Heechan Yang

Papers

Total Citations

H-Index

About

Heechan Yang is a leading researcher in agricultural artificial intelligence, with a primary focus on developing deep learning solutions for precision farming and autonomous weeding systems. His most influential work, "Learning Semantic Graphics Using Convolutional Encoder–Decoder Network for Autonomous Weeding in Paddy" (2019, 68 citations), introduces a novel convolutional encoder-decoder architecture that enables semantic segmentation of crops and weeds in paddy fields. This contribution directly addresses the critical challenge of reducing chemical herbicide use by enabling robots to visually distinguish between crops and invasive plants with high accuracy. Yang’s approach leverages end-to-end learning to generate pixel-level semantic graphics, allowing autonomous weeding machines to make real-time, targeted interventions. His research sits at the intersection of computer vision, robotics, and sustainable agriculture, offering a data-driven pathway to minimize environmental harm while maintaining crop yields. By demonstrating that deep neural networks can effectively interpret complex, unstructured farm environments, Yang has provided a foundational framework for next-generation precision agriculture technologies. His work is widely cited by researchers developing field-deployable robotic systems, underscoring its practical impact on reducing chemical runoff and promoting eco-friendly farming practices.