No abstract

Aiming at the weakness of the dark channel prior modelin and Retinex algorithm such as slow calculation speed, halo effect, and loss of details in the processing of UAV single image dehazingand, an improved Retinex algorithm is proposed. First, convert the RGB color space to the HIS color space, separate the brightness I, assign values to the three scales of large, medium and small, use Gaussian surround to obtain the three scale brightness images and then weight, and then switch the brightness image to the RGB color space, in order to achieve the information with more details. Finally, the haze images which is distinguished in three different landforms such as city, mountainous area and forestwill be performed simulation experiments in MATLAB, and adjust the image restoration effect by changing the parameters.

No abstract

Aiming at the monitored nonstationary signal in sensor networks, distributed compressed sensing-based data aggregation model and algorithm, DCS-DF-1, is presented to reduce the number of transmissions in sensor networks and improve the precision of sensing. To implement this algorithm, the variance of each recover sensing sequence of sensor is estimated using the wavelet transform, and the optimum weighting factor to each sensing is obtained accordingly. The fusion performance is better than each sensor and MMSEbased (minimum mean square error) method. Besides, analyze the influences of number of non-zero components to CPU time, SNR (signal-to-noise ratio), MSE (mean square error) and recover error of algorithm, as well as the relation of energy consumption to recover error. The calculation results show that DCS-DF-1 not only have better performance of stability and consistency, but also satisfy the monitoring requirements for non-stationary signal in sensor networks.

To achieve multi-resolution approximation of 3D defect profile reconstruction from magnetic flux leakage (MFL) signals, a radial wavelet basis function neural network iterative model, which contains a forward model and an inverse model based on a parallel radial wavelet basis function neural network (PRWBFNN), is proposed. The forward model in the loop is to determine the MFL signals for a given set of flaw parameters, and the inverse model is used to predict the profile given the measured value of the MFL signals and acts to constrain the solution space. This approach iteratively adjusts the weights of the inverse network to minimise the error between the measured and predicted values of the MFL signals. The reconstruction results of different defects indicate that significant advantages over other neural network-based defect characterisation schemes could be obtained.