Object Detection in Wideband SAR Images Using DiffusionDet

CFAR is a widely used algorithm for target detection in SAR images. The simplicity of computation and stable performance make it a key role in practice. However, for man-made target detection, conventional CFAR has a limited performance because of the non-adaptive processing window and the varieties of categories, sizes and structures of targets. In order to detect man-made targets with different size and complex structures in high resolution SAR images, an improved CFAR algorithm with an adaptive processing window named Adaptive-Window CFAR is proposed. A global guard window obtained by pre-detection adaptively is used to take place of the guard window in conventional CFAR makes AW -CFAR an algorithm with both adaptive threshold and adaptive processing window. In this case, the size of detectable targets is not fixed anymore and targets of different sizes and complex structures are detectable in AW-CF AR. Images with different resolutions and environments, which contain different categories of man-made targets, are used in the experiments. The experimental results show that the AW -CFAR inherits the simplicity of computation and stable performance of the conventional CFAR and has a better performance of man-made target detection in high resolution SAR images.

It is expensive and time-consuming to obtain a large number of labeled synthetic aperture radar (SAR) images. In the task of small training data size, the results of target detection on SAR images using deep network approaches are usually not ideal. In this study, considering that optical remote sensing images are much easier to be labeled than SAR images, we assume to have a large number of labeled optical remote sensing images and a small number of labeled SAR images with the similar scenes, propose to transfer knowledge from optical remote sensing images to SAR images, and develop a domain adaptive Faster R-CNN for SAR target detection with small training data size. In the proposed method, in order to make full use of the label information and realize more accurate domain adaptation knowledge transfer, an instance level domain adaptation constraint is used rather than feature level domain adaptation constraint. Specifically, generative adversarial network (GAN) constraint is applied as the domain adaptation constraint in the adaptation module after the proposals of Faster R-CNN to achieve instance level domain adaptation and learn the transferable features. The experimental results on the measured SAR image dataset show that the proposed method has higher detection accuracy in the task of SAR target detection with small training data size than the traditional Faster R-CNN.

Detection of distributed targets such as internal wave or ship wake on sea surface in Synthetic Aperture Radar (SAR) images is an important application of ocean microwave remote sensing. The chaotic characteristic of sea clutter gives some clues to targets detection on sea surface. Speckle, the inherent noise of SAR image, will affect the predictive accuracy of sea clutter adversely and reduce the detection performance of radar. In order to apply the chaotic characteristic of sea clutter to targets detection in SAR images more effectively, an improved chaos-based detection method is proposed in this paper. First, speckle noise is suppressed by undecimated wavelet transform (UWT), and then targets are detected on the basis of the chaotic characteristic of sea clutter from the denoised SAR images. Experimental results prove that the method proposed in this paper is effective for the distributed targets detection in SAR ocean images.

Target detection in the multiscale situation where there exit multiple ship targets with different sizes is a challenging task due to the mismatch of the sizes of ship targets and fixed windows. A new constant false alarm rate (CFAR) algorithm based on variable window for ship target detection in SAR images is proposed. First, the multiscale local contrast measure is introduced to estimate the ship target size without any prior knowledge about ships. Second, the size of neighborhood area is adaptively set and a transform algorithm is designed to enhance the contrast between targets and background. Finally, CFAR detection is implemented by adopting variable window to gain the accurate ship targets. Experimental results indicate that the proposed algorithm has better performance compared with other CFAR detection algorithms.

Monitoring aircraft using synthetic aperture radar (SAR) images is a very important task. Given its coherent imaging characteristics, there is a large amount of speckle interference in the image. This phenomenon leads to the scattering information of aircraft targets being masked in SAR images, which is easily confused with background scattering points. Therefore, automatic detection of aircraft targets in SAR images remains a challenging task. For this task, this paper proposes a framework for speckle reduction preprocessing of SAR images, followed by the use of an improved deep learning method to detect aircraft in SAR images. Firstly, to improve the problem of introducing artifacts or excessive smoothing in speckle reduction using total variation (TV) methods, this paper proposes a new nonconvex total variation (NTV) method. This method aims to ensure the effectiveness of speckle reduction while preserving the original scattering information as much as possible. Next, we present a framework for aircraft detection based on You Only Look Once v8 (YOLOv8) for SAR images. Therefore, the complete framework is called SAR-NTV-YOLOv8. Meanwhile, a high-resolution small target feature head is proposed to mitigate the impact of scale changes and loss of depth feature details on detection accuracy. Then, an efficient multi-scale attention module was proposed, aimed at effectively establishing short-term and long-term dependencies between feature grouping and multi-scale structures. In addition, the progressive feature pyramid network was chosen to avoid information loss or degradation in multi-level transmission during the bottom-up feature extraction process in Backbone. Sufficient comparative experiments, speckle reduction experiments, and ablation experiments are conducted on the SAR-Aircraft-1.0 and SADD datasets. The results have demonstrated the effectiveness of SAR-NTV-YOLOv8, which has the most advanced performance compared to other mainstream algorithms.

