Mr. Chalavadi Vishnu Profile

Chalavadi Vishnu

SPIE Involvement:

Author

Publications (6)

Proceedings Article | 3 April 2024 Paper

Multi-class object classification using deep learning models in automotive object detection scenarios

Soumya A., Linga Reddy Cenkeramaddi, Vishnu Chalavadi, Krishna Mohan C.

Proceedings Volume 13072, 1307206 (2024) https://doi.org/10.1117/12.3023463

Read Abstract +

SPIE Journal Paper | 1 November 2023

M2-APNet: A multimodal deep learning network to predict major air pollutants from temporal satellite images

Gudiseva Swetha, Rajeshreddy Datla, Chalavadi Vishnu, C. Krishna Mohan

JARS, Vol. 18, Issue 01, 012005, (November 2023) https://doi.org/10.1117/12.10.1117/1.JRS.18.012005

KEYWORDS: Satellites, Deep learning, Environmental monitoring, Data modeling, Air quality, Satellite imaging, Earth observing sensors, Machine learning, Education and training, Spatial resolution

Read Abstract +

SPIE Journal Paper | 12 August 2023 Open Access

Self-supervised embedding for generalized zero-shot learning in remote sensing scene classification

Rambabu Damalla, Rajeshreddy Datla, Chalavadi Vishnu, Chalavadi Krishna Mohan

JARS, Vol. 17, Issue 03, 032405, (August 2023) https://doi.org/10.1117/12.10.1117/1.JRS.17.032405

KEYWORDS: Semantics, Visualization, Remote sensing, Machine learning, Scene classification, Education and training, Data modeling, Classification systems, Visual process modeling, Feature extraction

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 7 June 2023 Paper

Adaptive spatial and temporal aggregation for table tennis shot recognition

Sravani Yenduri, Vishnu Chalavadi, Krishna Mohan C.

Proceedings Volume 12701, 127010H (2023) https://doi.org/10.1117/12.2679426

KEYWORDS: 3D modeling, RGB color model, Video, Action recognition, Transformers, Motion models, Pose estimation, Feature extraction, Convolution, Head

Read Abstract +

Action recognition is one of the challenging video understanding tasks in computer vision. Although there has been extensive research in the task of classifying coarse-grained actions, existing methods are still limited in differentiating actions with low inter-class and high intra-class variation. Particularly, the table tennis sport that involves shots of high inter-class similarity, subtle variations, occlusion, and view-point variations. While a few datasets have been available for event spotting and shot recognition, these benchmarks are mostly recorded in a constrained environment with a clear view/perception of shots executed by players. In this paper, we introduce a Table tennis shots 1.0 dataset consisting of 9000 videos of 6 fine-grained actions collected in an unconstrained manner to analyze the performance of both players. To effectively recognise these different types of table tennis shots, we propose an adaptive spatial and temporal aggregation method that can handle the spatial and temporal interactions concerning the subtle variations among shots and low inter-class variations. Our method consists of three components, namely, (i) feature extraction module, (ii) spatial aggregation network, and (iii) temporal aggregation network. The feature extraction module is a 3D convolutional neural network (3D-CNN) that captures the spatial and temporal characteristics of table tennis shots. In order to capture the interaction among the elements of the extracted 3D-CNN feature maps efficiently, we employ spatial aggregation network to obtain the compact spatial representation. Later, we propose to replace the final global average pooling layer (GAP) with the temporal aggregation network to overcome the loss of motion information due to averaging of temporal features. This temporal aggregation network utilizes the attention mechanism of bidirectional encoder representations from Transformers (BERT) to model the significant temporal interactions among the shots effectively. We demonstrate that our proposed approach improves the performance of existing 3D-CNN methods by ~10% on the Table tennis shots 1.0 dataset.We also show the performance of our approach on other action recognition datasets, namely, UCF-101 and HMDB-51.

Proceedings Article | 5 March 2022 Paper

A multimodal semantic segmentation for airport runway delineation in panchromatic remote sensing images

Rajeshreddy Datla, Vishnu Chalavadi, C. Krishna Mohan

Proceedings Volume 12084, 1208407 (2022) https://doi.org/10.1117/12.2622656

KEYWORDS: Image segmentation, Remote sensing, Transformers, Image fusion, Satellites, Satellite imaging, Image resolution, Image processing, Earth observing sensors

Read Abstract +

Proceedings Article | 5 March 2022 Paper

A framework to derive geospatial attributes for aircraft type recognition in large-scale remote sensing images

Rajeshreddy Datla, Vishnu Chalavadi, C. Krishna Mohan

Proceedings Volume 12084, 120840N (2022) https://doi.org/10.1117/12.2622655

KEYWORDS: Image segmentation, Remote sensing, Convolution, Spatial resolution, Satellites, Object recognition

Read Abstract +

Showing 5 of 6 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years