This letter proposes a rapid line-extraction (RLE) method for synthetic aperture radar (SAR) images. RLE first transforms an image in the space domain into an image in the frequency domain. Then, using the central-slice theorem, RLE skilfully maps the image in the frequency domain into a parameter space, which effectively accelerates the straight-line extraction process. Unlike the traditional Hough transform, RLE is performed directly on an edge-field image rather than on a binary edge map. Theoretical analysis proves the advantages of using the edge-field map. Notably, the computational complexity can be greatly reduced relative to the complexity of obtaining a binary edge map, and the method can efficiently avoid the negative influence of false edges in the binary edge map. More importantly, because speckle, clutter, and blurred edges in real-world images decrease the sharpness of peaks, edge-field images that include the strength and direction information of SAR images are adopted to reduce the diffusion of peaks and improve the detection accuracy. Experimental studies show that RLE works independently, is robust to noise, has low computational complexity, achieves high true-positive detection rates, and yields satisfactory detection precision.
20 March 2023 in IEEE Geoscience and Remote Sensing Letters
As one of main active learning methods, zero-shot target recognition with synthetic aperture radar (SAR) data has received considerable attention in recent years. Its goal is to distinguish new targets from the known classes without requiring additional training data. Existing zero-shot learning (ZSL) methods perform well on optical targets, but they fail to recognize zero-shot SAR targets. Due to the strong similarity of SAR targets between different classes, the ZSL task usually suffers from the distribution concentration problem. To tackle this problem, a Dual Branch Auto-Encoder (DBAE) network is proposed in this letter. DBAE effectively alleviates the distribution concentration problem by adding a classification assistance net. Its dual branch structure is specially designed for further improving the intra-class similarity and inter-class dissimilarity of SAR targets in the embedding space. By training with the defined hybrid loss function, DBAE automatically builds a stable embedding space. Extensive experiments on the public data set of Moving and Stationary Target Acquisition and Recognition (MSTAR) show that DBAE is of rational design and provides better or comparable ZSL recognition results.
23 September 2020 in IEEE Geoscience and Remote Sensing Letters
In real-world recognition tasks, it is difficult to collect training samples for all types of synthetic aperture radar (SAR) targets. The existing zero-shot learning (ZSL) methods use visual features and label semantics simultaneously to ensure a high recognition rate of unknown targets. However, meaningless information could influence the stability of the reference space. The negative impact will further drop the recognition rate of the ZSL methods. To overcome this problem, a new ZSL method is proposed by only adopting reflection similarity to recognize unknown targets. The proposed method adopts a triple-part network, in which the constructor-net and the supervisor-net jointly construct the reference space. It makes the space have a good representation and distinction. The third part of the triple-part network, as an interpreter-net, provides the uniformity of the target interpretation. The experimental results on moving and stationary target acquisition and recognition (MSTAR) data set show that the reference space with good quality can be obtained by discarding meaningless information. Especially, when the samples of known targets have slightly changed, the reference space still keeps good stability. Compared with the traditional ZSL methods, the recognition reliability of the proposed method on zero-shot targets is improved.
It is difficult to collect training samples for all types of synthetic aperture radar (SAR) targets. A realistic problem comes when unseen categories exist that are not included in training and benchmark data at the time of recognition, which is defined as open set recognition (OSR). Without the aid of side-information, generalized OSR methods used on ordinary optical images are usually not suitable for SAR images. In addition, OSR methods that require a large number of samples to participate in training are also not suitable for SAR images with the realistic situation of collection difficulty. In this regard, a task-oriented OSR method for SAR is proposed by distribution construction and relation measures to recognize targets of seen and unseen categories with limited training samples, and without any other simulation information. The method can judge category similarity to explain the unseen category. Distribution construction is realized by the graph convolutional network. The experimental results on the MSTAR dataset show that this method has a good recognition effect for the targets of both seen and unseen categories and excellent interpretation ability for unseen targets. Specifically, while recognition accuracy for seen targets remains above 95%, the recognition accuracy for unseen targets reaches 67% for the three-type classification problem, and 53% for the five-type classification problem.
2 November 2020 in IEEE Transactions on Geoscience and Remote Sensing
Edge detection is a critical component of synthetic aperture radar (SAR) image interpretation. Due to serious speckle noise, the core problems for SAR edge detection are how to keep a constant false alarm rate (CFAR) and how to achieve unbiased localization of the edges. Aiming at these problems, this article proposes a novel edge detector with a unique structure for noise-contaminated SAR images, which creatively integrates the difference operation with ratio operation (hence named as ``UDR: unbiased difference-ratio'' edge detector). Theoretical analysis proves that the difference operation effectively affords the UDR unbiased localization ability for both ideal and nonideal edges, and the ratio operation provides the UDR the property of CFAR under the influence of speckle noise. Experimental results on both simulated and real-world SAR images demonstrate the unbiased localization ability of the proposed UDR edge detection, insensitive to the changes of edge contrast, the width of the transition zone and the noise level. Benefited from the superior localization precision and insensitivity to noise, the average true positive detection rate of the proposed detector is improved to 95%, outperforming the compared state-of-the-art methods.
27 June 2018 in IEEE Geoscience and Remote Sensing Letters
In this letter, an antistretch edge detector has been proposed for synthetic aperture radar (SAR) images. Traditional detectors using anisotropy edge detection filters often incur severe edge stretch. If isotropy edge detection filters are used, the detectors usually have poor edge resolution. Hence, we skillfully fuse an anisotropy edge detection filter with an isotropy one. By embedding the fused filter into the routine ratio-based SAR edge detector, an antistretch edge detector is proposed. Benefiting from the fused edge detection filter, the proposed edge detector can obtain a good antistretch ability and keep a high edge resolution. A theoretical analysis indicates that the computational complexity of the proposed edge detector is close to conventional ratio-based edge detectors. The fusion operation will not affect the constant false alarm rate property. The receiver-operating-characteristic curves are used to objectively evaluate the proposed detector. Experimental studies show that the proposed detector has a lower false positive rate than the majority of detectors using only anisotropy filters or isotropy filters. Furthermore, the experimental results on simulated and real-world SAR images show that the proposed antistretch edge detector can obtain an accurate edge map.