Dongfei Xue
Papers
4
Total Citations
42
H-Index
3
About
Dongfei Xue is a researcher focused on advancing intelligent systems for indoor robotics and ambient intelligence. Their key research areas include indoor object recognition, deep learning for mobile robot navigation, and adaptive facial recognition systems. Xue’s major contributions lie in developing prior knowledge-based deep learning methods that significantly improve object detection precision in cluttered indoor environments, addressing a critical gap in mobile robot autonomy. Their most cited work, "Prior knowledge-based deep learning method for indoor object recognition and application" (2018, 22 citations), demonstrates how integrating contextual cues with convolutional neural networks enhances recognition accuracy. Complementing this, their 2017 study (15 citations) established a robust pipeline using pre-trained CNNs on public and private indoor datasets. Xue also pioneered adaptive ensemble approaches for ambient intelligence-assisted people search (2018, 3 citations) and hybrid online training systems that leverage semantic information for improved facial recognition in localized tasks (2016, 2 citations). These works collectively advance practical, real-world applications of AI in navigation and security, making Xue’s research foundational for students and engineers developing next-generation autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Indoor object recognition using pre-trained convolutional neural network15 citations · 2017
- 3
- 4