A new double-step fast CFAR scheme is proposed for multiple target detection in SAR images. The conventional multiple-cell based CFAR (MC-CFAR) detector is performed to find a potential target area. MC-CFAR carries out a quick search by which the CFAR sliding window is shifted by several cells for the reduced computational loads and it can also effectively reduce the small sized false alarm in the vicinity of the test cell. For the final target decision, the single-cell based CFAR detection is only applied to the pre-processed potential target areas. Using real-SAR image, the proposed CFAR scheme is compared with the conventional method in the sense of computational time and false alarm rate, which shows the faster computational speed and the lower false alarm rate.

Synthetic aperture radar (SAR) images suffer from speckle noise due to their imaging mechanism, which deteriorates image interpretability and hinders subsequent tasks like target detection and recognition. Traditional denoising methods fall short of the demands for high-quality SAR image processing, and deep learning approaches trained on synthetic datasets exhibit poor generalization because noise-free real SAR images are unattainable. To solve this problem and improve the quality of SAR images, a speckle noise suppression method based on subaperture decomposition and non-local low-rank tensor approximation is proposed. Subaperture decomposition yields azimuth-frame subimages with high global structural similarity, which are modeled as low-rank and formed into a 3D tensor. The tensor is decomposed to derive a low-dimensional orthogonal basis and low-rank representation, followed by non-local denoising and iterative regularization in the low-rank subspace for data reconstruction. Experiments on simulated and real SAR images demonstrate that the proposed method outperforms state-of-the-art techniques in speckle suppression, significantly improving SAR image quality.

With the rapid development of UAV and infrared imaging technology, the cost of UAV infrared imaging technology has decreased steadily. Small target detection technology in aerial infrared images has great potential for applications in many fields, especially in the field of traffic surveillance. Because of the low contrast and relatively limited feature information in infrared images compared to visible images, the difficulty involved in small road target detection in infrared aerial images has increased. To solve this problem, this study proposes a feature-enhanced attention and dual-GELAN net (FEADG-net) model. In this network model, the reliability and effectiveness of small target feature extraction is enhanced by a backbone network combined with low-frequency enhancement and a swin transformer. The multi-scale features of the target are fused using a dual-GELAN neck structure, and a detection head with the parameters of the auto-adjusted InnerIoU is constructed to improve the detection accuracy for small infrared targets. The viability of the method was proved using the HIT-UAV dataset and IRTS-AG dataset. According to a comparative experiment, the mAP50 of FEADG-net reached more than 90 percent, which was higher than that of any previous method and it met the real-time requirements. Finally, an ablation experiment was conducted to demonstrate that all three of the modules proposed in the method contributed to the improvement in the detection accuracy. This study not only designs a new algorithm for small road object detection in infrared remote sensing images from UAVs but also provides new ideas for small target detection in remote sensing images for other fields.

The existing Synthetic Aperture Radar (SAR) image target detection methods based on convolutional neural networks (CNNs) have achieved remarkable performance, but these methods require a large number of target-level labeled training samples to train the network. Moreover, some clutter is very similar to targets in SAR images with complex scenes, making the target detection task very difficult. Therefore, a SAR target detection network based on a semi-supervised learning and attention mechanism is proposed in this paper. Since the image-level label simply marks whether the image contains the target of interest or not, which is easier to be labeled than the target-level label, the proposed method uses a small number of target-level labeled training samples and a large number of image-level labeled training samples to train the network with a semi-supervised learning algorithm. The proposed network consists of a detection branch and a scene recognition branch with a feature extraction module and an attention module shared between these two branches. The feature extraction module can extract the deep features of the input SAR images, and the attention module can guide the network to focus on the target of interest while suppressing the clutter. During the semi-supervised learning process, the target-level labeled training samples will pass through the detection branch, while the image-level labeled training samples will pass through the scene recognition branch. During the test process, considering the help of global scene information in SAR images for detection, a novel coarse-to-fine detection procedure is proposed. After the coarse scene recognition determining whether the input SAR image contains the target of interest or not, the fine target detection is performed on the image that may contain the target. The experimental results based on the measured SAR dataset demonstrate that the proposed method can achieve better performance than the existing methods.

A novel target detection algorithm for synthetic aperture radar (SAR) images based on an improved visual attention method is proposed in this paper. With the development of SAR technology, target detection algorithms are confronted with many difficulties such as a complicated environment and scarcity of target information. Visual attention of the human visual system can make humans easily focus on key points in a complex picture, and the visual attention algorithm has been used in many fields. However, existing algorithms based on visual attention models cannot obtain satisfactory results for SAR image target detection under complex environmental conditions. After analysing the existing visual attention models, we combine the pyramid model of visual attention with singular value decomposition to simulate the human retina, which can make the visual attention model more suitable to the characteristics of SAR images. We introduce variance weighted information entropy into the model to optimize the detection results. The results obtained by the existing visual attention algorithm for target detection in SAR images yield a large number of false alarms and misses. However, the proposed algorithm can improve both the efficiency and accuracy of target detection in a complicated environment and under weak-target conditions. The experimental results validate the performance of our method.

