Zhi Zeng
Papers
2
Total Citations
22
H-Index
2
About
Zhi Zeng is an emerging researcher specializing in computer vision and deep learning applications for precision agriculture, with a particular focus on automated fruit detection systems. Their work centers on advancing object detection architectures — notably YOLO-based frameworks — to address real-world challenges in agricultural robotics and harvesting automation. Zeng's most notable contribution, DCFA-YOLO, demonstrates a sophisticated approach to multimodal sensing by fusing complementary color and depth image information through a dual-channel cross-feature fusion mechanism. This innovation tackles a critical bottleneck in agricultural automation: accurately detecting clustered produce, such as cherry tomato bunches, in complex natural environments. The paper has garnered 17 citations since its 2025 publication, signaling rapid uptake within the precision agriculture and computer vision communities. Their follow-up work, LEFF-YOLO, further refines this direction by developing a lightweight YOLOv8-based detection network with enhanced feature fusion, prioritizing computational efficiency without sacrificing detection accuracy — an essential consideration for deployment on edge devices in field conditions. Though early in their research career, Zeng's cumulative impact of 22 citations across just two publications reflects a focused and productive research trajectory with meaningful implications for the future of intelligent agricultural systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2