Phase filtering is a key step in the interferometric synthetic aperture radar (InSAR). Compared with the traditional method, the deep learning-based phase filtering method is superior in both accuracy and speed. However, traditional deep learning overly relies on huge data volume and is not interpretable and unstable for the purely data-driven and black-box properties. Therefore, a sparse model-based network for interferometric phase denoising (PD-SMNet) is proposed in this paper which joins conventional ISTA algorithm with the theory basis into a network structure. In contrast with the conventional network, the PD-SMNet is interpretable and more stable, and has good performance on small training samples. The experimental results on simulated and measured data show the proposed method significantly outperforms the previous three widely-used methods in both precision and speed. In addition, the proposed method has higher accuracy on small training sets than conventional deep learning.

In Interferometric Synthetic Aperture Radar (InSAR) data processing, phase filtering has a great impact on the accuracy of the resulting DEM and is therefore an inevitable step. Recently, convolutional neural networks are applied to InSAR phase filtering and show excellent performance, however, most of these deep learning-based methods do not make full use of the self-similarity of phase map, that is, pixels in different or far regions have a close relationship in values or distribution. In this paper, we propose a phase filtering method based on transformer network, which has the advantage of capturing the long-range dependency or exploiting the global features of the phase map, moreover, the deformable convolution is introduced to our method to further extract the local phase features. Experiments validate the efficiency and effectiveness of the proposed method to InSAR phase filtering.

The wide applications of 3-D synthetic aperture radar (SAR) imaging bring higher requirements for resolution and computational efficiency. The stepped frequency linear frequency modulated signal achieves high range resolution imaging by fusing multiple sub-pulses. However, its wide sub-pulse bandwidth results in a large amount of echo data to be processed, which results in a significant increase in the time consumption of the bandwidth synthesis algorithm. To achieve fast high range resolution 3-D SAR imaging, we propose an inter-array frequency-hopping linear frequency modulated signal model and a 3-D variable carrier frequency back projection algorithm. The proposed signal model transmits only one narrow bandwidth sub-pulse with hopping carrier frequency in each array element, which allows the receiver to sample the echo at a lower frequency. The lower sampling frequency and number of sub-pulse significantly reduce the amount of echo data. The proposed algorithm not only focuses the along-track direction and the cross-track direction of SAR image, but also fuses the low range resolution imaging results obtained by each sub-pulse into a high range resolution imaging result. Benefiting from the fusion of bandwidth synthesis algorithm and imaging algorithm, the computational efficiency is greatly improved. The experimental results demonstrate that the proposed algorithm achieves the comparable resolution and imaging quality as the ideal 3-D back projection (BP) algorithm with a large bandwidth chirp signal. Moreover, the time consumption of the proposed algorithm has been reduced to only 2.25% to 3.02% of that of the advanced high range resolution 3-D BP algorithm.

We present AliMe Avatar, a Vtuber designed for live-streaming sales in the E-commerce field. To support the emerging live shopping mode, the core of our digitial avatar is to enable customers to understand products and encourage customers to purchase in a virtual broadcasting room. Based on computer graphics & vision, natural language processing, and speech recognition & synthesis, our AI avatar is able to offer three kinds of key capabilities: custom appearance, product broadcasting, and multi-modal interaction. Currently, it has been launched online in the Taobao app, broadcasts 700+ hours and serves hundreds of thousands of customers per day. In this paper, we mainly focus on the product broadcasting part, demonstrate the system, present the underlying techniques, and share our experience in dealing with live-streaming E-commerce.

For traditional ground moving target indication, multiple channels are necessary to cancel ground clutter. For high-speed aircraft, slow moving target detection is a difficult problem because ground clutter cannot be eliminated completely by channel cancellation. In this paper, we propose a method, which is implemented by single-channel SAR images and improved Faster R-CNN, to detect the moving target and the stationary target. Synthetic aperture radar image which contains amplitude and phase information is put into the neural network to detect the moving and stationary target. We make a dataset to verify the availability of the proposed method. In order to increase the credibility of the dataset, we use FEKO to calculate the target electromagnetic scattering characteristics and use measured data scattering characteristics to generate the ground echo. The simulation proves that the proposed method has good performance in moving target detection and the performance of the proposed method is better than Faster R-CNN.

In this paper, an efficient registration algorithm for InSAR large scale image via discrete Fourier transform (DFT) model of the maximum correlation and image quadtree segmentation is proposed. In the scheme, a DFT-based sub-pixel registration model of InSAR complex images is constructed. Then, efficient sub-pixel registration for InSAR large-scale image is achieved by joint quadtree segmentation and DFT-based interpolation registration. Simulation and experimental results are presented to confirm the effectiveness of the proposed algorithm. The results demonstrate that the algorithm not only can achieve sub-pixel registration of InSAR large-scale image, but also has higher computational efficiency compared with the traditional maximum correlation registration method.