The CBATS (carrier-based aircraft take-off and landing training system) is an important application of virtual reality technology in the simulation field. Large-scale, real-time ocean simulations are the biggest challenge to the authenticity of the visual system of CBATS and are also currently the main research hotspot in the field of computer graphics. In this paper, a hybrid Ocean Modeling Method based on wavelet transform is presented. This method introduces an accurate phase calculation and a wind-field model solution to compensate for the randomness of wave generation and the lack of physical mechanism in spectral methods. The computational cost is greatly reduced by using a rough spatial grid to calculate the amplitude and phase values at any point in space, which effectively avoids Nyquist–Shannon Theorem limitations caused by the numerical solutions of PDEs (partial differential equations), and a high-fidelity simulation of high frequency, detailed sea surface and coherent phase-dependent wave effects is achieved. Practical verification shows that the method can fully meet the real-time simulation training requirements of CBATS with a strong real-time performance and good stability. Thus, it could play a significant role in improving the performance of the visual system.
High-resolution remote sensing images are the key data source for the visual system of a flight simulator for training a qualified pilot. However, due to hardware limitations, it is an expensive task to collect spectral and spatial images at very high resolutions. In this work, we try to tackle this issue with another perspective based on image super-resolution (SR) technology. First, we present a new ultra-high-resolution remote sensing image dataset named Airport80, which is captured from the airspace near various airports. Second, a deep learning baseline is proposed by applying the generative and adversarial mechanism, which is able to reconstruct a high-resolution image during a single image super-resolution. Experimental results for our benchmark demonstrate the effectiveness of the proposed network and show it has reached satisfactory performances.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.