Shuang-Wei Liu

About

Shuang-Wei Liu has made significant contributions to the intersection of computer vision and robotics, with a primary focus on object detection and recognition for robot-aided visual systems. Liu’s most cited work, “Multi-RPN Fusion-based Sparse PCA-CNN Approach to Object Detection and Recognition for Robot-aided Visual System” (2017, 3 citations), addresses a critical challenge in the field: the high misdetection rate of convolutional neural network (CNN)-based algorithms like Fast R-CNN and Faster R-CNN when object scales vary dramatically. By proposing a novel multi-region proposal network (RPN) fusion framework combined with sparse principal component analysis (PCA), Liu’s approach enhances detection robustness across scale variations, directly improving the reliability of robotic vision in real-world applications. This work demonstrates Liu’s expertise in deep learning architectures, feature extraction, and system integration for autonomous systems. While still early in their career, Liu’s research lays important groundwork for more adaptive and accurate visual perception in robotics, with potential implications for industrial automation, service robots, and autonomous navigation.

Research Focus

Key Achievements

Top Papers

1. 1
   Multi-RPN Fusion-based Sparse PCA-CNN Approach to Object Detection and Recognition for Robot-aided Visual System

   3 citations · 2017

Key Collaborators

Contact & Links