In order to solve the problem that students have insufficient understanding of the full-field goniophotometer instrumentation due to the expensive equipment and the high requirements of the experimental environment, virtual reality technology is used to complete the virtual laboratory of a light intensity distribution measurement of the full-field goniophotometer through Unity 3D. The virtual laboratory is designed for near-field measurement, mid-field measurement, and far-field measurement of light intensity. It combines 3D MAX and C# to realize the model building of laboratory, luminaire and full-field goniophotometer, the dynamic drawing of light distribution curves, and the simulation system can also be run on mobile phones. The experimental process is mainly through the manipulation of the virtual experimenter and each module to generate collision detection, pop-up buttons, and click on the button triggers an event and the operation prompt page appears. The light distribution curve is generated dynamically by reading and processing the IES file data to generate 3D coordinates. This virtual simulation laboratory is demonstrated on multiple platforms. The results proved that the virtual simulation restored the experimental process vividly and can complete the experimental teaching remotely.

Medical image segmentation is a crucial part of computer-aided diagnosis. Due to the enormous cost of labeling medical images, researchers have turned to exploring semi-supervised learning. However, the lack of supervisory information makes it difficult to accurately segment the fuzzy regions (e.g., complex edges or corners of organs). In this paper, we propose a novel method called Multi-task Consistency Segmentation Network based on Calibrated Uncertainty (CU-MCSNet). This model incorporates calibrated uncertainty to guide the network’s learning process. In addition, the model consists of two tasks: i) semantic segmentation as the primary task and ii) signed distance regression as the auxiliary task. To enhance the accuracy of edge segmentation, we propose the Edge Calibration Network for the primary task. This network integrates essential spatial and channel features, employing gradient complementation to hinder the accumulation of defective information and supply pertinent data to fuzzy regions. We also use the inter-task consistency loss to explore the underlying information of the images. In the multi-task domain, it is tough to balance each task manually, and we note that homoscedastic uncertainty focuses on inter-task variation. However, its numerical estimation may still be subject to bias. Therefore, we propose an adaptive loss-balancing strategy based on calibrated homoscedastic uncertainty. Extensive experiments show that our proposed method achieves state-of-the-art performance.