Keerthy Kusumam
Papers
7
Total Citations
228
H-Index
6
About
Keerthy Kusumam is a leading researcher in agricultural robotics and long-term autonomous navigation, whose work bridges the gap between computer vision and real-world field deployment. Her primary research areas include 3D vision for precision agriculture and visual teach-and-repeat (VT&R) navigation systems. Kusumam is best known for pioneering 3D-vision-based detection, localization, and sizing of broccoli heads using low-cost RGB-D sensors, a breakthrough that directly addresses the challenge of robotic harvesting in unstructured field environments. Her seminal 2017 paper on this topic has garnered 84 citations, establishing a foundation for subsequent work in agricultural robotics. In parallel, she has made significant contributions to long-term visual navigation, systematically evaluating image features under seasonal and illumination changes. Her 2016 paper on image features for VT&R navigation (59 citations) and her 2015 study on image features across seasons (24 citations) are widely referenced. More recently, Kusumam has advanced the field through self-supervised and contrastive learning approaches for robust feature matching and image registration in VT&R systems, with several 2022 publications demonstrating her ongoing impact. Her work is notable for its practical focus on enabling robots to operate reliably in challenging, changing environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Image features and seasons revisited24 citations · 2015
- 5
- 6
- 7