No Fear of the Dark: Image Retrieval Under Varying Illumination Conditions

Jenícek, Tomás; Chum, Ondřej

doi:10.1109/iccv.2019.00979

Cited by 30 publications

(16 citation statements)

References 30 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Khaliq et al (2019) draw their inspiration from NetVLAD and R-MAC, thereby combining VLAD description with ROI-extraction to show significant robustness to appearance-and viewpointvariation. Photometric-normalisation using both handcrafted and learning-based methodology is investigated by Jenicek and Chum (2019) to achieve illumination-invariance for place recognition.…”

Section: Literature Reviewmentioning

confidence: 99%

VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change

et al. 2021

View full text Add to dashboard Cite

Visual place recognition (VPR) is the process of recognising a previously visited place using visual information, often under varying appearance conditions and viewpoint changes and with computational constraints. VPR is related to the concepts of localisation, loop closure, image retrieval and is a critical component of many autonomous navigation systems ranging from autonomous vehicles to drones and computer vision systems. While the concept of place recognition has been around for many years, VPR research has grown rapidly as a field over the past decade due to improving camera hardware and its potential for deep learning-based techniques, and has become a widely studied topic in both the computer vision and robotics communities. This growth however has led to fragmentation and a lack of standardisation in the field, especially concerning performance evaluation. Moreover, the notion of viewpoint and illumination invariance of VPR techniques has largely been assessed qualitatively and hence ambiguously in the past. In this paper, we address these gaps through a new comprehensive open-source framework for assessing the performance of VPR techniques, dubbed “VPR-Bench”. VPR-Bench (Open-sourced at: https://github.com/MubarizZaffar/VPR-Bench) introduces two much-needed capabilities for VPR researchers: firstly, it contains a benchmark of 12 fully-integrated datasets and 10 VPR techniques, and secondly, it integrates a comprehensive variation-quantified dataset for quantifying viewpoint and illumination invariance. We apply and analyse popular evaluation metrics for VPR from both the computer vision and robotics communities, and discuss how these different metrics complement and/or replace each other, depending upon the underlying applications and system requirements. Our analysis reveals that no universal SOTA VPR technique exists, since: (a) state-of-the-art (SOTA) performance is achieved by 8 out of the 10 techniques on at least one dataset, (b) SOTA technique in one community does not necessarily yield SOTA performance in the other given the differences in datasets and metrics. Furthermore, we identify key open challenges since: (c) all 10 techniques suffer greatly in perceptually-aliased and less-structured environments, (d) all techniques suffer from viewpoint variance where lateral change has less effect than 3D change, and (e) directional illumination change has more adverse effects on matching confidence than uniform illumination change. We also present detailed meta-analyses regarding the roles of varying ground-truths, platforms, application requirements and technique parameters. Finally, VPR-Bench provides a unified implementation to deploy these VPR techniques, metrics and datasets, and is extensible through templates.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Learning-based localization methods have been proposed to solve both loop-closure detection [17], [56], [81], [83] and pose estimation [19], [37], [92]. They learn features with stable appearance over time [17], [22], [24], [58], [60], [64], [74], [91], train classifiers for place recognition [13], [31], [36], [39], [47], [94], and train CNNs to regress 2D-3D matches [9], [10], [76] or camera poses [19], [37], [92]. In this paper, we evaluate approaches based on learned robust local features [22], [24], [64], which constitute the state-of-the-art on our benchmarks.…”

Section: Related Workmentioning

confidence: 99%

Long-Term Visual Localization Revisited

Toft

Maddern²,

Torii

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

117

View full text Add to dashboard Cite

Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing conditions, including day-night changes, as well as weather and seasonal variations, while providing highly accurate six degree-of-freedom (6DOF) camera pose estimates. In this paper, we extend three publicly available datasets containing images captured under a wide variety of viewing conditions, but lacking camera pose information, with ground truth pose information, making evaluation of the impact of various factors on 6DOF camera pose estimation accuracy possible. We also discuss the performance of state-of-the-art localization approaches on these datasets. Additionally, we release around half of the poses for all conditions, and keep the remaining half private as a test set, in the hopes that this will stimulate research on long-term visual localization, learned local image features, and related research areas. Our datasets are available at visuallocalization.net, where we are also hosting a benchmarking server for automatic evaluation of results on the test set. The presented state-of-the-art results are to a large degree based on submissions to our server.

show abstract

“…These observations have led researchers to use dense local descriptors without a detection phase to address place recognition across day and night cycles [121]. An alternative is to preprocess the images with a learned photometric normalization to cope with significant illumination changes [191]. Notably, deep learned descriptors have shown better performance than hand-crafted ones in benchmarks with day/night conditions [69].…”

Section: E Adapting To Different Environmental Conditionsmentioning

confidence: 99%

A Survey on Deep Visual Place Recognition

2021

View full text Add to dashboard Cite

In recent years visual place recognition (VPR), i.e., the problem of recognizing the location of images, has received considerable attention from multiple research communities, spanning from computer vision to robotics and even machine learning. This interest is fueled on one hand by the relevance that visual place recognition holds for many applications and on the other hand by the unsolved challenge of making these methods perform reliably in different conditions and environments. This paper presents a survey of the state-of-the-art of research on visual place recognition, focusing on how it has been shaped by the recent advances in deep learning. We start discussing the image representations used in this task and how they have evolved from using hand-crafted to deep-learned features. We further review how metric learning techniques are used to get more discriminative representations, as well as techniques for dealing with occlusions, distractors, and shifts in the visual domain of the images. The survey also provides an overview of the specific solutions that have been proposed for applications in robotics and with aerial imagery. Finally the survey provides a summary of datasets that are used in visual place recognition, highlighting their different characteristics. INDEX TERMS Visual place recognition, image representation learning, deep learning.

show abstract

No Fear of the Dark: Image Retrieval Under Varying Illumination Conditions

Cited by 30 publications

References 30 publications

VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change

VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change

Long-Term Visual Localization Revisited

A Survey on Deep Visual Place Recognition

Contact Info

Product

Resources

About