A Mountain Summit Recognition Method Based on Improved Faster R-CNN

Mountain summits are vital topographic feature points, which are essential for understanding landform processes and their impacts on the environment and ecosystem. Traditional summit detection methods operate on handcrafted features extracted from digital elevation model (DEM) data and apply paramet...

Full description

Saved in:
Bibliographic Details
Main Authors: Yueping Kong, Yun Wang, Song Guo, Jiajing Wang
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2021/8235108
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850232568418402304
author Yueping Kong
Yun Wang
Song Guo
Jiajing Wang
author_facet Yueping Kong
Yun Wang
Song Guo
Jiajing Wang
author_sort Yueping Kong
collection DOAJ
description Mountain summits are vital topographic feature points, which are essential for understanding landform processes and their impacts on the environment and ecosystem. Traditional summit detection methods operate on handcrafted features extracted from digital elevation model (DEM) data and apply parametric detection algorithms to locate mountain summits. However, these methods may no longer be effective to achieve desirable recognition results in small summits and suffer from the objective criterion lacking problem. Thus, to address these problems, we propose an improved Faster region-convolutional neural network (R-CNN) to accurately detect the mountain summits from DEM data. Based on Faster R-CNN, the improved network adopts a residual convolution block to replace the traditional part and adds a feature pyramid network (FPN) to fuse the features with adjacent layers to better address the mountain summit detection task. The residual convolution is employed to capture the deep correlation between visual and physical morphological features. The FPN is utilized to integrate the location and semantic information in the extracted feature maps to effectively represent the mountain summit area. The experimental results demonstrate that the proposed network could achieve the highest recall and precision without manually designed summit features and accurately identify small summits.
format Article
id doaj-art-0a7b5a9a0cef40d68152169b57ea2e56
institution OA Journals
issn 1076-2787
1099-0526
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-0a7b5a9a0cef40d68152169b57ea2e562025-08-20T02:03:08ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/82351088235108A Mountain Summit Recognition Method Based on Improved Faster R-CNNYueping Kong0Yun Wang1Song Guo2Jiajing Wang3School of Information and Control, Xi’an University of Architecture and Technology, Xi’an 710055, ChinaSchool of Information and Control, Xi’an University of Architecture and Technology, Xi’an 710055, ChinaSchool of Information and Control, Xi’an University of Architecture and Technology, Xi’an 710055, ChinaSchool of Information and Control, Xi’an University of Architecture and Technology, Xi’an 710055, ChinaMountain summits are vital topographic feature points, which are essential for understanding landform processes and their impacts on the environment and ecosystem. Traditional summit detection methods operate on handcrafted features extracted from digital elevation model (DEM) data and apply parametric detection algorithms to locate mountain summits. However, these methods may no longer be effective to achieve desirable recognition results in small summits and suffer from the objective criterion lacking problem. Thus, to address these problems, we propose an improved Faster region-convolutional neural network (R-CNN) to accurately detect the mountain summits from DEM data. Based on Faster R-CNN, the improved network adopts a residual convolution block to replace the traditional part and adds a feature pyramid network (FPN) to fuse the features with adjacent layers to better address the mountain summit detection task. The residual convolution is employed to capture the deep correlation between visual and physical morphological features. The FPN is utilized to integrate the location and semantic information in the extracted feature maps to effectively represent the mountain summit area. The experimental results demonstrate that the proposed network could achieve the highest recall and precision without manually designed summit features and accurately identify small summits.http://dx.doi.org/10.1155/2021/8235108
spellingShingle Yueping Kong
Yun Wang
Song Guo
Jiajing Wang
A Mountain Summit Recognition Method Based on Improved Faster R-CNN
Complexity
title A Mountain Summit Recognition Method Based on Improved Faster R-CNN
title_full A Mountain Summit Recognition Method Based on Improved Faster R-CNN
title_fullStr A Mountain Summit Recognition Method Based on Improved Faster R-CNN
title_full_unstemmed A Mountain Summit Recognition Method Based on Improved Faster R-CNN
title_short A Mountain Summit Recognition Method Based on Improved Faster R-CNN
title_sort mountain summit recognition method based on improved faster r cnn
url http://dx.doi.org/10.1155/2021/8235108
work_keys_str_mv AT yuepingkong amountainsummitrecognitionmethodbasedonimprovedfasterrcnn
AT yunwang amountainsummitrecognitionmethodbasedonimprovedfasterrcnn
AT songguo amountainsummitrecognitionmethodbasedonimprovedfasterrcnn
AT jiajingwang amountainsummitrecognitionmethodbasedonimprovedfasterrcnn
AT yuepingkong mountainsummitrecognitionmethodbasedonimprovedfasterrcnn
AT yunwang mountainsummitrecognitionmethodbasedonimprovedfasterrcnn
AT songguo mountainsummitrecognitionmethodbasedonimprovedfasterrcnn
AT jiajingwang mountainsummitrecognitionmethodbasedonimprovedfasterrcnn