Due to the complexity of the underwater environment, underwater images captured by optical cameras usually suffer from haze and color distortion. Based on the similarity between the underwater imaging model and the atmosphere model, the dehazing algorithm is widely adopted for underwater image enhancement. As a key factor of the dehazing model, background light directly affects the quality of image enhancement. This paper proposes a novel background light estimation method which can enhance the underwater image. And it can be applied in 30-60m depth with artificial light. The method combines deep learning to obtain red channel information of the background light in the dark channel of the underwater image. Then, the background light is obtained by adaptive color deviation correction. Finally, the experiments of underwater images enhancement are carried out, using the dark channel prior algorithm based on the proposed background light estimation method. The results show that the proposed method effectively improves underwater image blur and color deviation, and is superior to other methods in multiple non-reference image evaluation indicators.
With the development of unmanned tracked vehicles, soil model predictions of soft terrains are becoming more essential. In order to accurately simulate the interaction characteristics between soil particles and the track, soil modeling with a discrete element method (DEM) is proposed. Volume-based scaled-up modeling of DEM soil particles and the calibration of DEM input parameters were investigated as a feasible approach to realizing many particle calculations. Calibration of DEM input parameters can solve the distortions between actual and DEM particle sizes. Cohesion and friction parameters of the scaled-up soil particle model were recalibrated by the shape accumulated through the virtual design of the experiment. Soil DEM particles were scaled up to 1 mm spherical particles, and recalibrated DEM parameter values were used to match the actual accumulated soil shape. Three calibrated scaled-up soil models were used for the shear stress–displacement DEM simulation of a track segment, and the mean absolute percentage error (MAPE) was less than 11% compared with the actual shear stress–displacement test. The parameter value of soil traction performance empirical model of a tracked vehicle is modified according to the soil shear stress–displacement DEM simulation. Comparative analysis was performed for travel test results of a tracked vehicle; the relative error of the soil traction prediction results to actuals was less than 16.8%. This showed that the volume-based particle scaling technique is an effective DEM for the mechanical simulation of soil.
Optical imaging usually shows significant differences in underwater environments with different characteristics. The general underwater imaging model ignores the influences of turbidity on the attenuation of light. For turbid water with different particle types and concentrations, we introduced background light correction and turbidity factors to express the influences. A parametric turbid underwater image generation model based on dark channel prior theory was proposed, in which, the transmission map changes with the turbidity while the image tone changes with the background light correction. Based on experiments, the high similarity between generated images and real images confirmed that our model can fit the imaging in different bodies of water. Thus, the model can be used to generate a greater diversity of samples of turbid underwater images. We also applied the model to turbid underwater image enhancement. The image quality evaluation results indicated that the model can enhance turbid underwater images well.
Trajectory planning of unmanned tracked vehicles is an important research field in autonomous technology. However, the existing path planning methods do not consider the mechanical carrying capacity of special soft terrain. Based on the problem that the existing methods seriously affect the safe passage of vehicle steering, a path planning method oriented to the steering traffic of tracked vehicles on soft terrain is proposed. The method is based on raster map and uses A-star path planning algorithm. On this basis, the turning point is extracted from the path, and the curvature of the turning point is controlled by combining the steering dynamics model of tracked vehicle in soft soil. It can predict the ability of the tracked vehicle to avoid obstacles in the thin soft soil of the mudflats. This method improves the lack of soft soil permeability assessment in path planning, and provides a theoretical basis for unmanned vehicle path planning technology under extreme ground conditions.