• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.12-20
• /
• 2011

In this paper, we propose an efficient object detection and classification algorithm for video surveillance applications. Previous researches mainly concentrated either on object detection or classification using particular type of feature e.g., Scale Invariant Feature Transform (SIFT) or Speeded Up Robust Feature (SURF) etc. In this paper we propose an algorithm that mutually performs object detection and classification. We combinedly use heterogeneous types of features such as texture and color distribution from local patches to increase object detection and classification rates. We perform object detection using spatial clustering on interest points, and use Bag of Words model and Naive Bayes classifier respectively for image representation and classification. Experimental results show that our combined feature is better than the individual local descriptor in object classification rate.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.28 no.9
• /
• pp.99-104
• /
• 2014

This paper presents a unified live-streaming method based on Hypertext Mark-up Language 5(HTML5) for an IP camera which is independent of browsers of clients and is implemented with open-source libraries. Currently, conventional security systems based on analog CCTV cameras are being modified to newer surveillance systems utilizing IP cameras. These cameras offer remote surveillance and monitoring regardless of the device being used at any time, from any location. However, this approach needs live-streaming protocols to be implemented in order to verify real-time video streams and surveillance is possible after installation of separate plug-ins or special software. Recently, live streaming is being conducted through HTML5 using two different standard protocols: HLS and DASH, that works with Apple and Android products respectively. This paper proposes a live-streaming approach that is linked on either of the two protocols which makes the system independent with the browser or OS. The client is possible to monitor real-time video streams without the need of any additional plug-ins. Moreover, by implementing open source libraries, development costs and time were economized. We verified usefulness of the proposed approach through mobile devices and extendability to other various applications of the system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.8A
• /
• pp.820-827
• /
• 2010

In these days, video applications for special purposes such as video conference systems among multiple users and video surveillance systems require multiple video connections and QoS guarantee. The video systems employ IEEE 802.11 Wireless LAN devices to support broadband wireless interfaces and easy internet accesses for cheaper prices. However, according to the current IEEE 802.11e HCCA standard, if more than three video sessions are established in WSTA services, some of them must share the TXOP because the available number of TSIDs for video transmission is two. In order to resolve the problem, we devised a method which can establish up to 15 video sessions by slightly modifying the frame structure while maintaining the compatibility with current standard. Our method is implemented on the NCTUns 4.0 network simulator, and evaluated not only numerically in terms of throughput, delay, and PSNR, but also experimentally in the sense of real video clips that are used as input to our simulation. The results showed that our method sufficiently guarantees the transmission bandwidth requested by each video session.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1910-1914
• /
• 2015

Human posture recognition is an attractive and challenging topic in computer vision due to its promising applications in the areas of personal health care, environmental awareness, human-computer-interaction and surveillance systems. Human posture recognition in video sequences consists of two stages: the first stage is training and evaluation and the second is deployment. In the first stage, the system is trained and evaluated using datasets of human postures to ‘teach’ the system to classify human postures for any future inputs. When the training and evaluation process is deemed satisfactory as measured by recognition rates, the trained system is then deployed to recognize human postures in any input video sequence. Different classifiers were used in the training such as Multilayer Perceptron Feedforward Neural networks, Self-Organizing Maps, Fuzzy C Means and K Means. Results show that supervised learning classifiers tend to perform better than unsupervised classifiers for the case of human posture recognition.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.1
• /
• pp.68-75
• /
• 1999

Machine recognition of faces from still and video images is emerging as an active research area spanning several disciplines such as image processing, pattern recognition, computer vision and neural networks. In addition, human face identification has numerous applications such as human interface based systems and real-time video systems of surveillance and security. In this paper, we propose an algorithm that can identify a particular individual face. We consider human face identification system in color space, which hasn't often considered in conventional in conventional methods. In order to make the algorithm insensitive to luminance, we convert the conventional RGB coordinates into normalized CIE coordinates. The normalized-CIE-based facial images are KL-transformed. The transformed data are used as the input of multi-layered neural network and the network are trained using error-backpropagation methods. Finally, we verify the system performance of the proposed algorithm by experiments.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.128-138
• /
• 2010

