Few-shot segmentation (FSS) is a cutting-edge technology that can meet requirements using a small workload. With the development of China Aerospace Engineering, FSS plays a fundamental role in astronaut working scene (AWS) intelligent parsing. Although mainstream FSS methods have made considerable breakthroughs in natural data, they are not suitable for AWSs. AWSs are characterized by a similar foreground (FG) and background (BG), indistinguishable categories, and the strong influence of light, all of which place higher demands on FSS methods. We design a pixel-wise and class-wise network (PCNet) to match support and query features using pixel-wise and class-wise semantic cues. Specifically, PCNet extracts pixel-wise semantic information at each layer of the backbone using novel cross-attention. Dense prototypes are further utilized to extract class-wise semantic cues as a supplement. In addition, the deep prototype is distilled in reverse to the shallow layer to improve its quality. Furthermore, we customize a dataset for AWSs and conduct abundant experiments. The results indicate that PCNet outperforms the published best method by 4.34% and 5.15% in accuracy under one-shot and five-shot settings, respectively. Moreover, PCNet compares favorably with the traditional semantic segmentation model under the 13-shot setting.
Mixed reality (MR) registers virtual information and real objects and is an effective way to supplement astronaut training. Spatial anchors are generally used to perform virtual–real fusion in static scenes but cannot handle movable objects. To address this issue, we propose a smart task assistance method based on object detection and point cloud alignment. Specifically, both fixed and movable objects are detected automatically. In parallel, poses are estimated with no dependence on preset spatial position information. Firstly, YOLOv5s is used to detect the object and segment the point cloud of the corresponding structure, called the partial point cloud. Then, an iterative closest point (ICP) algorithm between the partial point cloud and the template point cloud is used to calculate the object’s pose and execute the virtual–real fusion. The results demonstrate that the proposed method achieves automatic pose estimation for both fixed and movable objects without background information and preset spatial anchors. Most volunteers reported that our approach was practical, and it thus expands the application of astronaut training.