For navigation in tunnel environment, GPS sensors and ordinary cameras can’t function effectively. Thus infrared cameras are installed on top of our experimental vehicle, and here we propose an efficient object detection method to detect emergency lights from the collected data in tunnel environment. The proposed method firstly detects keypoints by setting thresholds for intensity of uniformly sampled points. Each keypoint is then verified by the appearance of its surrounding sub-image. After clustering the keypoints which satisfy the verification, the method verifies the keypoint clusters by their appearance and temporal information. Though the later steps are time-consuming, they deal with very few instances. And this improves the efficiency of the method, while not losing effectiveness of the appearance and temporal information. Thus the method gives promising results in real time. Detection performance and efficiency are verified by experiments carried on challenging real data.