Linpeng Zeng

Henan Institute of Science and Technology

Papers

Total Citations

H-Index

About

Linpeng Zeng is a leading researcher in agricultural artificial intelligence, with a primary focus on computer vision and deep learning for precision agriculture. His work centers on developing robust object detection models tailored to complex, real-world orchard environments, addressing critical challenges in automated yield estimation and crop monitoring. Zeng's most notable contribution is his pioneering application of improved Faster-RCNN architectures for apple detection, which directly confronts the limitations of traditional convolutional neural networks—particularly their inductive biases in handling occluded, variably lit, and densely clustered fruit in natural settings. His 2024 paper on this topic has already garnered 30 citations, reflecting its immediate impact on the field. By refining detection accuracy in unstructured agricultural scenes, Zeng's research bridges the gap between state-of-the-art computer vision and practical farming needs, offering scalable solutions for smart agriculture. His work is essential reading for researchers and students exploring the intersection of deep learning and agrotechnology, demonstrating how targeted architectural improvements can overcome the inherent constraints of CNNs in field applications.