Afaroj Ahamad
Papers
2
Total Citations
7
H-Index
2
About
Afaroj Ahamad is a researcher focused on advancing robotic vision and embedded systems, with key contributions in real-time floor region segmentation for autonomous mobile robots. His work addresses the critical challenge of enabling unmanned ground vehicles (UGVs) to navigate complex indoor environments cluttered with patterned floors, shadows, and reflections. Ahamad’s major contributions include the development of a Binary Fully Convolutional Neural Network (B-FCN) that leverages the Taguchi method for sub-optimization, achieving efficient and precise floor segmentation suitable for robotic vision. This work, published in 2020, has garnered 5 citations and demonstrates a novel approach to neural network acceleration. He further advanced the field with a hardware-accelerated algorithm for fast floor region estimation in single images, published in 2022, which has received 2 citations. Ahamad’s research is notable for its practical application of SoC FPGA acceleration, bridging the gap between deep learning efficiency and real-time robotic deployment. His work is particularly valuable for students and researchers interested in embedded AI, computer vision, and autonomous navigation, offering a pathway to robust, low-latency perception systems for smart rovers.
Research Focus
Key Achievements
Top Papers
- 1
- 2