Convolutional Neural Networks (CNNs), such as U-Net, have shown competitive performance in the automatic extraction of buildings from Very High-Resolution (VHR) aerial images. However, due to the unstable multi-scale context aggregation, the insufficient combination of multi-level features and the lack of consideration of the semantic boundary, most existing CNNs produce incomplete segmentation for large-scale buildings and result in predictions with huge uncertainty at building boundaries. This paper presents a novel network with a special boundary-aware loss embedded, called the Boundary-Aware Refined Network (BARNet), to address the gap above. The unique properties of the proposed BARNet are the gated-attention refined fusion unit, the denser atrous spatial pyramid pooling module, and the boundary-aware loss. The performance of the BARNet is tested on two popular data sets that include various urban scenes and diverse patterns of buildings. Experimental results demonstrate that the proposed method outperforms several state-of-the-art approaches in both visual interpretation and quantitative evaluations.
Vehicle targets in unmanned aerial vehicle (UAV) images are generally small, so a significant amount of detailed information on targets may be lost after neural computing, which leads to the poor performances of the existing recognition algorithms. Based on convolutional neural networks that utilize the YOLOv3 algorithm, this article focuses on the development of a quick automatic vehicle detection method for UAV images. First, a vehicle dataset for target recognition is constructed. Then, a novel YOLOv3 vehicle detection framework is proposed according to the following characteristics: The vehicle targets in the UAV image are relatively small and dense. The average precision (AP) increased by 5.48%, from 92.01% to 97.49%, which still remains the rather high processing speed of the YOLO network. Finally, the proposed framework is tested using three datasets: COWC, VEDAI, and CAR. The experimental results demonstrate that our method had a better detection capability.
8 April 2021 in Journal of Applied Polymer Science
As an inevitable phenomenon in most optical remote-sensing images, the effect of shadows is prominent in urban scenes. Shadow detection is critical for exploiting shadows and recovering the distorted information. Unfortunately, in general, automatic shadow detection methods for urban aerial images cannot achieve satisfactory performance due to the limitation of feature patterns and the lack of consideration of non-local contextual information. To address this challenging problem, the global-spatial-context-attention (GSCA) module was developed to self-adaptively aggregate all global contextual information over the spatial dimension for each pixel in this paper. The GSCA module was embedded into a modified U-shaped encoder–decoder network that was derived from the UNet network to output the final shadow predictions. The network was trained on a newly created shadow detection dataset, and the binary cross-entropy (BCE) loss function was modified to enhance the training procedure. The performance of the proposed method was evaluated on several typical urban aerial images. Experiment results suggested that the proposed method achieved a better trade-off between automaticity and accuracy. The F1-score, overall accuracy, balanced-error-rate, and intersection-over-union metrics of the proposed method were higher than those of other state-of-the-art shadow detection methods.
11 December 2020 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Remote sensing image change detection method plays a great role in land cover research, disaster assessment, medical diagnosis, video surveillance and other fields, so it has attracted wide attention. Based on a small sample data set from SZTAKI AirChange Benchmark Set, in order to solve the problem that the deep learning network needs a large number of samples, this work firstly uses non generative sample augmentation method and generative sample augmentation method based on DCGAN (Deep Convolutional Generative Adversarial Networks), and then constructs a remote sensing image change detection model based on an improved DeepLabv3+ network. This model can realize end-to-end training and prediction of remote sensing image change detection with sub-pixel convolution. Finally, Landsat 8, Google Earth, and OSCD (Onera Satellite Change Detection) dataset are used to verify the generalization performance of this network. The experimental results show that the improved network accuracy is 95.1% and the generalization performance is acceptable.
In agricultural remote sensing monitoring, the quality of optical remote sensing image data acquisition is often affected by climate, and the acquired satellite imagery results usually contain cloud information, which can lead to a lack of ground data information. Unlike thick clouds, the semi-transparent nature of thin clouds prevents thin clouds from completely obscuring the ground scene. In order to remove thin clouds in the cultivated land and restore the real ground information as much as possible, we proposed a cloud removal method of spatial information fusion self-attention generative adversarial network (SI-SA GAN) based on multi-directional perceptual attention and self-attention mechanism. The proposed method identifies and focuses on cloud regions by using the spatial attention, channel attention, and self-attention mechanism, which can enhance image information. The modules of the discriminator utilize residual networks and self-attention non-local neural networks to guide the output of image information. The generative adversarial network (GAN) is applied to remove clouds and restore the corresponding irregular occlusion area according to the depth characteristics of the input information, and a gradient penalty is applied to improve the robustness of the generative network. In this paper, we compared the evaluation indexes of other advanced models, the qualitative and quantitative results of Sentinel-2A datasets and public RICE datasets confirmed that the proposed method could enhance the image quality effectively after cloud removal, and the model has excellent thin cloud removal performance with small-scale training data.