SAR ship detection is essential for marine monitoring. Due to the high similarity between the harbor and the ship body on gray and texture features, the traditional methods are unable to achieve effective inshore ship detection. An improved Faster R-CNN based on MSER decision criterion for SAR ship detection in harbor is proposed in this paper. It is a ship detection method based on the combination of feature-based method and pixel-based method. Firstly, Faster R-CNN is used to generate region proposals. Then, replace the threshold decision criterion of Faster R-CNN with the maximum stability extremal region (MSER) method to reassess the generated region proposals with higher scores, aiming at improving the detection rate and reducing the false alarm rate simultaneously. Experimental results based on satellite-borne SAR data illustrate that the proposed method obtains excellent detection performance and low false alarm rate.
31 August 2022 in IEEE Transactions on Geoscience and Remote Sensing
Angular resolution of real aperture radar (RAR) can be improved using deconvolution methods to achieve enhanced target information based on the convolution relationship between target scatterings and an antenna pattern. However, depending on the wide scanning scope and dense sampling angular interval, the computational complexity of the deconvolution methods will drastically increase as the dimension of azimuthal data increases. In this article, to efficiently improve the angular resolution of RAR, a generalized adaptive asymptotic minimum variance (GAAMV) estimator that relies on a normalized projection array (NPA) model is proposed. On the one hand, the traditional convolution model of RAR is transformed into an NPA model to compress the data dimension. The proposed NPA model can normalize the signal model to make it independent of the sampling parameters. On the other hand, based on the NPA model, a GAAMV estimator is proposed to efficiently reconstruct the targets by adaptively updating each grid. Moreover, the penalty parameter is extended as a generalized case to improve its adaptability to different scenes. Based on the proposed model and method, the computational complexity can be decreased, especially for high-dimensional azimuthal data. Simulations and experimental data verify the proposed model and method.
20 August 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
A multistatic unmanned aerial vehicle-borne synthetic aperture radar (MuUAV-SAR) plays an important role in the applications of environmental monitoring and disaster warning because its distributed platforms can provide high-resolution imagery by fusing the multiple measurements. However, the flight paths of the multiple platforms are limited for such an unmanned system since the flight safety and the path length are basic conditions for guaranteeing the effective observation. This article first studies the observation signal model of the MuUAV-SAR imaging system and then analyzes the factors that determine the imaging resolution, while these factors are all determined by the flight path of unmanned aerial vehicles (UAVs). Second, an MuUAV-SAR imaging path planning problem is established as a constrained multiobjective optimization problem (CMOP), which considers the navigation and imaging performance of the UAV in the process of completing the path planning task in detail. For this CMOP, a heuristic search method is proposed to solve it, which can ensure that each step achieves local optimum, and it can also list all feasible solutions to meet the application requirements for selection. Finally, experimental results verify the effectiveness and practicability of the proposed heuristic path planning method.
28 September 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
With the development of economic globalization, coastal harbors have become an increasingly important gateway for international trade. Synthetic aperture radar (SAR) is an important microwave sensor with high resolution imaging capability. Harbor detection in SAR images is of great significance for timely obtaining coastal intelligence of a country. However, due to its complexity and diversity, harbor detection is challenging. In this article, a harbor detection method based on multidirectional one-dimensional scanning is proposed. First, discrete coastline to obtain control points, and multiple directions are selected at each control point, values of scanned pixels in each direction are recorded to obtain the representation vector. Then, a one-dimensional convolutional neural network for harbor features identification of representation vectors is designed. Finally, the harbors are located by clustering feature points. The proposed method can extract vectors to characterize the distribution of land, waters, and wharfs. Therefore, the problem of object detection in two-dimensional images is transformed into the identification of representation vectors. The method is effective for harbors with various scales and forms and has low computational complexity. Experimental results on spaceborne SAR images demonstrate the effectiveness of the proposed method.
23 October 2023 in IEEE Transactions on Geoscience and Remote Sensing
Multistatic airborne synthetic aperture radar (MuA-SAR) systems can achieve high-resolution imaging in a short time by fusing observation data from multiple radar platforms. However, its imaging quality relies on a rigorous design of the spatial configuration (SC) of each platform, mainly including the relative spatial separation and velocity. The rigorously designed SCs make it difficult to obtain in actual flight and weaken the flexibility advantage brought by the airborne platforms. Therefore, it is meaningful and necessary to explore a new SC design method to obtain relaxed SCs under the condition of ensuring imaging quality. In this paper, to relax the limitations of SC, an optimal design method for MuA-SAR SC is proposed. First, the relationship between the spatial configuration, wavenumber spectrum (WS) distribution, and imaging performance is established, and it visually reveals the configuration limitations. Second, an optimized search space of SC is defined by the peak to sidelobe ratio (PSLR) to relax the space to compromised configurations. Finally, the SC design problem is transformed into a constrained multiple objective optimization problem (CMOP) which is solved by the multiple objective particle swarm optimization (MOPSO) algorithm. The simulation results show that the proposed method can still obtain the optimized SC beyond the strictly restricted configuration space, which expands the SC limitations of the MuA-SAR system.
The resolution of bistatic SAR system is constrained by the signal bandwidth, distance, velocity and bistatic radar angle. The influence of topology structures and the strong coupling of echoes greatly limit the resolution of SAR images. And the problem of unbalanced two dimensional resolution brings difficulty and challenge to the target detection and recognition. Multi-static SAR can naturally form multiple pairs of bistatic SAR system and it fuses image information from multi-view by the design of topology structure to improve imaging resolution. To achieve optimal spatial resolution in all directions, the typical multi-static SAR geometric model is presented and the influence of topology structure on the two-dimensional resolution of bistatic and multi-static SAR is analyzed in this paper. Then, an equalization method to improve resolution for multi-static SAR is proposed. Finally, the simulation results validate the effectiveness of the proposed method.