Pamodya Peiris
Papers
3
Total Citations
19
H-Index
2
About
Pamodya Peiris is a researcher working at the intersection of computer vision, machine learning, and robotics, with contributions spanning pediatric rehabilitation technology and precision agriculture. His most recognized work introduces BabyNet, a lightweight deep learning network designed for infant reaching action recognition in unconstrained environments — a significant departure from the adult-focused action recognition systems that dominate the field. Garnering 13 citations since its 2021 publication, BabyNet addresses a critical gap by enabling future pediatric wearable robotic exoskeletons to autonomously interpret infant movements, with meaningful implications for early childhood rehabilitation. Peiris has also directed his expertise toward agricultural robotics, developing algorithmic frameworks that allow ground mobile robots to perform real-time, on-the-go tree detection and geometric trait estimation in fruit tree groves. This work tackles the labor-intensive challenge of by-tree data collection in precision agriculture, offering scalable automation solutions for modern farming. Across his research, Peiris demonstrates a consistent drive to apply intelligent sensing and recognition systems to domains where automation can deliver tangible human and societal benefit, from neonatal health to sustainable food production.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3