Search

The classification of hyperspectral images (HSIs) using convolutional neural networks (CNNs) has recently drawn significant attention. However, it is important to address the potential overfitting problems that CNN-based methods suffer when dealing with HSIs. Unlike common natural images, HSIs are essentially three-order tensors which contain two spatial dimensions and one spectral dimension. As a result, exploiting both spatial and spectral information is very important for HSI classification. This paper proposes a new hand-crafted feature extraction method, based on multiscale covariance maps (MCMs), that is specifically aimed at improving the classification of HSIs using CNNs. The proposed method has the following distinctive advantages. First, with the use of covariance maps, the spatial and spectral information of the HSI can be jointly exploited. Each entry in the covariance map stands for the covariance between two different spectral bands within a local spatial window, which can absorb and integrate the two kinds of information (spatial and spectral) in a natural way. Second, by means of our multiscale strategy, each sample can be enhanced with spatial information from different scales, increasing the information conveyed by training samples significantly. To verify the effectiveness of our proposed method, we conduct comprehensive experiments on three widely used hyperspectral data sets, using a classical 2-D CNN (2DCNN) model. Our experimental results demonstrate that the proposed method can indeed increase the robustness of the CNN model. Moreover, the proposed MCMs+2DCNN method exhibits better classification performance than other CNN-based classification strategies and several standard techniques for spectral-spatial classification of HSIs. [ABSTRACT FROM AUTHOR]

Automatic remote sensing (RS) image to map translation is a crucial technology for intelligent tile map generation. Although existing methods based on a generative network (GAN) generated unannotated maps at a single level, they have limited capacity in handling multi-resolution map generation at different levels. To address the problem, we proposed a novel conditional scale-consistent generation network (CscGAN) to simultaneously generate multi-level tile maps from multi-scale RS images, using only a single and unified model. Specifically, the CscGAN first uses the level labels and map annotations as prior conditions to guide hierarchical feature learning with different scales. Then, a multi-scale discriminator and two multi-scale generators are introduced to describe both high-resolution and low-resolution representations, aiming to improve the similarity of generated maps and thus produce high-quality multi-level tile maps. Meanwhile, a level classifier is designed for further exploring the characteristics of tile maps at different levels. Moreover, the CscGAN is optimized by jointly multi-scale adversarial loss, level classification loss, and scale-consistent loss in an end-to-end manner. Extensive experiments on multiple datasets and study areas demonstrate that the CscGAN outperforms the state-of-the-art methods in multi-level map translation, with great robustness and efficiency. [ABSTRACT FROM AUTHOR]

This paper deals with detecting small objects in remote sensing images from satellites or any aerial vehicle by utilizing the concept of image super-resolution for image resolution enhancement using a deep-learning-based detection method. This paper provides a rationale for image super-resolution for small objects by improving the current super-resolution (SR) framework by incorporating a cyclic generative adversarial network (GAN) and residual feature aggregation (RFA) to improve detection performance. The novelty of the method is threefold: first, a framework is proposed, independent of the final object detector used in research, i.e., YOLOv3 could be replaced with Faster R-CNN or any object detector to perform object detection; second, a residual feature aggregation network was used in the generator, which significantly improved the detection performance as the RFA network detected complex features; and third, the whole network was transformed into a cyclic GAN. The image super-resolution cyclic GAN with RFA and YOLO as the detection network is termed as SRCGAN-RFA-YOLO, which is compared with the detection accuracies of other methods. Rigorous experiments on both satellite images and aerial images (ISPRS Potsdam, VAID, and Draper Satellite Image Chronology datasets) were performed, and the results showed that the detection performance increased by using super-resolution methods for spatial resolution enhancement; for an IoU of 0.10, AP of 0.7867 was achieved for a scale factor of 16. [ABSTRACT FROM AUTHOR]

Remote-sensing time-series datasets are significant for global change research and a better understanding of the Earth. However, remote-sensing acquisitions often provide sparse time series due to sensor resolution limitations and environmental factors such as cloud noise for optical data. Image transformation is the method that is often used to deal with this issue. This paper considers the deep convolution networks to learn the complex mapping between sequence images, called adaptive filter generation network (AdaFG), convolution long short-term memory network (CLSTM), and cycle-consistent generative adversarial network (CyGAN) for construction of sequence image datasets. AdaFG network uses a separable 1D convolution kernel instead of 2D kernels to capture the spatial characteristics of input sequence images and then is trained end-to-end using sequence images. CLSTM network can map between different images using the state information of multiple time-series images. CyGAN network can map an image from a source domain to a target domain without additional information. Our experiments, which were performed with unmanned aerial vehicle (UAV) and Landsat-8 datasets, show that the deep convolution networks are effective to produce high-quality time-series image datasets, and the data-driven deep convolution networks can better simulate complex and diverse nonlinear data information. [ABSTRACT FROM AUTHOR]

