Anirudh Srinivasan Chakravarthy

Anirudh Srinivasan Chakravarthy

Auto-generated profile, based on publicly available information

Anirudh Srinivasan Chakravarthy

Robotics Institute Carnegie Mellon University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 January 2022 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
ACAnirudh S. Chakravarthy
Anirudh S. Chakravarthy
SSSoumendu Sinha
Soumendu Sinha
PNPratik Narang
Pratik Narang
MMMurari Mandal
Murari Mandal
Vinay ChamolaVinay Chamola
Vinay Chamola
FYF. Richard Yu
F. Richard Yu
Unmanned Aerial Vehicles (UAVs) are the promising “Flying IoT” devices of the future, which can be equipped with various sensors and cognitive capabilities to perform numerous tasks related to remote sensing, search and rescue operations, object tracking, segmentation of roads and buildings, surveillance, etc. However, these AI-driven tasks require heavy computation and may lead to suboptimal performance with embedded processors on a power-constrained battery-operated drone. This work proposes a novel deep learning approach for performing robust semantic segmentation of aerial scenes captured by UAVs. In our setup, the power-constrained drone is used only for data collection, while the computationally intensive tasks are offloaded to a GPU cloud server. Our architecture performs robust semantic segmentation by learning the segmentation maps from jointly utilizing of aerial scenes along with the respective “elevation maps” in a semi-supervised approach. We propose a three-tier deep learning architecture, wherein the first module aims at preliminary feature extraction from aerial scenes using a backbone feature extractor. The second module captures the spatial dependency between the aerial scenes and their respective elevation maps to obtain better semantic information, which is achieved by a bi-directional LSTM. The third module is aimed at enhancing the performance of semantic segmentation through a semi-supervised approach with an encoder to generate segmentation maps and a decoder to reconstruct feature maps. This semi-supervised feature learning ensures robust extraction along with scalability. The proposed architecture was validated on real-world aerial datasets and achieves state-of-the-art results for aerial image segmentation.

1 February 2020
Verified
Conference Paper
Closed access
ACAnirudh Srinivasan Chakravarthy
Anirudh Srinivasan Chakravarthy
SRSundaresan Raman
Sundaresan Raman
Tomatoes are one of the major horticulture crops in the world. Early Blight is one of the most widespread tomato diseases in India, often causing a significant reduction in produce. Agricultural produce of tomatoes is of utmost importance, making it necessary for timely recognition of Early Blight. Using self-collected images, we first explore classification of Early Blight in diseased leaves using ResNet and Xception networks, achieving a classification accuracy of 99.952%. However, significant focus has already been dedicated to disease classification in crops. Additionally, the lack of spatial information for affected leaves persuades us to move towards an object detection approach, utilizing variants based on the YOLO framework. We illustrate results with a twin focus on accuracy and real-time inference. Through our work, we aim to assist the development of a mobile application for disease identification.

10 August 2021 in ACM Transactions on Internet Technology
Verified
Journal Article
Open access
PGPrateek Garg
Prateek Garg
ACAnirudh Srinivasan Chakravarthy
Anirudh Srinivasan Chakravarthy
MMMurari Mandal
Murari Mandal
PNPratik Narang
Pratik Narang
Vinay ChamolaVinay Chamola
Vinay Chamola
MGMohsen Guizani
Mohsen Guizani
Aerial scenes captured by UAVs have immense potential in IoT applications related to urban surveillance, road and building segmentation, land cover classification, and so on, which are necessary for the evolution of smart cities. The advancements in deep learning have greatly enhanced visual understanding, but the domain of aerial vision remains largely unexplored. Aerial images pose many unique challenges for performing proper scene parsing such as high-resolution data, small-scaled objects, a large number of objects in the camera view, dense clustering of objects, background clutter, and so on, which greatly hinder the performance of the existing deep learning methods. In this work, we propose ISDNet (Instance Segmentation and Detection Network), a novel network to perform instance segmentation and object detection on visual data captured by UAVs. This work enables aerial image analytics for various needs in a smart city. In particular, we use dilated convolutions to generate improved spatial context, leading to better discrimination between foreground and background features. The proposed network efficiently reuses the segment-mask features by propagating them from early stages using residual connections. Furthermore, ISDNet makes use of effective anchors to accommodate varying object scales and sizes. The proposed method obtains state-of-the-art results in the aerial context.

19 September 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
ACAnirudh S. Chakravarthy
Anirudh S. Chakravarthy
MGMeghana Reddy Ganesina
Meghana Reddy Ganesina
PHPeiyun Hu
Peiyun Hu
LLLaura Leal-Taixé
Laura Leal-Taixé
SKShu Kong
Shu Kong
AOAljosa Osep
Aljosa Osep

1 February 2020
Verified
Conference Paper
Closed access
ACAnirudh Srinivasan Chakravarthy
Anirudh Srinivasan Chakravarthy
HRHonnesh Rohmetra
Honnesh Rohmetra
DGDivyam Goel
Divyam Goel
HBHarshan Baskar
Harshan Baskar
PGPrateek Garg
Prateek Garg
BRBijay Kumar Rout
Bijay Kumar Rout
Recent developments in Machine Learning and Computer Vision have enabled progress in autonomous navigation. However, most of the existing research focuses on European driving situations, with not much progress made in the Indian context. Our paper aims to achieve complete spatial understanding for the Indian context. Our focus is directed towards Semantic Segmentation and Instance Segmentation. We aim to develop an autonomous navigation pipeline by a combination of both approaches. Using DeepLabv3+ for Semantic Segmentation we achieve an mIOU of 68.58%, and using Hybrid Task Cascade we achieve an Average Recall of 56.5%.

22 September 2024 in arXiv
Verified
Preprint
Open access
PDF file
ACAnirudh S Chakravarthy
Anirudh S Chakravarthy
MGMeghana Reddy Ganesina
Meghana Reddy Ganesina
PHPeiyun Hu
Peiyun Hu
LLLaura Leal-Taixe
Laura Leal-Taixe
SKShu Kong
Shu Kong
AOAljosa Osep
Aljosa Osep
Addressing Lidar Panoptic Segmentation (LPS ) is crucial for safe deployment of autonomous vehicles. LPS aims to recognize and segment lidar points w.r.t. a pre-defined vocabulary of semantic classes, including thing classes of countable objects (e.g., pedestrians and vehicles) and stuff classes of amorphous regions (e.g., vegetation and road). Importantly, LPS requires segmenting individual thing instances (e.g., every single vehicle). Current LPS methods make an unrealistic assumption that the semantic class vocabulary is fixed in the real open world, but in fact, class ontologies usually evolve over time as robots encounter instances of novel classes that are considered to be unknowns w.r.t. the pre-defined class vocabulary. To address this unrealistic assumption, we study LPS in the Open World (LiPSOW): we train models on a dataset with a pre-defined semantic class vocabulary and study their generalization to a larger dataset where novel instances of thing and stuff classes can appear. This experimental setting leads to interesting conclusions. While prior art train class-specific instance segmentation methods and obtain state-of-the-art results on known classes, methods based on class-agnostic bottom-up grouping perform favorably on classes outside of the initial class vocabulary (i.e., unknown classes). Unfortunately, these methods do not perform on-par with fully data-driven methods on known classes. Our work suggests a middle ground: we perform class-agnostic point clustering and over-segment the input cloud in a hierarchical fashion, followed by binary point segment classification, akin to Region Proposal Network [1]. We obtain the final point cloud segmentation by computing a cut in the weighted hierarchical tree of point segments, independently of semantic classification. Remarkably, this unified approach leads to strong performance on both known and unknown classes.