This paper presents an algorithm to realize the detection and recognit ion of the optical fiber intrusion signals.It is decomposed and mapped on the embedded processor c onsisting of FPGA and DSP according to the processing time and operation characteristics of the al gorithm.The treatment process is divided into three parts.Firstly,with the original signals using 3Hz high-pass filtering,the high-pass filtered signal is divided into two parts respectively by two DSPs in parallel processing to save time cost,and all subsequent operations are in a pa rallel mode.The filtered data are standardized and compared with the detection threshold.If th e result is greater than the threshold,the signal is judged as vibration signal and marked as 1,if not,judged as the false alarm and marked as 0,and then the single path detection results are o btained.Then the data used for recognition are extracted based on the above detection results .Finally,the data input recognition module is used for feature extraction of mechanical,walk ing and digging signals,and the recognition results are obtained.The experimental results show that the algorithm can effectively detect and recognize the optical fiber intrusion signa ls,improve the operation speed and satisfy the real-time performance request of the OFPS to de tect and recognize the signal type.