Ship detection is an important but challenging task in the field of computer vision, partially due to the minuscule ship objects in optical remote sensing images and the interference of clouds occlusion and strong waves. Most of the current ship detection methods focus on boosting detection accuracy while they may ignore the detection speed. However, it is also indispensable to increase ship detection speed because it can provide timely ocean rescue and maritime surveillance. To solve the above problems, we propose an improved YOLOv3 (ImYOLOv3) based on attention mechanism, aiming to achieve the best trade-off between detection accuracy and speed. First, to realize high-efficiency ship detection, we adopt the off-the-shelf YOLOv3 as our basic detection framework due to its fast speed. Second, to boost the performance of original YOLOv3 for small ships, we design a novel and lightweight dilated attention module (DAM) to extract discriminative features for ship targets, which can be easily embedded into the basic YOLOv3. The integrated attention mechanism can help our model learn to suppress irrelevant regions while highlighting salient features useful for ship detection task. Furthermore, we introduce a multi-class ship dataset (MSD) and explicitly set supervised subclass according to the scales and moving states of ships. Extensive experiments verify the effectiveness and robustness of ImYOLOv3, and show that our method can accurately detect ships with different scales in different backgrounds, while at a real-time speed.

The spectral information contained in the hyperspectral images (HSI) distinguishes the intrinsic properties of a target from the background, which is widely used in remote sensing. However, the low imaging speed and high data redundancy caused by the high spectral resolution of imaging spectrometers limit their application in scenarios with the real-time requirement. In this work, we achieve the precise detection of camouflaged targets based on snapshot multispectral imaging technology and band selection methods in urban-related scenes. Specifically, the camouflaged target detection algorithm combines the constrained energy minimization (CEM) algorithm and the improved maximum between-class variance (OTSU) algorithm (t-OTSU), which is proposed to obtain the initial target detection results and adaptively segment the target region. Moreover, an object region extraction (ORE) algorithm is proposed to obtain a complete target contour that improves the target detection capability of multispectral images (MSI). The experimental results show that the proposed algorithm has the ability to detect different camouflaged targets by using only four bands. The detection accuracy is above 99%, and the false alarm rate is below 0.2%. The research achieves the effective detection of camouflaged targets and has the potential to provide a new means for real-time multispectral sensing in complex scenes.

Infrared small target detection is critical to infrared search and tracking systems. However, accurate and robust detection remains challenging due to the scarcity of target information and the complexity of clutter interference. Existing methods have some limitations in feature representation, leading to poor detection performance in complex scenes. Especially when there are sharp edges near the target or in cluster multitarget detection, the “target suppression” phenomenon tends to occur. To address this issue, we propose a robust unsupervised multifeature representation (RUMFR) method for infrared small target detection. On the one hand, robust unsupervised spatial clustering (RUSC) is designed to improve the accuracy of feature extraction; on the other hand, pixel-level multiple feature representation is proposed to fully utilize the target detail information. Specifically, we first propose the center-weighted interclass difference measure (CWIDM) with a trilayer design for fast candidate target extraction. Note that CWIDM also guides the parameter settings of RUSC. Then, the RUSC-based model is constructed to accurately extract target features in complex scenes. By designing the parameter adaptive strategy and iterative clustering strategy, RUSC can robustly segment cluster multitargets from complex backgrounds. Finally, RUMFR that fuses pixel-level contrast, distribution, and directional gradient features is proposed for better target representation and clutter suppression. Extensive experimental results show that our method has stronger feature representation capability and achieves better detection performance than several state-of-the-art methods.

Automatic ship detection in optical remote sensing images is of great significance due to its broad applications in maritime security and fishery control. Most ship detection algorithms utilize a single-band image to design low-level and hand-crafted features, which are easily influenced by interference like clouds and strong waves and not robust for large-scale variation of ships. In this paper, we propose a novel coarse-to-fine ship detection method based on discrete wavelet transform (DWT) and a deep residual dense network (DRDN) to address these problems. First, multi-spectral images are adopted for sea-land segmentation, and an enhanced DWT is employed to quickly extract ship candidate regions with missing alarms as low as possible. Second, panchromatic images with clear spatial details are used for ship classification. Specifically, we propose the local residual dense block (LRDB) to fully extract semantic feature via local residual connection and densely connected convolutional layers. DRDN mainly consists of four LRDBs and is designed to further remove false alarms. Furthermore, we exploit the multiclass classification strategy, which can overcome the large intra-class difference of targets and identify ships of different sizes. Extensive experiments demonstrate that the proposed method has high robustness in complex image backgrounds and achieves higher detection accuracy than other state-of-the-art methods.

Infrared small target detection (IRSTD) plays a vital role in various fields, especially in military early warning and maritime rescue. Its main goal is to accurately locate targets at long distances. Current deep learning-based methods mainly rely on mask-to-mask or box-to-box regression training approaches, making considerable progress in detection accuracy. However, these methods rely on large amounts of training data with expensive manual annotation. Although some researchers attempt to reduce the cost using single-point weak supervision (SPWS), the limited labeling accuracy significantly degrades the detection performance. To address these issues, we propose a novel point-to-point regression high-resolution dynamic network (P2P-HDNet), which can accurately locate the target center using only single-point annotation. Specifically, we first devise the high-resolution cross-feature extraction module (HCEM) to provide richer target detail information for the deep feature maps. Notably HCEM maintains high-resolution throughout the feature extraction process to minimize information loss. Then, the dynamic coordinate fusion module (DCFM) is devised to fully fuse the multidimensional features and enhance the positional sensitivity. Finally, we devise an adaptive target localization detection head (ATLDH) to further suppress clutter and improve the localization accuracy by regressing the Gaussian heatmap and adaptive non-maximal suppression strategy. Extensive experimental results show that P2P-HDNet can achieve better detection accuracy than the state-of-the-art (SOTA) methods with only single-point annotation. In addition, our code and datasets will be available at: https://github.com/Anton-Nrx/P2P-HDNet.