Clouds are one of the most serious disturbances when using satellite imagery for ground observations. The semi-translucent nature of thin clouds provides the possibility of 2D ground scene reconstruction based on a single satellite image. In this paper, we propose an effective framework for thin cloud removal involving two aspects: a network architecture and a training strategy. For the network architecture, a Wasserstein generative adversarial network (WGAN) in YUV color space called YUV-GAN is proposed. Unlike most existing approaches in RGB color space, our method performs end-to-end thin cloud removal by learning luminance and chroma components independently, which is efficient at reducing the number of unrecoverable bright and dark pixels. To preserve more detailed features, the generator adopts a residual encoding–decoding network without down-sampling and up-sampling layers, which effectively competes with a residual discriminator, encouraging the accuracy of scene identification. For the training strategy, a transfer-learning-based method was applied. Instead of using either simulated or scarce real data to train the deep network, adequate simulated pairs were used to train the YUV-GAN at first. Then, pre-trained convolutional layers were optimized by real pairs to encourage the applicability of the model to real cloudy images. Qualitative and quantitative results on RICE1 and Sentinel-2A datasets confirmed that our YUV-GAN achieved state-of-the-art performance compared with other approaches. Additionally, our method combining the YUV-GAN with a transfer-learning-based training strategy led to better performance in the case of scarce training data. [ABSTRACT FROM AUTHOR]

The automatic detection of aircrafts from SAR images is widely applied in both military and civil fields, but there are still considerable challenges. To address the high variety of aircraft sizes and complex background information in SAR images, a new fast detection framework based on convolution neural networks is proposed, which achieves automatic and rapid detection of aircraft with high accuracy. First, the airport runway areas are detected to generate the airport runway mask and rectangular contour of the whole airport are generated. Then, a new deep neural network proposed in this paper, named Efficient Weighted Feature Fusion and Attention Network (EWFAN), is used to detect aircrafts. EWFAN integrates the weighted feature fusion module, the spatial attention mechanism, and the CIF loss function. EWFAN can effectively reduce the interference of negative samples and enhance feature extraction, thereby significantly improving the detection accuracy. Finally, the airport runway mask is applied to the detected results to reduce false alarms and produce the final aircraft detection results. To evaluate the performance of the proposed framework, large-scale Gaofen-3 SAR images with 1 m resolution are utilized in the experiment. The detection rate and false alarm rate of our EWFAN algorithm are 95.4% and 3.3%, respectively, which outperforms Efficientdet and YOLOv4. In addition, the average test time with the proposed framework is only 15.40 s, indicating satisfying efficiency of automatic aircraft detection. [ABSTRACT FROM AUTHOR]

Infrared small-object segmentation (ISOS) has a persistent trade-off problem—that is, which came first, recall or precision? Constructing a fine balance between of them is, au fond, of vital importance to obtain the best performance in real applications, such as surveillance, tracking, and many fields related to infrared searching and tracking. F1-score may be a good evaluation metric for this problem. However, since the F1-score only depends upon a specific threshold value, it cannot reflect the user's requirements according to the various application environment. Therefore, several metrics are commonly used together. Now we introduce F-area, a novel metric for a panoptic evaluation of average precision and F1-score. It can simultaneously consider the performance in terms of real application and the potential capability of a model. Furthermore, we propose a new network, called the Amorphous Variable Inter-located Network (AVILNet), which is of pliable structure based on GridNet, and it is also an ensemble network consisting of the main and its sub-network. Compared with the state-of-the-art ISOS methods, our model achieved an AP of 51.69%, F1-score of 63.03%, and F-area of 32.58% on the International Conference on Computer Vision 2019 ISOS Single dataset by using one generator. In addition, an AP of 53.6%, an F1-score of 60.99%, and F-area of 32.69% by using dual generators, with beating the existing best record (AP, 51.42%; F1-score, 57.04%; and F-area, 29.33%). [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have emerged as a relevant tool for the classification of remotely sensed hyperspectral images (HSIs), with convolutional neural networks (CNNs) being the current state-of-the-art in many classification tasks. However, deep CNNs present several limitations in the context of HSI supervised classification. Although deep models are able to extract better and more abstract features, the number of parameters that must be fine-tuned requires a large amount of training data (using small learning rates) in order to avoid the overfitting and vanishing gradient problems. The acquisition of labeled data is expensive and time-consuming, and small learning rates forces the gradient descent to use many small steps to converge, slowing down the runtime of the model. To mitigate these issues, this paper introduces a new deep CNN framework for spectral-spatial classification of HSIs. Our newly proposed framework introduces shortcut connections between layers, in which the feature maps of inferior layers are used as inputs of the current layer, feeding its own output to the rest of the the upper layers. This leads to the combination of various spectral-spatial features across layers that allows us to enhance the generalization ability of the network with HSIs. Our experimental results with four well-known HSI datasets reveal that the proposed deep&dense CNN model is able to provide competitive advantages in terms of classification accuracy when compared to other state-of-the-methods for HSI classification. [ABSTRACT FROM AUTHOR]