The application of 3D scenes has gradually expanded in recent years. A 3D point cloud is unreliable when it is acquired because of the performance of the sensor. Therefore, it causes difficulties in utilization. Point cloud completion can reconstruct and restore sparse and incomplete point clouds to a more realistic shape. We propose a cyclic global guiding network structure and apply it to point cloud completion tasks. While learning the local details of the whole cloud, our network structure can play a guiding role and will not ignore the overall characteristics of the whole cloud. Based on global guidance, we propose a variety of fitting planes and layered folding attention modules to strengthen the local effect. We use the relationship between the point and the plane to increase the compatibility between the network learning and the original sparse point cloud. We use the attention mechanism of the layer overlay to strengthen the local effect between the encode and decode. Therefore, point clouds are more accurate. Our experiments indicate the effectiveness of our method on the ShapeNet, KITTI, and MVP datasets and are superior to other networks.

Stereo matching networks based on deep learning are widely developed and can obtain excellent disparity estimation. We present a new end-to-end fast deep learning stereo matching network in this work that aims to determine the corresponding disparity from two stereo image pairs. We extract the characteristics of the low-resolution feature images using the stacked hourglass structure feature extractor and build a multi-level detailed cost volume. We also use the edge of the left image to guide disparity optimization and sub-sample with the low-resolution data, ensuring excellent accuracy and speed at the same time. Furthermore, we design a multi-cross attention model for binocular stereo matching to improve the matching accuracy and achieve end-to-end disparity regression effectively. We evaluate our network on Scene Flow, KITTI2012, and KITTI2015 datasets, and the experimental results show that the speed and accuracy of our method are excellent.

Anomaly perception of infrared point targets has high application value in many fields, such as maritime surveillance, airspace surveillance, and early warning systems. This kind of abnormality includes the explosion of the target, the separation between stages, the disintegration caused by the abnormal strike, etc. By extracting the radiation characteristics of continuous frame targets, it is possible to analyze and warn the target state in time. Most anomaly detection methods adopt traditional outlier detection, which has the problems of poor accuracy and a high false alarm rate. Driven by data, this paper proposes a new network structure, called AC-LSTM, which combines Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM), and embeds the Periodic Time Series Data Attention module (PTSA). The network can better extract the spatial and temporal characteristics of one-dimensional time series data, and the PTSA module can consider the periodic characteristics of the target in the process of continuous movement, and focus on abnormal data. In addition, this paper also proposes a new time series data enhancement method, which slices and re-amplifies the long time series data. This method significantly improves the accuracy of anomaly detection. Through a large number of experiments, AC-LSTM has achieved higher scores on our collected datasets than other methods.

In recent years, the silicon-based optical phased array has been widely used in the field of light detection and ranging (LIDAR) due to its great solid-state steering ability. At the same time, the optical phased array transceiver integration scheme provides a feasible solution for low-cost information exchange of small devices in the future. Based on this, this paper designs a two-dimensional optical phased array transceiver with high efficiency and a large field of view, which can realize a dense array with antenna spacing of 5.5 μm × 5.5 μm by using low crosstalk waveguide wiring. Additionally, it can realize the conversion between the receiving mode and the transmitting mode by using the optical switch. The simulation results show that the scanning range of 16.3° × 16.3° can be achieved in the transmitting mode, and the overall loss is lower than 10dB. In the receiving mode, we can achieve a collection efficiency of more than 27%, and the antenna array receiving loss is lower than 12.1 dB.

The point cloud is disordered and unstructured, and it is difficult to extract detailed features. The detailed part of the target shape is difficult to complete in the point cloud completion task. It proposes a point cloud completion network (BCA-Net) focusing on detail reconstruction, which can reduce noise and refine shapes. Specifically, it utilizes residual deformation architecture to avoid error points. The break and recombine refinement method is used to recover complete point cloud details. In addition, it proposes a bilateral confidence aggregation unit based on recurrent path aggregation to refine the coarse point cloud shape using multiple gating. Our experiments on the ShapeNet and Complete3D datasets demonstrate that our network performs better than other point cloud completion networks.

We propose a 1 × 32 silicon photonics transceiver integrated optical phased array (OPA) with a large scanning angle. It can process receive and transmit signals simultaneously, which effectively increases the on-chip signal transmission efficiency. The simulation shows that the phase-tuned 62.2° lateral beam steering without grating lobe and the wavelength-tuned 31.2° longitudinal beam steering can be achieved in the transmitting mode, and the overall optical loss is less than 9.1 dB. In the receiving mode, the combination of the two detection methods reduces the complexity of the system while ensuring the sensitivity of the system. According to statistics, an effective collection area of 43.3% per unit area can be achieved in the receiving mode, which provides a reliable guarantee for subsequent high-quality signal processing.