Zhenzhen Song

Papers

Total Citations

256

H-Index

About

Dr. Zhenzhen Song is a leading researcher in agricultural robotics and computer vision, with a focused expertise in developing intelligent harvesting systems for specialty crops. Her work centers on overcoming the critical challenges of robotic fruit detection, canopy segmentation, and collision avoidance in complex orchard environments. Dr. Song’s major contributions include pioneering the application of deep learning architectures—such as Faster R-CNN with VGG16—for accurate kiwifruit detection in field images, achieving robust performance under varying lighting conditions. She further advanced the field by designing multi-class detection algorithms that enable robots to distinguish between fruit, branches, and trellis wires, significantly reducing collision risks during automated picking. Her research on canopy segmentation and wire reconstruction provides essential spatial mapping for robotic navigation. With her three most-cited papers accumulating over 250 citations, Dr. Song’s work directly addresses the labor-intensive nature of kiwifruit harvesting in China, where her studies support orchards producing approximately 70% of the nation’s crop. Her innovations are pivotal for transitioning from manual to automated harvesting, offering scalable solutions for global fruit production.