In this paper, we focus on the safety supervision of inland vessels. This paper especially aims at studying the vessel target detection and dynamic tracking algorithm based on computer vision and the target fusion algorithm based on multisensor. For the vessel video target detection and tracking, this paper analyzes the current widely used methods and theories. Additionally, facing the application scenarios and characteristics of inland vessels, a comprehensive vessel video target detection algorithm is proposed in this paper. It is combined with a three-frame difference method based on Canny edge detection and a background subtraction method based on mixed Gaussian background modeling. Besides, for the multisensor target fusion, the processing method of laser point cloud data and automatic identification system (AIS) data is analyzed in this paper. Based on the idea of fuzzy mathematics, this paper proposes a method for calculating the fuzzy correlation matrix with normal membership function, which realizes the fusion of vessel track features of laser point cloud data and AIS data under dynamic video correction. Finally, through this method, a set of vessel situation active intelligent perception systems based on multisensor fusion was developed. Experiments show that this method has better environmental applicability and detection accuracy than traditional manual detection and any single monitoring method.

The roller compacted concrete (RCC) dam has become one of the most competitive dam types due to its fast construction speed, low cost, and strong adaptability. However, the macroscale compaction test can hardly reflect the mesoscopic structure on the RCC’s rolling characteristics. According to the characteristics of RCC dam materials, a numerical discrete element method (DEM) is proposed in this paper, which is used to simulate the irregular shape and proportion of RCC aggregates. Moreover, a mesoscopic parameter inversion method based on the adaptive differential evolution (ADE) algorithm is proposed to enhance the efficiency of model contact parameters determination and overcome the inconvenience and time-consumption of conventional methods. Compared with the physical test, the simulation compression curve has good consistency with the physical test curve, and the proposed method can adequately reflect the physical and mechanical properties of RCC dam materials, which provides a basis for the subsequent research on the properties of RCC dam materials under different filling times.

Imagined speech is a kind of intuitive paradigm of Brain Computer Interface (BCI). In recent years, the accuracy of the classification based on the electroencephalogram of imagined speech has increased owing to the more and more complex models. In order to further improve the accuracy and reduce the complexity of the model to a practical level, this paper proposed an efficient architecture consisted of Large Kernel and ConvMixer. This architecture increased the accuracy to 75.73%. The performance of the architecture is higher than other models, including combination EEGNet and Transformer which is the best model in the past. The results of further experiments show that Large Kernel can extract more task-related features from the EEG of imagined speech. ConvMixer can achieve a certain degree of performance improvement even with a greatly simplified structure of model.

Since the effect of the facet braiding phenomenon, the display quality of reconstructed image degrades with increasing depth of field in tabletop three-dimensional light-field display. Here, to analysis the facet braiding, the imaging process of the tabletop 360-degree three-dimensional light-field display based on conical lens array is mathematically modeled. A viewpoint-fitting encoding algorithm is proposed to reduce the effect of the facet-braiding phenomenon and improve the range of depth of field, which is optimized to form the best synthetic encoded image by fitting the reconstructed image seen by the simulated human eye to the parallax image captured at the corresponding location. The effectiveness of the proposed optimization algorithm is verified by simulation analysis and optical experiments, respectively. In the experiment, the clear depth of field range of the display system is increased from 13 cm to 15 cm, and the visualization effect of the reconstructed three-dimensional image is enhanced.