• Journal of Internet Computing and Services
• /
• v.9 no.3
• /
• pp.169-178
• /
• 2008

In this paper, we propose a video summarization system which is based on activity in video acquired by multiple non-overlapping cameras for wide-area surveillance. The proposed system separates persons by time-independent background removal and detects activities of the segmented persons by their motions. In this paper, we extract eleven activities based on whose direction the persons move to and consider a key-frame as a frame which contains a meaningful activity. The proposed system summarizes based on activity-based key-frames and controls an amount of summarization according to an amount of activities. Thus the system can summarize videos by camera, time, and activity.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.1
• /
• pp.44-54
• /
• 2007

In the military field, according to the MIL-STD-188-220, which is an Ad-Hoc communication protocol used for sending out or receiving data and voice smoothly among nodes in the situation that wireless communication nodes move arbitrarily, data communication is cut off because nodes can not know topology changes perpetually in the link disconnection state due to node movement in the case that transmitters do not confirm whether data is delivered to receivers or not, and transmit only the data having routine precedence continuously. In order to solve this problem, we have proposed the technique that makes efficient data communication possible by achieving a rapid topology change detection and link information update using TEST frame. We have analyzed TEST frame application effects in the two aspects of the topology update delay time and the data transmission success ratio.

• Journal of Broadcast Engineering
• /
• v.7 no.3
• /
• pp.219-228
• /
• 2002

In this paper, we propose a new method of converting 2D video into 3D stereoscopic video, called stereoscopic conversion. In general, stereoscopic images are produced using the motion informations. However unreliable motion informations obtained especially from block-based motion estimation cause the wrong generation of stereoscopic images. To solve for this problem, we propose a stereoscopic conversion method based upon the utilization of key frame that has the better accuracy of estimated motion informations. As well, as generation scheme of stereoscopic images associated with the motion type of each key frame is proposed. For the performance evaluation of our proposed method, we apply it to five test images and measure the accuracy of key frame-based stereoscopic conversion. Experimental results show that our proposed method has the accuracy more than about 90 percent in terms of the detection ratio of key frames.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2449-2463
• /
• 2014

Hierarchical B-frame coding was introduced into H.264/SVC to provide temporal scalability and improve coding performance. A content analysis-based adaptive group of picture structure (AGS) can further improve the coding efficiency, but damages the inter-frame correlation and temporal scalability of hierarchical B-frame to different degrees. In this paper, we propose a group of pictures (GOP) adaptation coding method based on the positions of video cuts. First, the cut positions are accurately detected by the combination of motion coherence (MC) and mutual information (MI); then the GOP is adaptively and proportionately set by the analysis of MC in one scene. In addition, we propose a binary tree algorithm to achieve the temporal scalability of any size of GOP. The results for test sequences and real videos show that the proposed method reduces the bit rate by up to about 15%, achieves a performance gain of about 0.28-1.67 dB over a fixed GOP, and has the advantages of better transmission resilience and video summaries.

• Journal of Korea Multimedia Society
• /
• v.21 no.9
• /
• pp.1044-1051
• /
• 2018

In this paper, we propose a new method to improve low light image. In order to improve the image quality of a night image with a moving object as much as the quality of a daytime image, the following tasks were performed. Firstly, we reduce the noisy of the input night image and improve the night image by the tone mapping method. Secondly, we segment the input night image into a foreground with motion and a background without motion. The motion is detected using both the difference between the current frame and the previous frame and the difference between the current frame and the night background image. The background region of the night image takes pixels from corresponding positions in the daytime image. The foreground regions of the night image take the pixels from the corresponding positions of the image which is improved by the tone mapping method. Experimental results show that the proposed method can improve the visual quality more clearly than the existing methods.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2003.05a
• /
• pp.319-323
• /
• 2003

In this paper, we propose a hybrid transceiver for underwater acoustic communication, which allows the system to reduce complexity and increase robustness in time variant underwater channel environments. It is designed in the digital domain except for amplifiers and implemented by using a multiple digital signal processors (DSPs) system. The digital modulation technique is quadrature phase shift keying (QPSK) and frame synchronization is an energy (non-coherent) detection scheme based on the quadrature receiver structure. DSP implementation is based on block data parallel architecture (BDPA). We shaw experimental results in th? underwater anechoic basin at KRISO. The results indicate that the frame synchronization is performed without PLL. Also, we shaw that the adaptive equalizer can compensate frame synchronization error and the correction capability is dependent on the length of equalizer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1123-1140
• /
• 2019

