Image-similarity-based convolutional neural network for robot visual relocalization

• Main Authors: Wang, Li, Li, Ruifeng, Sun, Jingwen, Seah, Hock Soon, Quah, Chee Kwang, Zhao, Lijun, Tandianus, Budianto
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Visual Relocalization; CNN
• Online Access: https://hdl.handle.net/10356/147613
• Institution: Nanyang Technological University

Convolutional neural network (CNN)-based methods, which train an end-to-end model to regress a six degree of freedom (DoF) pose of a robot from a single red–green–blue (RGB) image, have been developed to overcome the poor robustness of robot visual relocalization recently. However, the pose precisio...