Search

The identification of the propagation conditions of the wireless system, i.e., line-of-sight (LOS) and non-line-of-sight (NLOS), has a significant impact on radio based positioning performance and channel modeling. Traditional methods to identify LOS/NLOS are usually based on extracting features of the channel impulse response (CIR), based on which a decision threshold is used to distinguish between LOS and NLOS conditions. However, channel features of LOS and NLOS are sometimes similar with each other, which usually results in low accuracy of LOS/NLOS identification. In this paper, we use the combined channel feature that is consist of channel state information (CSI) and four characteristics of the channel impulse response as input, and use Long Short-Term Memory (LSTM) to train the learning method to identify LOS/NLOS condition. The proposed method is evaluated based on measured data. The results show that the proposed method achieves an accuracy of 95.477% for LOS/NLOS channel identification.

TV corner-logo is widely used in current video program, and becomes one of the hot spots in information extraction and analysis. TV corner-logo detection and segmentation algorithm is important for information extraction. In this paper, we presented an adaptive threshold segmentation algorithm, based on the combined time-averaged edge detection and saliency detection, to effectively separate and extract the TV corner-logo from the video sequence. First, we applied Canny operator to detect edges and then calculate the weighted average edge of ten frames, so as to get the time-averaged edge image. Then we combine the time-averaged edge image with the saliency map to get a more accurate segmentation. Finally, we used the adaptive threshold segmentation algorithm to separate the corner-logo. Experimental results show that, this method can effectively detect and separate the corner-logo from the background.