Many Internet of Things (IoT) applications involving bursty traffic have emerged recently with event detection. A power management scheme qualified for uplink bursty traffic (PM-UBT) is proposed by distinguishing between bursty and general uplink traffic patterns in the IEEE 802.11 standard to balance energy consumption and uplink latency, especially for stations with limited power and constrained buffer size. The proposed PM-UBT allows a station to transmit an uplink bursty frame immediately regardless of the state. Only when the sleep timer expires can the station send uplink general traffic and receive all downlink frames from the access point. The optimization problem (OP) for PM-UBT is power consumption minimization under a constrained buffer size at the station. This OP can be solved effectively by the bisection method, which demonstrates a performance similar to that of exhaustive search but with less computational complexity. Simulation results show that when the frame arrival rate in a station is between 5 and 100 frame/second, PM-UBT can save approximately 5 mW to 30 mW of power compared with an existing power management scheme. Therefore, the proposed power management strategy can be used efficiently for delay-intolerant uplink traffic in event-driven IoT applications, such as health status monitoring and environmental surveillance.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.5
• /
• pp.149-156
• /
• 2019

The existing subtract image based intrusion detection system for CCTV digital images has a problem that it can not distinguish intruders from moving backgrounds that exist in the natural environment. In this paper, we tried to solve the problems of existing system by designing real - time intrusion detection system for CCTV digital image by combining subtract image based intrusion detection method and background learning artificial neural network technology. Our proposed system consists of three steps: subtract image based intrusion detection, background artificial neural network learning stage, and background artificial neural network evaluation stage. The final intrusion detection result is a combination of result of the subtract image based intrusion detection and the final intrusion detection result of the background artificial neural network. The step of subtract image based intrusion detection is a step of determining the occurrence of intrusion by obtaining a difference image between the background cumulative average image and the current frame image. In the background artificial neural network learning, the background is learned in a situation in which no intrusion occurs, and it is learned by dividing into a detection window unit set by the user. In the background artificial neural network evaluation, the learned background artificial neural network is used to produce background recognition or intrusion detection in the detection window unit. The proposed background learning intrusion detection system is able to detect intrusion more precisely than existing subtract image based intrusion detection system and adaptively execute machine learning on the background so that it can be operated as highly practical intrusion detection system.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.4
• /
• pp.269-275
• /
• 2017

Automatic vehicle detection is a very important function for autonomous vehicles. Conventional vehicle detection approaches are based on visible-light images obtained from cameras mounted on a vehicle in the daytime. However, unlike daytime, a visible-light image is generally dark at night, and the contrast is low, which makes it difficult to recognize a vehicle. As a feature point that can be used even in the low light conditions of nighttime, the rear lamp is virtually unique. However, conventional rear lamp-based detection methods seldom cope with atypical lamps, such as LED lamps, or flashing turn signals. In this paper, we detect atypical lamps by blurring the lamp area with a low pass filter (LPF) to make out the lamp shape. We also propose to detect flickering of the turn signal lamp in a manner such that the lamp area is vertically projected, and the maximum difference of two paired lamps is examined. Experimental results show that the proposed algorithm has a higher F-measure value of 0.24 than the conventional lamp pairing-based detection methods, on average. In addition, the proposed algorithm shows a fast processing time of 6.4 ms per frame, which verifies real-time performance of the proposed algorithm.

• Fire Science and Engineering
• /
• v.22 no.4
• /
• pp.27-32
• /
• 2008

In this paper, a flame and smoke detection algorithm is proposed to recognize a fire. Flame and smoke have specific color distribution and continuously change shapes of them. In the proposed flame detection algorithm, specific regions are candidated as flame by color distributions and variations of frames of video. Some of candidated regions are decided as flame by the magnitude of motion vector. To determine smoke in the field of view of camera, edge is important because high frequency component is decreased by it. Candidated region of smoke is assigned by color distributions, inter-frame differences and the value of edge. The candidated region is settled as smoke region with magnitude of motion vector. As results of simulations, it is shown that the proposed algorithm is useful for flame and smoke detection.