triggered Labs: Use Case of Conservation of Mechanical Energy}, author = {Viswanadh, K. S. and {Om Kathalkar} and Nilesh, Nitin and Chaudhari, Sachin and Choppella, Venkatesh}, year = {2022}, publisher = {IEEE}, journal = {9th International Conference on Future Internet of Things and Cloud (FiCloud), Rome, Italy}, doi = {10.1109/FiCloud57274.2022.00021}, }