We propose a surveillance system with fiber optic cables based on multi-channel distributed acoustic sensing (DAS) interrogator equipped with optical rotary switch. By switching the optical connection between the interrogator and multiple optical fiber-under-test, we can sample the sensed vibration signal from the fibers with single pulse generator and optical receiver. To identify the source of detected vibration signal, we separated the monitoring process as 2-phases. In the phase-1, we monitor the fibers during 3 second periodically and simply classify the vibration signal is whether threat or non-threat to the fiber-optic cable route using 1-dimensional convolutional neural network. When the result is threat, the optical switch fixed the port and we intentionally monitor the fiber in 10 second to acquire more vibration signal. We adopted 2-D convolutional neural network to classify the source of vibration signal. We trained the two classification models with vibration signal from the deployed fiber-optic cables and the results show the accuracy of 94.5 and 98.2 %.