Qingchuan Liu

Universiti Teknologi MARA, Xingtai University

Papers

Total Citations

H-Index

About

Qingchuan Liu is a researcher focused on advancing computer vision for industrial robotics, particularly in object detection under challenging conditions. Their work addresses critical issues in automated grasping tasks, where multi-target objects are often partially occluded or stacked, hindering visual detection accuracy and real-time performance. Liu’s major contributions include developing improved versions of the Mask R-CNN algorithm, a leading deep learning framework for instance segmentation. In their 2023 paper, "An Improved Mask R-CNN Algorithm for High Object Detection Speed and Accuracy," they enhanced the model’s efficiency and precision, laying groundwork for practical robotic applications. Their 2024 study, "Partial Occlusion Object Detection Based on Improved Mask-RCNN," specifically tackles occlusion scenarios common in industrial settings, demonstrating how algorithmic refinements can boost detection reliability. While each paper has garnered 3 citations, these works represent early but impactful steps toward robust, real-time visual systems for manufacturing automation. Liu’s research bridges computer vision and robotics, offering solutions that could streamline production lines and reduce errors in object handling. Their focus on improving both speed and accuracy highlights a pragmatic approach to deploying AI in real-world environments, making their contributions valuable for students and engineers exploring vision-based robotic control.