The landslide is a widespread and devastating natural disaster, posing serious threats to human life, security, and natural assets. Investigating efficient methods for accurate landslide detection with remote sensing images has important academic and practical implications. In this article, we proposed an LS-YOLO, a novel and effective model for landslide detection with remote sensing images. We first built a multi-scale landslide dataset (MSLD) and introduced random seeds in the data augmentation to increase data robustness. Considering the multi-scale characteristic of landslides in remote sensing images, a multi-scale feature extraction module is designed based on Efficient Channel Attention, Average Pooling, and Spatial Separable Convolution. To increase the receptive field of the model, dilated convolution is employed to the decoupled head. Specifically, the context enhancement module consisting of dilation convolutions is added to the decoupled head regression task branch, and then the improved decoupled head is to replace the coupled head in YOLOv5s. Extensive experiments show that our proposed model has high performance for multi-scale landslide detection, and outperforms other object detection models (Faster RCNN, SSD, EfficientDet-D0, YOLOv5s, YOLOv7, and YOLOX). Compared to the baseline model YOLOv5s, the AP of the LS-YOLO for detecting landslides has increased by 2.18% to 97.06%. The code and MSLD will be available at https://github.com/wenjieo/LS-YOLO.

Recently, deep learning-based methods for synthetic aperture radar (SAR) ship detection have made remarkable advancements. However, most existing methods primarily focus on achieving high detection accuracy by employing complex models, leading to an increase in computational costs. In addition, some methods do not adequately consider the impact of speckle noise interference. To address these challenges, we propose a multiscale ship detector, called visual saliency-lightweight ship detector (VS-LSDet), utilizing visual saliency and lightweight convolutional neural network. First, a visual saliency enhancement module is proposed as a preprocessing step to visually highlight the ships and weaken the impact of speckle noise in the image. Second, a lightweight backbone called ghost-shuffle net (GSNet) is designed. We introduce two types of ghost-shuffle blocks as basic convolution blocks by introducing ghost convolution to reduce the model complexity and channel shuffle operation to enhance the representation ability of the feature map. Then, we propose a multishape dilated convolution block incorporated into GSNet to enlarge its receptive fields, further improving the detector's performance. Finally, a hybrid attention module (HyAM) is proposed, it leverages both spatial and channel information within the feature map. HyAM can emphasize ship-related features while suppressing irrelevant features from the background in the feature map. Experimental results on public SAR ship datasets demonstrate that, compared to other ship detection methods, VS-LSDet achieves higher detection accuracy with lower model complexity. Specifically, on the SSDD dataset, the AP value of VS-LSDet is 97.51%, with 2.53 M parameters and 6.21 GFLOPs.

Object detection in UAV images is an important and challenging task for many applications, which often needs highly efficient detection algorithms to meet the accuracy and real-time requirements of the applications. In this paper, we investigate efficient mechanisms for detecting dense and small objects in UAV images. Specifically, 1) kernel K-means is used to obtain optimal anchors for dense and small object detection; 2) a spatial information enhancement module (SIE) is proposed to improve the detection accuracy of dense objects by extracting object spatial location information; 3) a Coord_C3 module is proposed to improve the receptive field of the network and to reduce the number of network parameters; 4) a small detection head is added in the Head of network and skip connections are employed in the Neck of network to improve the detection accuracy of small objects. Experimental results on the VisDrone2019, LEVIR-ship and Stanford Drone datasets show that our method not only has higher detection accuracy, but also runs faster compared to state-of-the-art detection methods.

As an atmospheric phenomenon, haze significantly reduces the visibility of outdoor and remote sensing images. Remote sensing and outdoor imaging have different mechanisms, existing dehazing methods are hard to be applied for both outdoor images and remote sensing images. In this paper, an efficient dehazing method is proposed which can be applied for both outdoor and remote sensing images. Dehazing methods based on image enhancement and image restoration methods are both advantages of the proposed method. To address the problem of inaccurate calculation of transmittance in existing methods, a Gaussian-weighted image fusion is introduced to obtain a refined transmittance. In addition, to solve the problem of image colour distortion after dehazing, an unsharp mask method is used to correct the dehazed image. Experiments on the synthetic dataset and real dataset show that the proposed method is able to dehaze both the outdoor and remote sensing images, and outperforms existing methods by visual inspection. On the RICE remote sensing image dataset, the proposed method has an image peak signal-to-noise ratio of 27.08 and structural similarity of 0.94, which are higher than other methods.

Ship detection is of great importance in territorial security and marine environmental protection. However, the accurate detection of small ships is a challenging task in complex environments mainly due to small ships having few features on remote sensing images. In this letter, we propose a small ship detection model based on YOLOv5s. The major features of the proposed model include: (1) a detection layer is added with a shallow feature map in the Head and skip connections are employed in the Neck to improve the detection accuracy of small ships; (2) a novel and effective Hybrid Spatial Pyramid Pooling (HSPP) is proposed to fuse the local and global information of feature maps; (3) a Coordinate Attention mechanism is employed in the Backbone to augment the representations of small ships, and EIOU is used as the loss function for bounding box regression to enhance the localization accuracy of the proposed model; (4) K-means++ algorithm is used to obtain more reasonable anchors for small ship detection. We introduce the multi-scale ship dataset OSSD, which contains 10133 images. Experiments on LEVIR-Ship and OSSD validate the effectiveness of our proposed model. The code and OSSD will be available at https://github.com/wenjieo/Improved-YOLOv5s-for-small-ship-detection.

Water body segmentation is an important tool for the hydrological monitoring of the Earth. With the rapid development of convolutional neural networks, semantic segmentation techniques have been used on remote sensing images to extract water bodies. However, some difficulties need to be overcome to achieve good results in water body segmentation, such as complex background, huge scale, water connectivity, and rough edges. In this study, a water body segmentation model (DUPnet) with dense connectivity and multi-scale pyramidal pools is proposed to rapidly and accurately extract water bodies from Gaofen satellite and Landsat 8 OLI (Operational Land Imager) images. The proposed method includes three parts: (1) a multi-scale spatial pyramid pooling module (MSPP) is introduced to combine shallow and deep features for small water bodies and to compensate for the feature loss caused by the sampling process; (2) dense blocks are used to extract more spatial features to DUPnet’s backbone, increasing feature propagation and reuse; (3) a regression loss function is proposed to train the network to deal with the unbalanced dataset caused by small water bodies. The experimental results show that the F1, MIoU, and FWIoU of DUPnet on the 2020 Gaofen dataset are 97.67%, 88.17%, and 93.52%, respectively, and on the Landsat River dataset, they are 96.52%, 84.72%, 91.77%, respectively.