17 September 2024 in IEEE Geoscience and Remote Sensing Magazine
Ship detection and classification pose critical challenges in maritime surveillance and monitoring. On the one hand, they find applications in civilian domains, like fishery management, illegal immigrant monitoring, and marine rescue. On the other hand, ships are important targets in maritime combat. Ship detection and classification help to obtain timely maritime military intelligence that holds immense importance in seizing control of the maritime battlefield and ensuring the success of military operations [1], [2]. Remote sensing technology, facilitated by sensors mounted on platforms like satellites and airplanes, enables long-distance noncontact imaging of ground targets. It offers high timeliness, wide coverage, and low-cost accessibility and is not constrained by geographic conditions. Consequently, it has emerged as the primary method for monitoring vessels [4], [5].
25 October 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
As artificial intelligence continues to advance, deep learning has greatly contributed to the advancement of ship recognition using Synthetic Aperture Radar (SAR) images. Deep learning-based SAR ship recognition performance is largely dependent on the sample set used. SAR ship recognition datasets published in recent years, however, are most derived from a single SAR satellite sensor. It needs to be evaluated and analyzed carefully whether the model trained by a single satellite dataset can still achieve the same accuracy with different SAR satellites. The paper focuses on the following research to address these issues. Firstly, using multiple SAR satellite sensors, we create a new SAR ship dataset (named generalization performance evaluation dataset, GPED) containing multi-resolution and multi-polarization data to examine the generalization performance of the deep learning-based SAR ship recognition method. GPED and a marine target detection dataset (MTDD) are then used to evaluate and analyze the generalization performance of current mainstream deep learning methods. According to the the experiment results, the mean average accuracy (mAP) of the ship recognition model trained on GPED is generally higher than that of MTDD, which proves that GPED has a better generalization performance. Furthermore, SAR ship detection datasets have more samples than ship recognition datasets, which inspired us to use transfer learning to transfer knowledge from ship detection to ship recognition. In this paper, a method for ship recognition based on transfer learning that utilizes the knowledge gained from the ship detection task is proposed. The method includes two modules: pretraining module and fine-tuning module. It can apply samples of unlabeled ship types to ship recognition, thus reducing the number of labeled samples that are required for ship recognition. The experimental results on GPED and MTDD show that our method can achieve good recognition performances.
3 October 2022 in IEEE Journal on Miniaturization for Air and Space Systems
In recent years, researchers have started to apply neural networks to ship detection of synthetic aperture radar (SAR). However, SAR images are difficult to acquire and interpret manually. Sufficient training samples cannot be obtained, which limits the performance of ship detection. Therefore, data enhancement has become an active means to handle the issue of insufficient samples. To evaluate the performance of diverse data enhancement methods, a variety of data enhancement methods is used to expand the ship samples in the SAR ship detection dataset, including rotation, shift, mirror, brightening, etc. Moreover, we used the combination of diverse data enhancement methods for experiments. Experiments were performed using the SSDD dataset. Based on the experimental results, we analyze the characteristics of diverse data enhancement methods.
11 March 2025 in IEEE Geoscience and Remote Sensing Letters
Rapid and accurate prediction of the sea clutter amplitude distribution is essential to improve target detection capability in SAR imagery. In this paper, we propose a multi-task learning network (SCA-Net) for sea clutter amplitude distribution prediction of SAR images. To reduce the number of model parameters, we design a shallow residual network structure with four residual blocks and replace the normal convolution with depthwise separable convolution in the residual blocks. The efficient channel attention (ECA) module is incorporated into each residual block to strengthen the model’s feature extraction capability. To validate the performance of the model, we construct a sea clutter amplitude distribution prediction dataset (SCADP) using GaoFen-3 wave mode data. The experimental results on the SCADP dataset indicate that the proposed method achieves the highest prediction accuracy, which proves that the method can effectively achieve integrated prediction of amplitude distribution types and parameters of sea clutter.
22 September 2023 in IEEE Geoscience and Remote Sensing Letters
The freeboard height of ship is a critical parameter that mirrors the ship’s load capacity and safety performance. However, research on the height of ship is less explored. This letter derives imaging differences between the top and bottom of the ship’s freeboard based on SAR imaging geometry and then establishes a ship-sea coupling scattering path model. Relying on the proposed model and the polarimetric synthetic aperture radar’s (PolSAR) capability to differentiate various scattering mechanisms, a method for retrieving the freeboard height of ships is proposed. This method primarily utilizes the total backscattering power SPAN and double-bounce scattering component (DBL) features of single-pass PolSAR data acquired with a single antenna. Finally, the proposed method is verified by the in-situ data and tested on different types of ships, such as cargo ships and bulk carriers, and the absolute relative error (ARE) of the retrieval results is less than 6.1%.