关键词: 时频分量检测, 时频分布（TFD）-Hough变换, 覆盖聚类, 感知编组

Abstract: To solve the problem that the existing methods cannot effectively extract time-frequency component in the real communication monitoring environment, a novel method for the time-frequency component detection is proposed on the basis of the improved TFD-Hough transformation. Under the circumstance that the number of detected component is unknown, the proposed method can take full advantage of the linearity clustering trait of the magnitude of component in time-frequency distribution, and combine the covering clustering algorithm with perceptual organization to implement the procedure of extracting and detecting parameters of signal component one by one, avoiding the flaws brought by the energy difference and the lack of the location information of the target in global detection. The experimental results demonstrate the validity of the proposed method, which can meet the requirement of actively identifying the abnormity of communication signal.

Key words: time-frequency component detection, Time-Frequency Distribution（TFD）-Hough transformation, covering clustering algorithm, perceptual organization