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.
Forward Looking InfraRed (FLIR) imaging system has been widely used for both military and civilian purposes.
Military applications include target acquisition and tracking, night vision system. Civilian applications include thermal
efficiency analysis, short-ranged wireless communication, weather forecasting and other various applications. The
dynamic range of FLIR imaging system is larger than one of commercial display. Generally, auto gain controlling and
contrast enhancement algorithm are applied to FLIR imaging system. In IR imaging system, histogram equalization and
plateau equalization is generally used for contrast enhancement. However, they have no solution about the excessive
enhancing when luminance histogram has been distributed in specific narrow region. In this paper, we proposed a
Regional Density Distribution based Wide Dynamic Range algorithm for Infrared Camera Systems. Depending on the
way of implementation, the result of WDR is quite different. Our approach is single frame type WDR algorithm for
enhancing the contrast of both dark and white detail without loss of bins of histogram with real-time processing. The
significant change in luminance caused by conventional contrast enhancement methods may introduce luminance
saturation and failure in object tracking. Proposed method guarantees both the effective enhancing in contrast and
successive object tracking. Moreover, since proposed method does not using multiple images on WDR, computation
complexity might be significantly reduced in software / hardware implementation. The experimental results show that
proposed method has better performance compared with conventional Contrast enhancement methods.