scholarly journals Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration

2019 ◽  
Vol 33 ◽  
pp. 8034-8041 ◽  
Author(s):  
Kai Liu ◽  
Hua Wang ◽  
Fei Han ◽  
Hao Zhang
Keyword(s):  
Large Scale ◽  
Optimization Problem ◽  
Data Sets ◽  
Place Recognition ◽  
Benchmark Data ◽  
Localization And Mapping ◽  
Novel Method ◽  
Visual Place Recognition ◽  
Holistic Representation

Visual place recognition is essential for large-scale simultaneous localization and mapping (SLAM). Long-term robot operations across different time of the days, months, and seasons introduce new challenges from significant environment appearance variations. In this paper, we propose a novel method to learn a location representation that can integrate the semantic landmarks of a place with its holistic representation. To promote the robustness of our new model against the drastic appearance variations due to long-term visual changes, we formulate our objective to use non-squared ℓ2-norm distances, which leads to a difficult optimization problem that minimizes the ratio of the ℓ2,1-norms of matrices. To solve our objective, we derive a new efficient iterative algorithm, whose convergence is rigorously guaranteed by theory. In addition, because our solution is strictly orthogonal, the learned location representations can have better place recognition capabilities. We evaluate the proposed method using two large-scale benchmark data sets, the CMU-VL and Nordland data sets. Experimental results have validated the effectiveness of our new method in long-term visual place recognition applications.

Visual Place Recognition in Long-term and Large-scale Environment based on CNN Feature

2018 ◽  
Author(s):  
Jianliang Zhu ◽  
Yunfeng Ai ◽  
Bin Tian ◽  
Dongpu Cao ◽  
Sebastian Scherer
Keyword(s):  
Large Scale ◽  
Place Recognition ◽  
Visual Place Recognition

scholarly journals Variational Bayesian Approach to Condition-Invariant Feature Extraction for Visual Place Recognition

2021 ◽  
Vol 11 (19) ◽  
pp. 8976
Author(s):  
Junghyun Oh ◽  
Gyuho Eoh
Keyword(s):  
Large Scale ◽  
Environmental Changes ◽  
Place Recognition ◽  
Stochastic Variational Inference ◽  
Invariant Features ◽  
Variational Autoencoder ◽  
Model Condition ◽  
Visual Place Recognition ◽  
Perceptual Changes

As mobile robots perform long-term operations in large-scale environments, coping with perceptual changes becomes an important issue recently. This paper introduces a stochastic variational inference and learning architecture that can extract condition-invariant features for visual place recognition in a changing environment. Under the assumption that a latent representation of the variational autoencoder can be divided into condition-invariant and condition-sensitive features, a new structure of the variation autoencoder is proposed and a variational lower bound is derived to train the model. After training the model, condition-invariant features are extracted from test images to calculate the similarity matrix, and the places can be recognized even in severe environmental changes. Experiments were conducted to verify the proposed method, and the experimental results showed that our assumption was reasonable and effective in recognizing places in changing environments.

scholarly journals Towards a Robust Visual Place Recognition in Large-Scale vSLAM Scenarios Based on a Deep Distance Learning

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 310
Author(s):  
Liang Chen ◽  
Sheng Jin ◽  
Zhoujun Xia
Keyword(s):  
Distance Learning ◽  
Large Scale ◽  
Critical Role ◽  
Distance Constraint ◽  
Place Recognition ◽  
Learning Method ◽  
Localization And Mapping ◽  
Depth Analysis ◽  
Visual Place Recognition ◽  
Distance Relationship

The application of deep learning is blooming in the field of visual place recognition, which plays a critical role in visual Simultaneous Localization and Mapping (vSLAM) applications. The use of convolutional neural networks (CNNs) achieve better performance than handcrafted feature descriptors. However, visual place recognition is still a challenging task due to two major problems, i.e., perceptual aliasing and perceptual variability. Therefore, designing a customized distance learning method to express the intrinsic distance constraints in the large-scale vSLAM scenarios is of great importance. Traditional deep distance learning methods usually use the triplet loss which requires the mining of anchor images. This may, however, result in very tedious inefficient training and anomalous distance relationships. In this paper, a novel deep distance learning framework for visual place recognition is proposed. Through in-depth analysis of the multiple constraints of the distance relationship in the visual place recognition problem, the multi-constraint loss function is proposed to optimize the distance constraint relationships in the Euclidean space. The new framework can support any kind of CNN such as AlexNet, VGGNet and other user-defined networks to extract more distinguishing features. We have compared the results with the traditional deep distance learning method, and the results show that the proposed method can improve the performance by 19–28%. Additionally, compared to some contemporary visual place recognition techniques, the proposed method can improve the performance by 40%/36% and 27%/24% in average on VGGNet/AlexNet using the New College and the TUM datasets, respectively. It’s verified the method is capable to handle appearance changes in complex environments.

