Vidya Kamath

Vidya Kamath

Auto-generated profile, based on publicly available information

Vidya Kamath

Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications

25 March 2024 in IEEE Access
Verified
Journal Article
Open access
VKVidya Kamath
Vidya Kamath
RARenuka A
Renuka A
VKVishwas G. Kini
Vishwas G. Kini
SPShwetha Prabhu
Shwetha Prabhu
Most computer vision applications that use deep learning on constrained device come from the Internet of Things (IoT) or robotics fields, where low-quality cameras are used to capture input images in real time. Since most pretrained models typically undergo training on high-quality image datasets, the low-quality, noisy, or blurry images captured with these resource-constrained devices could possibly have a negative impact on the models’ performance. To determine if model performance is impacted by training models using low-quality data, a secondary image dataset named MOD-2022 was prepared for object detection and tracking tasks using an exploratory data preparation methodology. This dataset was primarily designed to include a wider range of classes with an adequate number of images per class while being free of errors due to inaccurate labelling or annotations. Additionally, a training approach is also proposed to support the model’s training when the dataset is considerably large. A VGG16-SSD model was trained with this approach on the prepared dataset and deployed on a Raspberry Pi and it showed that this approach is very useful in developing models for resource-constrained applications. Furthermore, this data preparation approach can be extended to prepare numerous other datasets required for training models designed to be deployed on constrained devices similar to the Raspberry Pi.

24 February 2025 in IEEE Access
Verified
Journal Article
Open access
JVJ. Vanajakshi
J. Vanajakshi
RARenuka A
Renuka A
VKVidya Kamath
Vidya Kamath
NAN. D. Adesh
N. D. Adesh
Recent advancements in transportation technology have necessitated a seamless integration of sensors, cameras, and communication protocols for autonomous vehicles. Ensuring cybersecurity for these vehicles has become critical, as they are vulnerable to attacks that could jeopardize safety and performance. While machine learning and deep learning models could be developed to address cybersecurity issues in autonomous vehicles, developing these models requires large datasets for training. Obtaining real-world data from actual vehicles also presents significant challenges. To address these limitations, a low-cost Pro-CHASER testbed— Prototype testbed for Car Hacking Attack Simulation and Evaluation using Raspberry Pi—was developed using a Controller Area Network (CAN) bus network with CAN-HAT (Hardware Attached on Top). This testbed utilized CAN to simulate autonomous vehicle functions and explore attack vectors. Microsoft Threat Modelling Tool, and MITRE ATT&CK framework were used to identify the vulnerabilities in the context of autonomous vehicles. The identified attacks were exploited using the designed testbed by employing many security testing tools to simulate CAN message injection attacks, USB exploits, and ROS-based fake image publisher attack, respectively. Through these attack simulations, the testbed functionalities were successfully compromised. The results demonstrated that message injection into the CAN bus manipulated sensor data that led to erroneous decision-making. Unauthorized access to the physical access points led to the injection of a malicious payload via a USB port. The computer vision system’s response to the false data ultimately compromised the vehicle’s perception and control. The findings highlight the capability of Pro-CHASER in identifying cyber security risks in autonomous vehicles, which offers a practical and low-cost platform for threat simulation and evaluation.

15 February 2025 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
VKVidya Kamath
Vidya Kamath
RARenuka A
Renuka A
Discovering deep learning-based computer vision solutions for use with constrained devices is exceptionally hard, and the trade-offs are often too undermining. Deep learning models are enormous, which makes it challenging to deploy them on constrained platforms. The convolutional neural network is the fundamental framework for majority of the models that are currently in use. However, operational neural networks have recently shown to be a better option to the convolutional equivalents on a variety of tasks due to their heterogeneous nature and greater resemblance to the functioning of biological neurons. The question of whether heterogeneous models could function on constrained devices and be deployed in real time remains a major concern. To address this problem, an object detection model architecture based on a single-shot multi-box detector with self-organized operational neural networks as its backbone was developed, which can perform efficiently on constrained devices such as Raspberry Pi. The resultant backbone architecture was named as VireNet. In contrast to homogeneous conventional deep learning networks that use convolutions, heterogeneous networks were chosen to develop VireNet, which provides a more productive and effective solution. Furthermore, an in-depth explanation of the design space has been provided to aid any future research that is associated with this architectural search. This new approach might mark the very beginning of the use of heterogeneity to address issues on devices with constrained resources.

31 March 2023
Verified
Other
Open access
SESteven Eschrich
Steven Eschrich
WFWilliam J. Fulp
William J. Fulp
YPYudi Pawitan
Yudi Pawitan
JFJohn A. Foekens
John A. Foekens
MSMarcel Smid
Marcel Smid
JTJavier F. Torres-Roca
Javier F. Torres-Roca