Name
Title | ||
|---|---|---|
Deep Learning Off-the-shelf Holistic Feature Descriptors for Visual Place Recognition in Challenging Conditions |
Abstract | ||
|---|---|---|
In this paper, we present a comprehensive study on the utility of deep learning feature extraction methods for visual place recognition task in three challenging conditions, appearance variation, viewpoint variation and combination of both appearance and viewpoint variation. We extensively compared the performance of convolutional neural network architectures with batch normalization layers in terms of fraction of the correct matches. These architectures are primarily trained for image classification and object detection problems and used as holistic feature descriptors for visual place recognition task. To verify effectiveness of our results, we utilized four real world datasets in place recognition. Our investigation demonstrates that convolutional neural network architectures coupled with batch normalization and trained for other tasks in computer vision outperform architectures which are specifically designed for place recognition tasks. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/MMSP48831.2020.9287063 | 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP) |
Keywords | DocType | ISSN |
off-the-shelf holistic feature descriptors,visual place recognition task,convolutional neural network architectures,batch normalization layers,image classification,object detection problems,deep learning feature extraction methods,computer vision | Conference | 2163-3517 |
ISBN | Citations | PageRank |
978-1-7281-9323-6 | 0 | 0.34 |
References | Authors | |
13 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Farid Aliajni | 1 | 0 | 0.34 |
| Esa Rahtu | 2 | 832 | 52.76 |