scholarly journals Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction

2018 ◽  
Vol 6 ◽  
pp. 451-465 ◽  
Author(s):  
Daniela Gerz ◽  
Ivan Vulić ◽  
Edoardo Ponti ◽  
Jason Naradowsky ◽  
Roi Reichart ◽  
...  
Keyword(s):  
Large Scale ◽  
Language Modeling ◽  
Language Models ◽  
Data Sets ◽  
High Type ◽  
Word Level ◽  
Level Information ◽  
Character Sequences ◽  
Novel Method ◽  
Morphologically Rich Languages

Neural architectures are prominent in the construction of language models (LMs). However, word-level prediction is typically agnostic of subword-level information (characters and character sequences) and operates over a closed vocabulary, consisting of a limited word set. Indeed, while subword-aware models boost performance across a variety of NLP tasks, previous work did not evaluate the ability of these models to assist next-word prediction in language modeling tasks. Such subword-level informed models should be particularly effective for morphologically-rich languages (MRLs) that exhibit high type-to-token ratios. In this work, we present a large-scale LM study on 50 typologically diverse languages covering a wide variety of morphological systems, and offer new LM benchmarks to the community, while considering subword-level information. The main technical contribution of our work is a novel method for injecting subword-level information into semantic word vectors, integrated into the neural language modeling training, to facilitate word-level prediction. We conduct experiments in the LM setting where the number of infrequent words is large, and demonstrate strong perplexity gains across our 50 languages, especially for morphologically-rich languages. Our code and data sets are publicly available.

scholarly journals Identifying global synchronies in marine zooplankton populations: issues and opportunities

2004 ◽  
Vol 61 (4) ◽  
pp. 445-456 ◽  
Author(s):  
R.Ian Perry ◽  
Harold P Batchelder ◽  
David L Mackas ◽  
Sanae Chiba ◽  
Edward Durbin ◽  
...  
Keyword(s):  
Large Scale ◽  
International Comparisons ◽  
Data Access ◽  
Ecosystem Change ◽  
Data Sets ◽  
Time Lags ◽  
Structural Constraints ◽  
Spatial And Temporal Scales ◽  
Marine Zooplankton

Abstract Analyses of the influences of climate variability on local zooplankton populations and those within ocean basins are relatively recent (past 5–10 years). What is lacking are comparisons of zooplankton population variability among the world's oceans, in contrast to such global comparisons of fish populations. This article examines the key questions, capabilities, and impediments for global comparisons of zooplankton populations using long-term (>10 year) data sets. The key question is whether global synchronies in zooplankton populations exist. If yes, then (i) to what extent are they driven by “bottom-up” (productivity) or “top-down” (predation) forcing; (ii) are they initiated by persistent forcing or by episodic events whose effects propagate through the system with different time-lags; and (iii) what proportion of the biological variance is caused directly by physical forcing and what proportion might be caused by non-linear instabilities in the biological dynamics (e.g. through trophodynamic links)? The capabilities are improving quickly that will enable global comparisons of zooplankton populations. Several long-term sampling programmes and data sets exist in many ocean basins, and the data are becoming more available. In addition, there has been a major philosophical change recently that now recognizes the value of continuing long-term zooplankton observation programmes. Understanding of life-history characteristics and the ecosystem roles of zooplankton are also improving. A first and critical step in exploring possible synchrony among zooplankton from geographically diverse regions is to recognize the limitations of the various data sets. There exist several impediments that must be surmounted before global comparisons of zooplankton populations can be realized. Methodological issues concerned with the diverse spatial and temporal scales of “monitored” planktonic populations are one example. Other problems include data access issues, structural constraints regarding funding of international comparisons, and lack of understanding by decision-makers of the value of zooplankton as indicators of ecosystem change. We provide recommendations for alleviating some of these impediments, and suggest a need for an easily understood example of global synchrony in zooplankton populations and the relation of those signals to large-scale climate drivers.

