Place Recognition: An Overview of Vision Perspective
Place recognition is one of the most fundamental topics in the computer-vision and robotics communities, where the task is to accurately and efficiently recognize the location of a given query image. Despite years of knowledge accumulated in this field, place recognition still remains an open proble...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/8/11/2257 |
id |
doaj-f822ace0a5844bd9ad53823dfc85cddc |
---|---|
record_format |
Article |
spelling |
doaj-f822ace0a5844bd9ad53823dfc85cddc2020-11-24T22:00:10ZengMDPI AGApplied Sciences2076-34172018-11-01811225710.3390/app8112257app8112257Place Recognition: An Overview of Vision PerspectiveZhiqiang Zeng0Jian Zhang1Xiaodong Wang2Yuming Chen3Chaoyang Zhu4College of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, Fujian, ChinaSchool of Science and Technology, Zhejiang International Studies University, Hangzhou 310023, Zhejiang, ChinaCollege of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, Fujian, ChinaCollege of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, Fujian, ChinaSchool of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, Zhejiang, ChinaPlace recognition is one of the most fundamental topics in the computer-vision and robotics communities, where the task is to accurately and efficiently recognize the location of a given query image. Despite years of knowledge accumulated in this field, place recognition still remains an open problem due to the various ways in which the appearance of real-world places may differ. This paper presents an overview of the place-recognition literature. Since condition-invariant and viewpoint-invariant features are essential factors to long-term robust visual place-recognition systems, we start with traditional image-description methodology developed in the past, which exploits techniques from the image-retrieval field. Recently, the rapid advances of related fields, such as object detection and image classification, have inspired a new technique to improve visual place-recognition systems, that is, convolutional neural networks (CNNs). Thus, we then introduce the recent progress of visual place-recognition systems based on CNNs to automatically learn better image representations for places. Finally, we close with discussions and mention of future work on place recognition.https://www.mdpi.com/2076-3417/8/11/2257place recognitionConvolutional Neural Networkfeature extractionbag-of-visual words (BoW)vector of locally aggregated descriptors (VLAD) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhiqiang Zeng Jian Zhang Xiaodong Wang Yuming Chen Chaoyang Zhu |
spellingShingle |
Zhiqiang Zeng Jian Zhang Xiaodong Wang Yuming Chen Chaoyang Zhu Place Recognition: An Overview of Vision Perspective Applied Sciences place recognition Convolutional Neural Network feature extraction bag-of-visual words (BoW) vector of locally aggregated descriptors (VLAD) |
author_facet |
Zhiqiang Zeng Jian Zhang Xiaodong Wang Yuming Chen Chaoyang Zhu |
author_sort |
Zhiqiang Zeng |
title |
Place Recognition: An Overview of Vision Perspective |
title_short |
Place Recognition: An Overview of Vision Perspective |
title_full |
Place Recognition: An Overview of Vision Perspective |
title_fullStr |
Place Recognition: An Overview of Vision Perspective |
title_full_unstemmed |
Place Recognition: An Overview of Vision Perspective |
title_sort |
place recognition: an overview of vision perspective |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2018-11-01 |
description |
Place recognition is one of the most fundamental topics in the computer-vision and robotics communities, where the task is to accurately and efficiently recognize the location of a given query image. Despite years of knowledge accumulated in this field, place recognition still remains an open problem due to the various ways in which the appearance of real-world places may differ. This paper presents an overview of the place-recognition literature. Since condition-invariant and viewpoint-invariant features are essential factors to long-term robust visual place-recognition systems, we start with traditional image-description methodology developed in the past, which exploits techniques from the image-retrieval field. Recently, the rapid advances of related fields, such as object detection and image classification, have inspired a new technique to improve visual place-recognition systems, that is, convolutional neural networks (CNNs). Thus, we then introduce the recent progress of visual place-recognition systems based on CNNs to automatically learn better image representations for places. Finally, we close with discussions and mention of future work on place recognition. |
topic |
place recognition Convolutional Neural Network feature extraction bag-of-visual words (BoW) vector of locally aggregated descriptors (VLAD) |
url |
https://www.mdpi.com/2076-3417/8/11/2257 |
work_keys_str_mv |
AT zhiqiangzeng placerecognitionanoverviewofvisionperspective AT jianzhang placerecognitionanoverviewofvisionperspective AT xiaodongwang placerecognitionanoverviewofvisionperspective AT yumingchen placerecognitionanoverviewofvisionperspective AT chaoyangzhu placerecognitionanoverviewofvisionperspective |
_version_ |
1725844964499259392 |