On the performance of ConvNet features for place recognition
Australian Centre for Robotic Vision · Queensland University of Technology
Abstract
After the incredible success of deep learning in the computer vision domain, there has been much interest in applying Convolutional Network (ConvNet) features in robotic fields such as visual navigation and SLAM. Unfortunately, there are fundamental differences and challenges involved. Computer vision datasets are very different in character to robotic camera data, real-time performance is essential, and performance priorities can be different. This paper comprehensively evaluates and compares the utility of three state-of-the-art ConvNets on the problems of particular relevance to navigation for robots; viewpoint-invariance and condition-invariance, and for the first time enables real-time place recognition…
Citation impact
- FWCI
- 834.30
- Percentile
- 100%
- References
- 50
Authors
5- NSNiko SünderhaufCorresponding
Australian Centre for Robotic Vision, Queensland University of Technology
- SSSareh Shirazi
Australian Centre for Robotic Vision, Queensland University of Technology
- FDFeras Dayoub
Australian Centre for Robotic Vision, Queensland University of Technology
- BUBen Upcroft
Queensland University of Technology, Australian Centre for Robotic Vision
- MMMichael Milford
Queensland University of Technology, Australian Centre for Robotic Vision
Topics & keywords
- Computer science
- Artificial intelligence
- Locality
- Convolutional neural network
- Categorization
- Domain (mathematical analysis)
- Machine learning
- Sketch recognition