Papers
1
Total Citations
2
H-Index
1
About
J Ebin is a researcher advancing the frontier of autonomous navigation through innovative work in visual odometry (VO) and deep learning architectures. Their primary research focus lies in developing hybrid models that combine convolutional neural networks (CNNs) with transformer mechanisms to enhance localization accuracy for autonomous agents such as vehicles and robots. Ebin’s most notable contribution, the "ViT VO - A Visual Odometry Technique Using CNN-Transformer Hybrid Architecture" (2023), introduces a novel framework that leverages the strengths of both CNNs for spatial feature extraction and transformers for capturing long-range dependencies in sequential motion data. This work, with 2 citations, addresses a critical challenge in VO—enabling agents to reliably track their paths and detect obstacles in dynamic environments. By integrating attention mechanisms into traditional odometry pipelines, Ebin’s research offers a promising pathway toward more robust, real-time localization systems. Their achievements underscore a commitment to bridging computer vision and robotics, making their work a valuable reference for students and researchers exploring hybrid deep learning solutions for autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1