• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.574-578
• /
• 2009

Real-time object detection for distinguishing a moving object of interests from the background image in still image or video image sequence is an essential step to a correct object tracking and recognition. Moving cast shadow can be misclassified as part of objects or moving objects because the shadow region is included in the moving object region after object segmentation. For this reason, an algorithm for shadow removal plays an important role in the results of accurate moving object detection and tracking systems. To handle with the problems, an accurate algorithm based on the features of moving object and shadow in color space is presented in this paper. Experimental results show that the proposed algorithm is effective to detect a moving object and to remove shadow in test video sequences.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.35-38
• /
• 2009

The paper presents an effective method to detect fire in video surveillance and monitoring system. The main contribution of this work is that we successfully use the Hidden Markov Models in the process of detecting the fire with a few preprocessing steps. First, the moving pixels detected from image difference, the color values obtained from the fire flames, and their pixels clustering are applied to obtain the image regions labeled as fire candidates; secondly, utilizing massive training data, including fire videos and non-fire videos, creates the Hidden Markov Models of fire and non-fire, which are used to make the final decision that whether the frame of the real-time video has fire or not in both temporal and spatial analysis. Experimental results demonstrate that it is not only robust but also has a very low false alarm rate, furthermore, on the ground that the HMM training which takes up the most time of our whole procedure is off-line calculated, the real-time detection and alarm can be well implemented when compared with the other existing methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.10
• /
• pp.3475-3489
• /
• 2014

Here we present a simple flame detection method for an infrared (IR) thermal camera based real-time fire surveillance digital signal processor (DSP) system. Infrared thermal cameras are especially advantageous for unattended fire surveillance. All-weather monitoring is possible, regardless of illumination and climate conditions, and the data quantity to be processed is one-third that of color videos. Conventional IR camera-based fire detection methods used mainly pixel-based temporal correlation functions. In the temporal correlation function-based methods, temporal changes in pixel intensity generated by the irregular motion and spreading of the flame pixels are measured using correlation functions. The correlation values of non-flame regions are uniform, but the flame regions have irregular temporal correlation values. To satisfy the requirement of early detection, all fire detection techniques should be practically applied within a very short period of time. The conventional pixel-based correlation function is computationally intensive. In this paper, we propose an IR camera-based simple flame detection algorithm optimized with a compact embedded DSP system to achieve early detection. To reduce the computational load, block-based calculations are used to select the candidate flame region and measure the temporal motion of flames. These functions are used together to obtain the early flame detection algorithm. The proposed simple algorithm was tested to verify the required function and performance in real-time using IR test videos and a real-time DSP system. The findings indicated that the system detected the flames within 5 to 20 seconds, and had a correct flame detection ratio of 100% with an acceptable false detection ratio in video sequence level.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.141-149
• /
• 2013

This paper presents a high-speed intrusion detection process for multi-core video surveillance systems. The high-speed intrusion detection was designed to a parallel process. Based on the analysis of the conventional process, a parallel intrusion detection process was proposed so as to be accelerated by utilizing multiple processing cores in contemporary computing systems. The proposed process performs the intrusion detection in a per-frame parallel manner, considering the data dependency between frames. The proposed process was validated by implementing a multi-threaded intrusion detection program. For the system having eight processing cores, the detection speed of the proposed program is higher than that of the conventional one by up to 353.76% in terms of the frame rate.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.10
• /
• pp.66-74
• /
• 2008

Surveillance system using active tracking camera has no distance limitation of surveillance range compared to supersonic or sound sensors. However, complex motion tracking algorithm requires huge amount of computation. Compared to conventional methods using DSPs or embedded processors, this paper proposes and implements a novel motion tracker unit that detects and extracts motion information of moving objects by using picture difference of consecutive frames. The proposed motion tracker unit was implemented in FPGA with about 13,000 gates. It processes NTSC format video and was verified by embedding it into the active surveillance camera system. We also propose and implements a motion estimator unit linkable to video codec by embedding the proposed motion tracker unit into ready-made motion estimator unit. The implemented motion estimator unit is about 17,000 gates in $0.35{\mu}m$ process.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12C
• /
• pp.744-752
• /
• 2011

In intelligent surveillance system, various methods for detecting abnormal behavior were proposed recently. However, most researches are not robust enough to be utilized for actual reality which often has occlusions because of assumption the researches have that individual objects can be tracked. This paper presents a novel method to detect abnormal behavior by analysing major motion of the scene for complex environment in which object tracking cannot work. First, we generate Visual Word and Visual Document from motion information extracted from input video and process them through LDA(Latent Dirichlet Allocation) algorithm which is one of document analysis technique to obtain major motion information(location, magnitude, direction, distribution) of the scene. Using acquired information, we compare similarity between motion appeared in input video and analysed major motion in order to detect motions which does not match to major motions as abnormal behavior.

