scholarly journals HQ-ISNet: High-Quality Instance Segmentation for Remote Sensing Imagery

2020 ◽  
Vol 12 (6) ◽  
pp. 989 ◽  
Author(s):  
Hao Su ◽  
Shunjun Wei ◽  
Shan Liu ◽  
Jiadian Liang ◽  
Chen Wang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Prediction Accuracy ◽  
Semantic Segmentation ◽  
Remote Sensing Images ◽  
Feature Maps ◽  
High Quality ◽  
Remote Sensing Imagery ◽  
Instance Segmentation

Instance segmentation in high-resolution (HR) remote sensing imagery is one of the most challenging tasks and is more difficult than object detection and semantic segmentation tasks. It aims to predict class labels and pixel-wise instance masks to locate instances in an image. However, there are rare methods currently suitable for instance segmentation in the HR remote sensing images. Meanwhile, it is more difficult to implement instance segmentation due to the complex background of remote sensing images. In this article, a novel instance segmentation approach of HR remote sensing imagery based on Cascade Mask R-CNN is proposed, which is called a high-quality instance segmentation network (HQ-ISNet). In this scheme, the HQ-ISNet exploits a HR feature pyramid network (HRFPN) to fully utilize multi-level feature maps and maintain HR feature maps for remote sensing images’ instance segmentation. Next, to refine mask information flow between mask branches, the instance segmentation network version 2 (ISNetV2) is proposed to promote further improvements in mask prediction accuracy. Then, we construct a new, more challenging dataset based on the synthetic aperture radar (SAR) ship detection dataset (SSDD) and the Northwestern Polytechnical University very-high-resolution 10-class geospatial object detection dataset (NWPU VHR-10) for remote sensing images instance segmentation which can be used as a benchmark for evaluating instance segmentation algorithms in the high-resolution remote sensing images. Finally, extensive experimental analyses and comparisons on the SSDD and the NWPU VHR-10 dataset show that (1) the HRFPN makes the predicted instance masks more accurate, which can effectively enhance the instance segmentation performance of the high-resolution remote sensing imagery; (2) the ISNetV2 is effective and promotes further improvements in mask prediction accuracy; (3) our proposed framework HQ-ISNet is effective and more accurate for instance segmentation in the remote sensing imagery than the existing algorithms.

scholarly journals DETECTION OF ARTIFICIAL OBJECTS IN REMOTE SENSING IMAGE BASED ON DEEP LEARNING

2020 ◽  
Vol XLII-3/W10 ◽  
pp. 321-326 ◽  
Author(s):  
Y. Dai ◽  
J. S. Xiao ◽  
B. S. Yi ◽  
J. F. Lei ◽  
Z. Y. Du
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
High Resolution ◽  
Object Detection ◽  
Detection Method ◽  
Remote Sensing Image ◽  
Remote Sensing Images ◽  
Feature Maps ◽  
Aspect Ratios ◽  
Efficient Detection

Abstract. Aiming at multi-class artificial object detection in remote sensing images, the detection framework based on deep learning is used to extract and localize the numerous targets existing in very high resolution remote sensing images. In order to realize rapid and efficient detection of the typical artificial targets on the remote sensing image, this paper proposes an end-to-end multi-category object detection method in remote sensing image based on the convolutional neural network to solve several challenges, including dense objects and objects with arbitrary direction and large aspect ratios. Specifically, in this paper, the feature extraction process is improved by utilizing a more advanced backbone network with deeper layers and combining multiple feature maps including the high-resolution features maps with more location details and low-resolution feature maps with highly-abstracted information. And a Rotating Regional Proposal Network is adopted into the Faster R-CNN network to generate candidate object-like regions with different orientations and to improve the sensitivity to dense and cluttered objects. The rotation factor is added into the regional proposal network to control the generation of anchor box’s angle and to cover enough directions of typical man-made objects. Meanwhile, the misalignment caused by the two quantifications operations in the pooling process is eliminated and a convolution layer is appended before the fully connected layer of the final classification network to reduce the feature parameters and avoid overfitting. Compared with current generic object detection method, the proposed algorithm focus on the arbitrary oriented and dense artificial targets in remote sensing images. After comprehensive evaluation with several state-of-the-art object detection algorithms, our method is proved to be effective to detect multi-class artificial object in remote sensing image. Experiments demonstrate that the proposed method combines the powerful features extracted by the improved convolutional neural networks with multi-scale features and rotating region network is more accurate in the public DOTA dataset.

scholarly journals Improved Anchor-Free Instance Segmentation for Building Extraction from High-Resolution Remote Sensing Images

2020 ◽  
Vol 12 (18) ◽  
pp. 2910
Author(s):  
Tong Wu ◽  
Yuan Hu ◽  
Ling Peng ◽  
Ruonan Chen
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Semantic Segmentation ◽  
Aerial Images ◽  
Building Extraction ◽  
Remote Sensing Images ◽  
Highly Sensitive ◽  
Segmentation Methods ◽  
Speed And Accuracy ◽  
Instance Segmentation

Building extraction from high-resolution remote sensing images plays a vital part in urban planning, safety supervision, geographic databases updates, and some other applications. Several researches are devoted to using convolutional neural network (CNN) to extract buildings from high-resolution satellite/aerial images. There are two major methods, one is the CNN-based semantic segmentation methods, which can not distinguish different objects of the same category and may lead to edge connection. The other one is CNN-based instance segmentation methods, which rely heavily on pre-defined anchors, and result in the highly sensitive, high computation/storage cost and imbalance between positive and negative samples. Therefore, in this paper, we propose an improved anchor-free instance segmentation method based on CenterMask with spatial and channel attention-guided mechanisms and improved effective backbone network for accurate extraction of buildings in high-resolution remote sensing images. Then we analyze the influence of different parameters and network structure on the performance of the model, and compare the performance for building extraction of Mask R-CNN, Mask Scoring R-CNN, CenterMask, and the improved CenterMask in this paper. Experimental results show that our improved CenterMask method can successfully well-balanced performance in terms of speed and accuracy, which achieves state-of-the-art performance at real-time speed.