Synthetic Aperture Radar (SAR) is widely used in ship target detection because of its ability to operate under various weather conditions. However, some target images are difficult to obtain and label, resulting in a small sample size, which limits the development of target detection. Aiming at the problem of ship target detection in small sample SAR images, domain knowledge is used to revise and enhance the basic model in this paper. Firstly, a lightweight convolutional neural network model more suitable for small-sample SAR image ship target classification is proposed, involving target pixel and aspect ratio as domain knowledge to correct the classification results. Then, for ship target detection in SAR images, the acquisition method of scale class domain knowledge is improved. Moreover, texture-related domain knowledge based on the gray level co-occurrence matrix is extracted and used as classification features for the model to revise the model. Finally, Marine Targets Classification Dataset (MTCD) and Marine Targets Detection Dataset (MTDD) are briefly introduced and adjusted to meet the requirements of this research through screening and modification. The test results on balanced MTDD and small-sample datasets demonstrate the effectiveness of domain knowledge in improving network performance.

: Sea clutter has a non-Rayleigh probability density when examined with a radar that has high resolution. This report discusses the properties of non- Rayleigh sea clutter and the detection of targets in non-Rayleigh sea clutter. The spatially varying clutter model is presented and is used to explain the non- Rayleigh nature of sea clutter. The variation of clutter distributions with various radar parameters such as frequency, pulse width, and polarization was determined, and the correlation properties of clutter were established. A way was developed of constructing a realistic realization of the sea surface on a computer, and the surface was used to predict non-Rayleigh clutter densities for various conditions and to indicate some finer points associated with the detection of small targets on the ocean's surface. Finally, various detectors were compared and the problems of pulse-to-pulse and scan-to-scan processing were analyzed.

In the field of infrared remote sensing, the problem of IR small target detection is still an important component part. Concerning infrared dim small target (IRDST) detection, firstly the infrared image is processed with DWT method to get the wavelet coefficients image, but the distribution characteristics, such as scales, frequencies, orientations of wavelet coefficients in different sub-bands are various, so wavelet image denoised by a single threshold criterion can not give a satisfying estimation. Based on this motivation, a spatially adaptive multi-model de-noising strategy (SAMMDS) based IRDST detection method is proposed in this paper, which can adjust thresholding strategy according to the distribution of noise in different scales and directions. Spatially adaptive BayesShrink (SABS) thresholding, traditional BayesShrink (BS) thresholding and generalized cross validation (GCV) thresholding are all adopted here to process each sub-band separately. After reconstructing the denoised wavelet image, a simple global thresholding is used to separate the background and target finally. Experimental results demonstrate that the proposed algorithm performs better than other typical wavelet methods for small target detection with various complex backgrounds.

Aiming at the challenges faced in ship target detection in complex large scenes of spaceborne SAR images, such as difficulties in detecting small targets, severe target occlusion, large amounts of SAR data, and limited computing power of airborne/spaceborne computing units, this paper proposes a lightweight ship detection model based on the improved YOLOv5 and realizes the edge deployment of the algorithm in combination with the Huawei Ascend hardware platform. The main contributions include: 1) Rotating target detection framework: By introducing an angle classification head, the problem of bounding box overlap of densely distributed ships near the shore is solved, and the ability to distinguish multi-directional targets is improved. 2) Lightweight network design: Using MobileNetV3 as the backbone network and combining it with a multi-granularity feature enhancement strategy, while compressing the number of model parameters, the detection performance of small targets is maintained. 3) Deployment optimization on the Ascend platform: Reconstructing operators based on the CANN heterogeneous computing architecture, realizing the pipeline optimization of the entire process of preprocessing-inference-post-processing, and achieving real-time detection efficiency on the Atlas 200DK chip. Experiments show that the average precision of the improved model on the public dataset SSDD is 1.74% higher than that of the baseline YOLOv5, and the number of parameters is reduced by 43%, providing a reusable technical path for the self-controllable edge computing of SAR ship detection.

Synthetic aperture radar (SAR) images often face problems such as coherent speckle noise, low contrast and complex target geometric characteristics due to their unique coherent imaging mechanism, which limits the performance of traditional target detection methods. This paper proposes a target detection technology based on deep learning guided by the physical mechanism of synthetic aperture radar (SAR) imaging. By integrating SAR electromagnetic scattering characteristics and data-driven features, a highly interpretable and high-precision detection model is constructed to solve the problems of missed alarms, false alarms and insufficient multi-category recognition accuracy in traditional methods in SAR image processing. By introducing an anchor-free mechanism, a dynamic sample allocation strategy and a spatial topological structure construction method, the network can effectively extract the physical and semantic features of SAR images and improve the accuracy and interpretability of target detection. Experimental results show that this method significantly improves the detection performance in complex scenes, providing technical support for the application of SAR images in environmental monitoring, disaster assessment and other fields.