In this paper, we propose a new bit assignment scheme for Wyner-Ziv video coding. Distributed video coding (DVC) is a new video coding paradigm which enables greatly low complexity encoding because it does not have any motion prediction module at encoder. Therefore, it is very well suited for many applications such as video communication, video surveillance, extremely low power consumption video coding, and other portable applications. Theoretically, the Wyner-Ziv video coding is proved to achieve the same rate-distortion (RD) performance comparable to that of the joint video coding. However, its RD performance has much gap compared to MC-DCT-based video coding such as H.264/AVC. Moreover, Transform Domain Wyner-Ziv (TDWZ) video coding which is a kind of DVC with transform module has difficulty of exact bit assignment because the entire image is treated as a same message. In this paper, we propose a feasible bit assignment algorithm using adaptive quantization matrix selection for the TDWZ video coding. The proposed method can calculate suitable bit amount for each region using the local characteristics of image. Simulation results show that the proposed method can enhance coding performance.

• Journal of Computing Science and Engineering
• /
• v.9 no.1
• /
• pp.29-38
• /
• 2015

Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.9 no.3
• /
• pp.166-171
• /
• 2009

In recent years, video detection systems have been implemented in various infrastructures such as airport, public transportation, power generation system, water dam and so on. Recognizing moving objects in video sequence is an important problem in computer vision, with applications in several fields, such as video surveillance and target tracking. Segmentation and tracking of multiple vehicles in crowded situations is made difficult by inter-object occlusion. In the system described in this paper, the mean shift algorithm is firstly used to filter and segment a color vehicle image in order to get candidate regions. These candidate regions are then analyzed and classified in order to decide whether a candidate region contains a license plate or not. And then some characters in the license plate is recognized by using the fuzzy ARTMAP neural network, which is a relatively new architecture of the neural network family and has the capability to learn incrementally unlike the conventional BP network. We finally design a license plate recognition system using the mean shift algorithm and fuzzy ARTMAP neural network and show its performance via some computer simulations.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.661-664
• /
• 2009

Recently, intelligent surveillance camera systems are needed popularly. However, current researches are focussed on improvement of a single module rather than implementation of an integrated system. In this paper, we implemented a moving wireless surveillance camera system which is composed of face detection, and using motion sensor. In our implementation, we used a camera module from SHARP, a pair of wireless video transmission module from ECOM, body of moving robot used for A4WD1 Combo kit for RC, a pair of ZigBee RF wireless transmission module from ROBOBLOCK, and a motion sensor module (AMN14111) from PANASONIC. We used OpenCV library for face dection and MFC for implement software. We identified real-time operations of face detection, PTT control, and motion sensor detecton. Thus, the implemented system will be useful for the applications of remote control, human detection, and using motion sensor.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.449-463
• /
• 2015

Video object tracking is important for variety of applications, such as security, video indexing and retrieval, video surveillance, communication, and compression. This paper proposes an object tracking method in HEVC bitstreams. Without pixel reconstruction, motion vector (MV) and size of prediction unit in the bitstream are employed in an Spatio-Temporal Markov Random Fields (ST-MRF) model which represents the spatial and temporal aspects of the object's motion. Coefficient-based object shape adjustment is proposed to solve the over-segmentation and the error propagation problems caused in other methods. In the experimental results, the proposed method provides on average precision of 86.4%, recall of 79.8% and F-measure of 81.1%. The proposed method achieves an F-measure improvement of up to 9% for over-segmented results in the other method even though it provides only average F-measure improvement of 0.2% with respect to the other method. The total processing time is 5.4ms per frame, allowing the algorithm to be applied in real-time applications.