Hengqiang Su
Papers
1
Total Citations
22
H-Index
1
About
Hengqiang Su is a researcher advancing the field of agricultural computer vision, with a primary focus on lightweight deep learning models for precision fruit detection in complex environments. His most cited work, "Improved YOLOv7-Tiny Complex Environment Citrus Detection Based on Lightweighting" (2023, 22 citations), introduces YOLO-DCA, a novel detection model that addresses critical challenges in citrus orchards—including variable lighting, branch occlusion, and fruit overlap. By replacing standard convolutions with depth-separable convolutions (DWConv), Su achieves significant model lightweighting without sacrificing detection accuracy, making real-time deployment on resource-constrained devices feasible. This contribution is particularly impactful for smart agriculture, enabling efficient automated harvesting and yield estimation. Su’s research demonstrates a strong commitment to bridging the gap between state-of-the-art object detection and practical agricultural applications, with his work already garnering attention from peers seeking robust, deployable solutions for in-field fruit recognition. His innovations in model compression and environmental robustness position him as a rising contributor to the intersection of computer vision and precision agriculture.
Research Focus
Key Achievements
Top Papers
- 1