A large number of remote video sensors are being deployed in the world to collect, store, and analyze the real-world data. Since a remote video sensor produces very large data, the total amount of video data are extremely large in size, complexity, and capacity. Important events from a remote video sensor are closely related to a motion in video. We present, in this paper, a fast motion detection method based on the number of bits used for encoding a video stream and the GOP-level motion detection. A low complexity measurement of the number of bits is performed in the coded video sequence and then, we store and process the coded video stream only if the total bits are larger than a pre-defined threshold. We also use a GOP level motion detection to reduce processing overhead compared to the conventional motion vector-based approach which processes every frame. Manipulating the number of bits is itself a much easier task than full reconstruction of each pixel of a video frame and it can save storage cost because it only stores a coded video sequence with a motion. The proposed method also contributes to reduction of computational complexity compared to the manipulation of motion vectors per 4x4 macro block. To evaluate our method, we deployed a centralized single server connected to H.264 capable remote video sensors. Results on the video sequences showed that the proposed approach can process more video sequences than the conventional compressed domain approach.