CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial Images
Instance segmentation of high-resolution aerial images is challenging when compared to object detection and semantic segmentation in remote sensing applications. It adopts boundary-aware mask predictions, instead of traditional bounding boxes, to locate the objects-of-interest in pixel-wise. Meanwhi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/14/2788 |
| _version_ | 1797526118959415296 |
|---|---|
| author | Xiangfeng Zeng Shunjun Wei Jinshan Wei Zichen Zhou Jun Shi Xiaoling Zhang Fan Fan |
| author_facet | Xiangfeng Zeng Shunjun Wei Jinshan Wei Zichen Zhou Jun Shi Xiaoling Zhang Fan Fan |
| author_sort | Xiangfeng Zeng |
| collection | DOAJ |
| description | Instance segmentation of high-resolution aerial images is challenging when compared to object detection and semantic segmentation in remote sensing applications. It adopts boundary-aware mask predictions, instead of traditional bounding boxes, to locate the objects-of-interest in pixel-wise. Meanwhile, instance segmentation can distinguish the densely distributed objects within a certain category by a different color, which is unavailable in semantic segmentation. Despite the distinct advantages, there are rare methods which are dedicated to the high-quality instance segmentation for high-resolution aerial images. In this paper, a novel instance segmentation method, termed consistent proposals of instance segmentation network (CPISNet), for high-resolution aerial images is proposed. Following top-down instance segmentation formula, it adopts the adaptive feature extraction network (AFEN) to extract the multi-level bottom-up augmented feature maps in design space level. Then, elaborated RoI extractor (ERoIE) is designed to extract the mask RoIs via the refined bounding boxes from proposal consistent cascaded (PCC) architecture and multi-level features from AFEN. Finally, the convolution block with shortcut connection is responsible for generating the binary mask for instance segmentation. Experimental conclusions can be drawn on the iSAID and NWPU VHR-10 instance segmentation dataset: (1) Each individual module in CPISNet acts on the whole instance segmentation utility; (2) CPISNet* exceeds vanilla Mask R-CNN 3.4%/3.8% <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> on iSAID validation/test set and 9.2% <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> on NWPU VHR-10 instance segmentation dataset; (3) The aliasing masks, missing segmentations, false alarms, and poorly segmented masks can be avoided to some extent for CPISNet; (4) CPISNet receives high precision of instance segmentation for aerial images and interprets the objects with fitting boundary. |
| first_indexed | 2024-03-10T09:24:42Z |
| format | Article |
| id | doaj.art-6457186517294aa7a0b76323613d4c3c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T09:24:42Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6457186517294aa7a0b76323613d4c3c2023-11-22T04:52:23ZengMDPI AGRemote Sensing2072-42922021-07-011314278810.3390/rs13142788CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial ImagesXiangfeng Zeng0Shunjun Wei1Jinshan Wei2Zichen Zhou3Jun Shi4Xiaoling Zhang5Fan Fan6School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaInstance segmentation of high-resolution aerial images is challenging when compared to object detection and semantic segmentation in remote sensing applications. It adopts boundary-aware mask predictions, instead of traditional bounding boxes, to locate the objects-of-interest in pixel-wise. Meanwhile, instance segmentation can distinguish the densely distributed objects within a certain category by a different color, which is unavailable in semantic segmentation. Despite the distinct advantages, there are rare methods which are dedicated to the high-quality instance segmentation for high-resolution aerial images. In this paper, a novel instance segmentation method, termed consistent proposals of instance segmentation network (CPISNet), for high-resolution aerial images is proposed. Following top-down instance segmentation formula, it adopts the adaptive feature extraction network (AFEN) to extract the multi-level bottom-up augmented feature maps in design space level. Then, elaborated RoI extractor (ERoIE) is designed to extract the mask RoIs via the refined bounding boxes from proposal consistent cascaded (PCC) architecture and multi-level features from AFEN. Finally, the convolution block with shortcut connection is responsible for generating the binary mask for instance segmentation. Experimental conclusions can be drawn on the iSAID and NWPU VHR-10 instance segmentation dataset: (1) Each individual module in CPISNet acts on the whole instance segmentation utility; (2) CPISNet* exceeds vanilla Mask R-CNN 3.4%/3.8% <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> on iSAID validation/test set and 9.2% <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> on NWPU VHR-10 instance segmentation dataset; (3) The aliasing masks, missing segmentations, false alarms, and poorly segmented masks can be avoided to some extent for CPISNet; (4) CPISNet receives high precision of instance segmentation for aerial images and interprets the objects with fitting boundary.https://www.mdpi.com/2072-4292/13/14/2788instance segmentationaerial imagesregion proposalsconvolutional neural networks |
| spellingShingle | Xiangfeng Zeng Shunjun Wei Jinshan Wei Zichen Zhou Jun Shi Xiaoling Zhang Fan Fan CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial Images Remote Sensing instance segmentation aerial images region proposals convolutional neural networks |
| title | CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial Images |
| title_full | CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial Images |
| title_fullStr | CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial Images |
| title_full_unstemmed | CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial Images |
| title_short | CPISNet: Delving into Consistent Proposals of Instance Segmentation Network for High-Resolution Aerial Images |
| title_sort | cpisnet delving into consistent proposals of instance segmentation network for high resolution aerial images |
| topic | instance segmentation aerial images region proposals convolutional neural networks |
| url | https://www.mdpi.com/2072-4292/13/14/2788 |
| work_keys_str_mv | AT xiangfengzeng cpisnetdelvingintoconsistentproposalsofinstancesegmentationnetworkforhighresolutionaerialimages AT shunjunwei cpisnetdelvingintoconsistentproposalsofinstancesegmentationnetworkforhighresolutionaerialimages AT jinshanwei cpisnetdelvingintoconsistentproposalsofinstancesegmentationnetworkforhighresolutionaerialimages AT zichenzhou cpisnetdelvingintoconsistentproposalsofinstancesegmentationnetworkforhighresolutionaerialimages AT junshi cpisnetdelvingintoconsistentproposalsofinstancesegmentationnetworkforhighresolutionaerialimages AT xiaolingzhang cpisnetdelvingintoconsistentproposalsofinstancesegmentationnetworkforhighresolutionaerialimages AT fanfan cpisnetdelvingintoconsistentproposalsofinstancesegmentationnetworkforhighresolutionaerialimages |