Deep learning features at scale for visual place recognition
Zetao Chen,Adam Jacobson,Niko Sünderhauf,Ben Upcroft,Lingqiao Liu,Chunhua Shen,Ian Reid,Michael Milford +7 more
- pp 3223-3230
Reads0
Chats0
TLDR
This paper trains, at large scale, two CNN architectures for the specific place recognition task and employs a multi-scale feature encoding method to generate condition- and viewpoint-invariant features.Abstract:
The success of deep learning techniques in the computer vision domain has triggered a range of initial investigations into their utility for visual place recognition, all using generic features from networks that were trained for other types of recognition tasks. In this paper, we train, at large scale, two CNN architectures for the specific place recognition task and employ a multi-scale feature encoding method to generate condition- and viewpoint-invariant features. To enable this training to occur, we have developed a massive Specific PlacEs Dataset (SPED) with hundreds of examples of place appearance change at thousands of different places, as opposed to the semantic place type datasets currently available. This new dataset enables us to set up a training regime that interprets place recognition as a classification problem. We comprehensively evaluate our trained networks on several challenging benchmark place recognition datasets and demonstrate that they achieve an average 10% increase in performance over other place recognition algorithms and pre-trained CNNs. By analyzing the network responses and their differences from pre-trained networks, we provide insights into what a network learns when training for place recognition, and what these results signify for future research in this area.read more
Citations
More filters
Posted Content
Self-Supervised Visual Place Recognition Learning in Mobile Robots.
Sudeep Pillai,John J. Leonard +1 more
TL;DR: This work shows that it is able to learn an appropriate distance metric for arbitrary real-valued image descriptors (including state-of-the-art CNN models), that is specifically geared for visual place recognition in mobile robots, by leveraging the synchronization between sensors.
Proceedings ArticleDOI
Long-Term Localization With Time Series Map Prediction for Mobile Robots in Dynamic Environments
TL;DR: Zhang et al. as discussed by the authors presented a long-term localization approach named ArmMPU (ARMA-based Map Prediction and Update) based on time series modeling and prediction.
Proceedings ArticleDOI
RGB-D Indoor Mapping Using Deep Features
TL;DR: An RGB-D SLAM system using a deep learning approach for mapping indoor environments is proposed, and a pre-trained CNN model with multiple random recursive structures is utilized to acquire deep features in an efficient way with no need for training.
Journal ArticleDOI
GSV-Cities: Toward Appropriate Supervised Visual Place Recognition
TL;DR: The GSV-Cities dataset as mentioned in this paper provides a large-scale dataset with accurate ground truth covering more than 40 cities across all continents over a 14-year period, covering weather, illumination, season, traffic, and occlusion.
Journal ArticleDOI
Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments
TL;DR: In this article , a multi-step approach of decreasing the precision of model parameters, combining with network depth reduction and fewer neurons in the classifier stage, was proposed to reduce the memory requirements and computational effort while maintaining state-of-the-art performance.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Posted Content
Rich feature hierarchies for accurate object detection and semantic segmentation
TL;DR: This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Posted Content
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia,Evan Shelhamer,Jeff Donahue,Sergey Karayev,Jonathan Long,Ross Girshick,Sergio Guadarrama,Trevor Darrell +7 more
TL;DR: Caffe as discussed by the authors is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.
Proceedings ArticleDOI
Dimensionality Reduction by Learning an Invariant Mapping
TL;DR: This work presents a method - called Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) - for learning a globally coherent nonlinear function that maps the data evenly to the output manifold.