Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments

09/23/2019
by   Hanjiang Hu, et al.
0

Visual localization is a crucial problem in mobile robotics and autonomous driving. One solution is to retrieve images with known pose from a database for the localization of query images. However, in environments with drastically varying conditions (e.g. illumination changes, seasons, occlusion, dynamic objects), retrieval-based localization is severely hampered and becomes a challenging problem. In this paper, a novel domain-invariant feature learning method (DIFL) is proposed based on ComboGAN, a multi-domain image translation network architecture. By introducing a feature consistency loss (FCL) between the encoded features of the original image and translated image in another domain, we are able to train the encoders to generate domain-invariant features in a self-supervised manner. To retrieve a target image from the database, the query image is first encoded using the encoder belonging to the query domain to obtain a domain-invariant feature vector. We then preform retrieval by selecting the database image with the most similar domain-invariant feature vector. We validate the proposed approach on the CMU-Seasons dataset, where we outperform state-of-the-art learning-based descriptors in retrieval-based localization for high and medium precision scenarios.

READ FULL TEXT

page 1

page 4

research
09/16/2020

Domain-invariant Similarity Activation Map Metric Learning for Retrieval-based Long-term Visual Localization

Visual localization is a crucial component in the application of mobile ...
research
09/26/2018

Night-to-Day Image Translation for Retrieval-based Localization

Visual localization is a key step in many robotics pipelines, allowing t...
research
08/27/2020

Learning Condition Invariant Features for Retrieval-Based Localization from 1M Images

Image features for retrieval-based localization must be invariant to dyn...
research
10/01/2020

DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization

Long-Term visual localization under changing environments is a challengi...
research
04/24/2019

Bridging the Domain Gap for Ground-to-Aerial Image Matching

The visual entities in cross-view images exhibit drastic domain changes ...
research
03/31/2022

Semantic Pose Verification for Outdoor Visual Localization with Self-supervised Contrastive Learning

Any city-scale visual localization system has to overcome long-term appe...
research
11/08/2014

A Novel Approach to Develop a New Hybrid Technique for Trademark Image Retrieval

Trademark Image Retrieval is playing a vital role as a part of CBIR Syst...

Please sign up or login with your details

Forgot password? Click here to reset