scholarly journals A Multi-Scale Spatial Attention Region Proposal Network for High-Resolution Optical Remote Sensing Imagery

2021 ◽  
Vol 13 (17) ◽  
pp. 3362
Author(s):  
Ruchan Dong ◽  
Licheng Jiao ◽  
Yan Zhang ◽  
Jin Zhao ◽  
Weiyan Shen
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Spatial Attention ◽  
Recall Rate ◽  
Optical Remote Sensing ◽  
Remote Sensing Images ◽  
Remote Sensing Imagery ◽  
Multi Scale ◽  
Backbone Network

Deep convolutional neural networks (DCNNs) are driving progress in object detection of high-resolution remote sensing images. Region proposal generation, as one of the key steps in object detection, has also become the focus of research. High-resolution remote sensing images usually contain various sizes of objects and complex background, small objects are easy to miss or be mis-identified in object detection. If the recall rate of region proposal of small objects and multi-scale objects can be improved, it will bring an improvement on the performance of the accuracy in object detection. Spatial attention is the ability to focus on local features in images and can improve the learning efficiency of DCNNs. This study proposes a multi-scale spatial attention region proposal network (MSA-RPN) for high-resolution optical remote sensing imagery. The MSA-RPN is an end-to-end deep learning network with a backbone network of ResNet. It deploys three novel modules to fulfill its task. First, the Scale-specific Feature Gate (SFG) focuses on features of objects by processing multi-scale features extracted from the backbone network. Second, the spatial attention-guided model (SAGM) obtains spatial information of objects from the multi-scale attention maps. Third, the Selective Strong Attention Maps Model (SSAMM) adaptively selects sliding windows according to the loss values from the system’s feedback, and sends the windowed samples to the spatial attention decoder. Finally, the candidate regions and their corresponding confidences can be obtained. We evaluate the proposed network in a public dataset LEVIR and compare with several state-of-the-art methods. The proposed MSA-RPN yields a higher recall rate of region proposal generation, especially for small targets in remote sensing images.

scholarly journals HRCNet: High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images

2020 ◽  
Vol 13 (1) ◽  
pp. 71
Author(s):  
Zhiyong Xu ◽  
Weicun Zhang ◽  
Tianxiang Zhang ◽  
Jiangyun Li
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
High Resolution ◽  
Spatial Information ◽  
Semantic Segmentation ◽  
Context Information ◽  
Remote Sensing Images ◽  
Global Context ◽  
Boundary Information ◽  
Extraction Stage

Semantic segmentation is a significant method in remote sensing image (RSIs) processing and has been widely used in various applications. Conventional convolutional neural network (CNN)-based semantic segmentation methods are likely to lose the spatial information in the feature extraction stage and usually pay little attention to global context information. Moreover, the imbalance of category scale and uncertain boundary information meanwhile exists in RSIs, which also brings a challenging problem to the semantic segmentation task. To overcome these problems, a high-resolution context extraction network (HRCNet) based on a high-resolution network (HRNet) is proposed in this paper. In this approach, the HRNet structure is adopted to keep the spatial information. Moreover, the light-weight dual attention (LDA) module is designed to obtain global context information in the feature extraction stage and the feature enhancement feature pyramid (FEFP) structure is promoted and employed to fuse the contextual information of different scales. In addition, to achieve the boundary information, we design the boundary aware (BA) module combined with the boundary aware loss (BAloss) function. The experimental results evaluated on Potsdam and Vaihingen datasets show that the proposed approach can significantly improve the boundary and segmentation performance up to 92.0% and 92.3% on overall accuracy scores, respectively. As a consequence, it is envisaged that the proposed HRCNet model will be an advantage in remote sensing images segmentation.

scholarly journals Efficient Patch-Wise Semantic Segmentation for Large-Scale Remote Sensing Images

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3232 ◽  
Author(s):  
Yan Liu ◽  
Qirui Ren ◽  
Jiahui Geng ◽  
Meng Ding ◽  
Jiangyun Li
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Large Scale ◽  
Semantic Segmentation ◽  
Remote Sensing Image ◽  
Training Data ◽  
Land Resources ◽  
Remote Sensing Images ◽  
Training Strategy ◽  
The Impact

Efficient and accurate semantic segmentation is the key technique for automatic remote sensing image analysis. While there have been many segmentation methods based on traditional hand-craft feature extractors, it is still challenging to process high-resolution and large-scale remote sensing images. In this work, a novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to segment common land resources. First, to handle the high-resolution image, the images are split as local patches and then a patch-wise network is built. Second, training data is preprocessed in several ways to meet the specific characteristics of remote sensing images, i.e., color imbalance, object rotation variations and lens distortion. Third, a multi-scale training strategy is developed to solve the severe scale variation problem. In addition, the impact of conditional random field (CRF) is studied to improve the precision. The proposed method was evaluated on a dataset collected from a capital city in West China with the Gaofen-2 satellite. The dataset contains ten common land resources (Grassland, Road, etc.). The experimental results show that the proposed algorithm achieves 54.96% in terms of mean intersection over union (MIoU) and outperforms other state-of-the-art methods in remote sensing image segmentation.

Sign in / Sign up

Export Citation Format

Share Document