Chengzhi Tan

Papers

Total Citations

H-Index

About

Chengzhi Tan is a leading researcher in agricultural artificial intelligence, specializing in computer vision and deep learning for precision agriculture. His work focuses on solving critical challenges in automated fruit detection, particularly under complex natural conditions such as occlusion and variable illumination. Tan’s most influential contribution is the development of an improved YOLOv3 model based on a dual path network for cherry tomato detection (2021, 51 citations), which significantly enhances small-target semantic feature extraction and reduces information loss during network transmission. His complementary study on detecting ripe fruits under natural occlusion and illumination conditions (2021, 48 citations) further advances robust vision systems for real-world harvesting environments. With nearly 100 citations across his top papers, Tan’s research directly addresses the practical limitations of deep learning in agriculture, enabling more reliable and efficient automated fruit recognition. His work is foundational for the next generation of intelligent harvesting robots, bridging the gap between theoretical computer vision and field-ready agricultural technology.