Shujuan Zhang
Papers
7
Total Citations
92
H-Index
6
About
Shujuan Zhang is a prominent researcher at the intersection of computer vision and precision agriculture, specializing in intelligent detection systems for fruit and crop recognition in complex real-world environments. Her work centers on developing lightweight, high-accuracy deep learning models — primarily adaptations of the YOLO (You Only Look Once) architecture — tailored to the unique challenges of automated agricultural harvesting and quality assessment. Zhang's most significant contributions include custom detection frameworks such as FPG-YOLO, YOLO-GEW, YOLO-RFEW, and YOLO-PEM, each engineered to address specific agricultural challenges: camouflaged fruits, fruit bagging, ripeness classification, and occluded targets in greenhouse or orchard settings. Her subjects span a diverse range of crops, including "Yuluxiang" pears, flat jujubes, muskmelons, "Okubo" peaches, and cucumbers — reflecting a broad commitment to advancing China's agricultural automation. With a cumulative citation count exceeding 90 across just seven recent publications, Zhang's research has gained rapid traction within the agricultural AI community. Her emphasis on deploying computationally efficient models suitable for embedded robotic systems makes her work particularly valuable for fruit-thinning and harvesting robot development, directly addressing labor shortages and quality control challenges facing modern horticulture.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7