Zongmin Liu
Papers
4
Total Citations
26
H-Index
3
About
Zongmin Liu is a robotics and computer vision researcher whose work sits at the intersection of intelligent perception, deep learning, and autonomous systems. His research primarily focuses on developing advanced detection and segmentation methods that enable robots to operate effectively in real-world environments, spanning both indoor service robotics and industrial welding automation. Liu's most recognized contributions include novel adaptations of deep learning architectures — most notably improvements to Mask RCNN and YOLOv8 — tailored for challenging detection scenarios. His 2023 work on multiple target detection for service robots in complex indoor scenes has garnered 12 citations, reflecting growing interest in assistive technologies for elderly care and healthcare support. Complementing this, his improved Mask RCNN framework further advances indoor scene understanding for autonomous robotic assistance. On the industrial side, Liu has made meaningful strides in robotic welding automation, developing a 3D visual perception-based path planning system for medium-thick plates and a highly accurate weld position segmentation method using BoT-YOLOv8, both published in 2025 and already accumulating citations. Collectively, his body of work demonstrates a sustained commitment to bridging cutting-edge computer vision research with practical robotic applications across healthcare and manufacturing domains.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4