scholarly journals Direct Learning of Sparse Changes in Markov Networks by Density Ratio Estimation

2014 ◽  
Vol 26 (6) ◽  
pp. 1169-1197 ◽  
Author(s):  
Song Liu ◽  
John A. Quinn ◽  
Michael U. Gutmann ◽  
Taiji Suzuki ◽  
Masashi Sugiyama
Keyword(s):  
Network Structure ◽  
Large Scale ◽  
Optimization Problem ◽  
Density Ratio ◽  
Network Models ◽  
Structure Change ◽  
Data Sets ◽  
Markov Networks ◽  
Markov Network ◽  
Naive Approach

We propose a new method for detecting changes in Markov network structure between two sets of samples. Instead of naively fitting two Markov network models separately to the two data sets and figuring out their difference, we directly learn the network structure change by estimating the ratio of Markov network models. This density-ratio formulation naturally allows us to introduce sparsity in the network structure change, which highly contributes to enhancing interpretability. Furthermore, computation of the normalization term, a critical bottleneck of the naive approach, can be remarkably mitigated. We also give the dual formulation of the optimization problem, which further reduces the computation cost for large-scale Markov networks. Through experiments, we demonstrate the usefulness of our method.

scholarly journals NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences

2021 ◽  
Author(s):  
Diwei Sheng ◽  
Yuxiang Chai ◽  
Xinru Li ◽  
Chen Feng ◽  
Jianzhe Lin ◽  
...  
Keyword(s):  
Place Recognition ◽  
Data Anonymization ◽  
Visual Place Recognition

Multiscale Convolutional Descriptor Aggregation for Visual Place Recognition

2020 ◽  
Vol 2020 (10) ◽  
pp. 313-1-313-7
Author(s):  
Raffaele Imbriaco ◽  
Egor Bondarev ◽  
Peter H.N. de With
Keyword(s):  
Image Matching ◽  
Large Scale ◽  
Place Recognition ◽  
Aggregation Method ◽  
Local Descriptors ◽  
Multi Scale ◽  
Vector Construction ◽  
Visual Place Recognition ◽  
Different Sources ◽  
Geometric Verification

Visual place recognition using query and database images from different sources remains a challenging task in computer vision. Our method exploits global descriptors for efficient image matching and local descriptors for geometric verification. We present a novel, multi-scale aggregation method for local convolutional descriptors, using memory vector construction for efficient aggregation. The method enables to find preliminary set of image candidate matches and remove visually similar but erroneous candidates. We deploy the multi-scale aggregation for visual place recognition on 3 large-scale datasets. We obtain a Recall@10 larger than 94% for the Pittsburgh dataset, outperforming other popular convolutional descriptors used in image retrieval and place recognition. Additionally, we provide a comparison for these descriptors on a more challenging dataset containing query and database images obtained from different sources, achieving over 77% Recall@10.

Comparing lake sediment records of landscape macronutrient loadings with N14CP model simulations: 200 years of change in British lakes

2020 ◽  
Author(s):  
John Boyle ◽  
Ed Tipping ◽  
Jess Davies ◽  
Neil Rose ◽  
Simon Turner ◽  
...  
Keyword(s):  
Lake Sediment ◽  
Large Scale ◽  
Process Models ◽  
Mountain Lake ◽  
Scale Model ◽  
Data Sets ◽  
Empirical Reality ◽  
C Isotopes ◽  
Sediment Records

<p>To fully understand coupling between P and other macronutrients it is necessary to have both long-term data sets and process models, combining empirical reality with numerical simulation of coupling processes. Here, lake sediment records of N and P from four UK lakes are compared with model output from N14CP, a long-term, large-scale model of cycling and export of macronutrients from the landscape. The sediment records at the three lakes that have substantial lowland contributions reveal strongly increasing N and P loading through the late 19<sup>th</sup> century, with steady increases through the twentieth century. Corresponding changes in N and C isotopes are observed. However, the one mountain lake show maximum N and P loadings in the 19<sup>th</sup> century, with declines through the twentieth, consistent with a wholly different land use history. The N14CP model shows N and P increasing from mid 19<sup>th</sup> century for average lowland sites, in agreement with the lowland sediment records. The implications of these results for our knowledge about the history of P and N coupling and leaching from UK soils are discussed.</p>

Sign in / Sign up

Export Citation Format

Share Document