2 results about "Best matching" patented technology

The invention discloses a ground traffic sign real-time detection method based on intelligent driving, and belongs to the field of traffic information detection in the intelligent traffic industry. The method comprises the steps of obtaining an image Src of a road in front of an intelligent vehicle in a real-time mode, conducting cutting, grey-level transformation, Gaussian filtering and binarization processing on the obtained original image Src to obtain a binary image Src_bw, meanwhile, and reading in a ground traffic sign template image temp_i prepared in advance, wherein each template can find one best matching area corresponding to the template in the Src_bw through template matching; cutting the templates to be stored as new images dst_i, and conducting subtraction on the temp_i and the corresponding dst_i to obtain new images diff_i; conducting statistic on white pixel number diff_i_Sum in each diff_i, wherein the template corresponding to the diff_i with the smallest white pixel number is most similar to a ground sign; when the diff_i_Sum is smaller than the set threshold value, considering that the ground traffic sign in the template exists in the Src_bw. The ground traffic sign real-time detection method is applicable for the intelligent driving in complex city road environment.

The invention discloses a non-Gaussian noise suppression method based on energy detection. The non-Gaussian noise suppression method comprises the following steps: (1) establishing a non-Gaussian noise model library; (2) receiving signal data by employing USRP (Universal Software Radio Peripheral), carrying out analysis on amplitude characteristics of the signal data received by the USRP based on an energy detection method, and making a statistics on parameter characteristics of each model in the model library, thereby obtaining a probability density curve distributed by each model; (3) then comparing the obtained probability density curves of the models with graphs in the noise model library, and selecting the noise model with the minimum phase difference and the best matching effect as a background noise; and (4) at last carrying out offset processing on the data containing a primary user signal and on the signal data of the background noise, namely making a subtraction between two signal amplitude values at a same frequency, thereby reducing the amplitude value of a noise signal and improving a signal-to-noise ratio. According to the non-Gaussian noise suppression method disclosed by the invention, the spectrum sensing property can be effectively improved; and the method has an application value in fields such as military communication, information processing and the like.