• Journal of Information Technology Services
• /
• v.15 no.4
• /
• pp.97-109
• /
• 2016

The rapid deployment of millions of mobile sensors and smart devices has resulted in high demand for opportunistic encounter-based networking. For the cooperative video surveillance of dashboard cameras in nearby vehicles, a fast and energy-efficient asynchronous neighbor discovery protocol is indispensable because a dashboard camera is an energy-hungry device after the vehicle's engine has turned off. In the existing asynchronous neighbor discovery protocols, all nodes always try to discover all neighbors. However, a dashboard camera needs to discover nearby dashboard cameras when an event is detected. In this paper, we propose a fast and energy-efficient asynchronous neighbor discovery protocol, which enables nodes : 1) to have different roles in neighbor discovery, 2) to discover neighbors within a search range, and 3) to report promptly the exact discovery result. The proposed protocol has two modes: periodic wake-up mode and active discovery mode. A node begins with the periodic wake-up mode to be discovered by other nodes, switches to the active discovery mode on receiving a neighbor discovery request, and returns to the periodic wake-up mode when the active discovery mode finishes. In the periodic wake-up mode, a node wakes up at multiples of number ${\alpha}$, where ${\alpha}$ is determined by the node's remaining battery power. In the active discovery mode, a node wakes up for consecutive ${\gamma}$ slots. Then, the node operating in the active discovery mode can discover all neighbors waking up at multiples of ${\beta}$ for ${\beta}{\leq}{\gamma}$ within ${\gamma}$ time slots. Since the proposed protocol assigns one half of the duty cycle to each mode, it consumes equal to or less energy than the existing protocols. A performance comparison shows that the proposed protocol outperforms the existing protocols in terms of discovery latency and energy consumption, where the frequency of neighbor discovery requests by car accidents is not constantly high.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.9
• /
• pp.4472-4477
• /
• 2013

This paper describes the color features of smoke in each standard color model in order to present the most suitable color model for somke detection in video surveillance system. Histogram intersection technique is used to analyze the difference characteristics between color of smoke and color of non smoke. The considered standard color models are RGB, YCbCr, CIE-Lab, HSV, and if the calculated histogram intersection value is large for the considered color model, then the smoke spilt characteristics are not good in that color model. If the calculated histogram intersection value is small, then the smoke spilt characteristics are good in that color model. The analyzed result shows that the RGB and HSV color models are the most suitable for color model based smoke detection by performing respectively 0.14 and 0.156 for histogram intersection value.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3159-3176
• /
• 2014

This work presents an analysis of the buffer features of an access router, especially the size, the impact on delay and the packet loss rate. In particular, we study how these features can affect the Quality of Service (QoS) of multimedia applications when generating traffic bursts in local networks. First, we show how in a typical SME (Small and Medium Enterprise) network in which several multimedia flows (VoIP, videoconferencing and video surveillance) share access, the upgrade of the bandwidth of the internal network may cause the appearance of a significant amount of packet loss caused by buffer overflow. Secondly, the study shows that the bursty nature of the traffic in some applications traffic (video surveillance) may impair their QoS and that of other services (VoIP and videoconferencing), especially when a certain number of bursts overlap. Various tests have been developed with the aim of characterizing the problems that may appear when network capacity is increased in these scenarios. In some cases, especially when applications generating bursty traffic are present, increasing the network speed may lead to a deterioration in the quality. It has been found that the cause of this quality degradation is buffer overflow, which depends on the bandwidth relationship between the access and the internal networks. Besides, it has been necessary to describe the packet loss distribution by means of a histogram since, although most of the communications present good QoS results, a few of them have worse outcomes. Finally, in order to complete the study we present the MOS results for VoIP calculated from the delay and packet loss rate.