Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image Segmentation
In recent years, the deep learning method based on fully convolution networks has proven to be an effective method for the semantic segmentation of remote sensing images (RSIs). However, the rich information and complex content of RSIs make networks training for segmentation more challenging. Specif...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9947207/ |
| _version_ | 1828179001033621504 |
|---|---|
| author | Jiaojiao Li Yuzhe Liu Jiachao Liu Rui Song Wei Liu Kailiang Han Qian Du |
| author_facet | Jiaojiao Li Yuzhe Liu Jiachao Liu Rui Song Wei Liu Kailiang Han Qian Du |
| author_sort | Jiaojiao Li |
| collection | DOAJ |
| description | In recent years, the deep learning method based on fully convolution networks has proven to be an effective method for the semantic segmentation of remote sensing images (RSIs). However, the rich information and complex content of RSIs make networks training for segmentation more challenging. Specifically, the observing distance between the space-borne cameras and the ground objects is extraordinarily far, resulting in that some smaller objects only occupy a few pixels in the image. However, due to the rapid degeneration of tiny objects during the training process, most algorithms cannot properly handle these common small objects in RSIs with satisfactory results. In this article, we propose a novel feature guide network with a context aggregation pyramid (CAP) for RSIs segmentation to conquer these issues. An innovative edge-guide feature transform module is designed to take advantage of the edge and body information of objects to strengthen edge contours and the internal consistency in homogeneous regions, which can explicitly enhance the representation of tiny objects and relieve the degradation of small objects. Furthermore, we design a CAP pooling strategy to adaptively capture optimal feature characterization that can assemble multiscale features according to the significance of different contexts. Extensive experiments on three large-scale remote sensing datasets demonstrate that our method not only can outperform the state-of-the-art methods for objects of different scales but can also achieve robust segmentation results, especially for tiny objects. |
| first_indexed | 2024-04-12T05:24:27Z |
| format | Article |
| id | doaj.art-3a96cd50b6ad4be69a5ac32851ac69f5 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-12T05:24:27Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-3a96cd50b6ad4be69a5ac32851ac69f52022-12-22T03:46:20ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01159900991210.1109/JSTARS.2022.32218609947207Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image SegmentationJiaojiao Li0https://orcid.org/0000-0002-0470-9469Yuzhe Liu1Jiachao Liu2Rui Song3https://orcid.org/0000-0002-2790-1752Wei Liu4Kailiang Han5https://orcid.org/0000-0003-4039-2160Qian Du6https://orcid.org/0000-0001-8354-7500State Key Laboratory of Integrated Service Networks, Xidian University, Xi'an, ChinaState Key Laboratory of Integrated Service Networks, Xidian University, Xi'an, ChinaState Key Laboratory of Integrated Service Networks, Xidian University, Xi'an, ChinaState Key Laboratory of Integrated Service Networks, Xidian University, Xi'an, ChinaState Key Laboratory of Geo-Information Engineering, Xi'an, ChinaKey Laboratory of Infrared System Detection and Imaging Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, ChinaDepartment of Electrical and Computer Engineering, Mississippi State University, Starkville, MS, USAIn recent years, the deep learning method based on fully convolution networks has proven to be an effective method for the semantic segmentation of remote sensing images (RSIs). However, the rich information and complex content of RSIs make networks training for segmentation more challenging. Specifically, the observing distance between the space-borne cameras and the ground objects is extraordinarily far, resulting in that some smaller objects only occupy a few pixels in the image. However, due to the rapid degeneration of tiny objects during the training process, most algorithms cannot properly handle these common small objects in RSIs with satisfactory results. In this article, we propose a novel feature guide network with a context aggregation pyramid (CAP) for RSIs segmentation to conquer these issues. An innovative edge-guide feature transform module is designed to take advantage of the edge and body information of objects to strengthen edge contours and the internal consistency in homogeneous regions, which can explicitly enhance the representation of tiny objects and relieve the degradation of small objects. Furthermore, we design a CAP pooling strategy to adaptively capture optimal feature characterization that can assemble multiscale features according to the significance of different contexts. Extensive experiments on three large-scale remote sensing datasets demonstrate that our method not only can outperform the state-of-the-art methods for objects of different scales but can also achieve robust segmentation results, especially for tiny objects.https://ieeexplore.ieee.org/document/9947207/Context aggregation pyramid (CAP)deep learningedge guideremote sensing images (RSIs)semantic segmentation |
| spellingShingle | Jiaojiao Li Yuzhe Liu Jiachao Liu Rui Song Wei Liu Kailiang Han Qian Du Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image Segmentation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Context aggregation pyramid (CAP) deep learning edge guide remote sensing images (RSIs) semantic segmentation |
| title | Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image Segmentation |
| title_full | Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image Segmentation |
| title_fullStr | Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image Segmentation |
| title_full_unstemmed | Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image Segmentation |
| title_short | Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image Segmentation |
| title_sort | feature guide network with context aggregation pyramid for remote sensing image segmentation |
| topic | Context aggregation pyramid (CAP) deep learning edge guide remote sensing images (RSIs) semantic segmentation |
| url | https://ieeexplore.ieee.org/document/9947207/ |
| work_keys_str_mv | AT jiaojiaoli featureguidenetworkwithcontextaggregationpyramidforremotesensingimagesegmentation AT yuzheliu featureguidenetworkwithcontextaggregationpyramidforremotesensingimagesegmentation AT jiachaoliu featureguidenetworkwithcontextaggregationpyramidforremotesensingimagesegmentation AT ruisong featureguidenetworkwithcontextaggregationpyramidforremotesensingimagesegmentation AT weiliu featureguidenetworkwithcontextaggregationpyramidforremotesensingimagesegmentation AT kailianghan featureguidenetworkwithcontextaggregationpyramidforremotesensingimagesegmentation AT qiandu featureguidenetworkwithcontextaggregationpyramidforremotesensingimagesegmentation |