• Journal of Korea Multimedia Society
• /
• v.14 no.10
• /
• pp.1252-1261
• /
• 2011

In this paper, we propose the comparison method of pattern similarity for video segmentation algorithm. The shot boundary type is categorized as 2 types, abrupt change and gradual change. The representative examples of gradual change are dissolve, fade-in, fade-out or wipe transition. The proposed method consider the problem to detect shot boundary as 2-class problem. We concentrated if the shot boundary event happens or not. It is essential to define similarity between frames for shot boundary detection. We proposed 2 similarity measures, within similarity and between similarity. The within similarity is defined by feature comparison between frames belong to same shot. The between similarity is defined by feature comparison between frames belong to different scene. Finally we calculated the statistical patterns comparison between the within similarity and between similarity. Because this measure is robust to flash light or object movement, our proposed algorithm make contribution towards reducing false positive rate. We employed color histogram and mean of sub-block on frame image as frame feature. We performed the experimental evaluation with video dataset including set of TREC-2001 and TREC-2002. The proposed algorithm shows the performance, 91.84% recall and 86.43% precision in experimental circumstance.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.11-19
• /
• 2021

An abnormal object refers to a person, an object, or a mechanical device that performs abnormal and unusual behavior and needs observation or supervision. In order to detect this through artificial intelligence algorithm without continuous human intervention, a method of observing the specificity of temporal features using optical flow technique is widely used. In this study, an abnormal situation is identified by learning an algorithm that translates an input image frame to an optical flow image using a Generative Adversarial Network (GAN). In particular, we propose a technique that improves the pre-processing process to exclude unnecessary outliers and the post-processing process to increase the accuracy of identification in the test dataset after learning to improve the performance of the model's abnormal behavior identification. UCSD Pedestrian and UMN Unusual Crowd Activity were used as training datasets to detect abnormal behavior. For the proposed method, the frame-level AUC 0.9450 and EER 0.1317 were shown in the UCSD Ped2 dataset, which shows performance improvement compared to the models in the previous studies.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.747-761
• /
• 2024

Recently, modern vehicles have been controlled by Electronic Control Units (ECUs), by which the safety and convenience of drivers are highly improved. It is known that a luxury vehicle has more than 100 ECUs to electronically control its function. However, the modern vehicles are getting targeted by cyber attacks because of this computer-based automotive system. To address the cyber attacks, automotive manufacturers have been developing some methods for securing their vehicles, such as automotive Intrusion Detection System (IDS). This development is only allowed to the automotive manufacturers because they have databases for their in-vehicle network (i.e., DBC Format File) which are highly confidential. This confidentiality poses a significant challenge to external researchers who attempt to conduct automotive security researches. To handle this restricted information, in this paper, we propose a method to partially understand the DBC Format File by analyzing in-vehicle network traffics. Our method is designed to analyze Controller Area Network (CAN) traffics so that checksum signals are identified in CAN Frame Data Field. Also, our method creates a Lookup Set by which a checksum signal is correctly estimated for a given message. We validate our method with the publicly accessible dataset as well as one from a real vehicle.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.2
• /
• pp.35-44
• /
• 2002

The translation and the rotation of camera occur global motion which affects all over the frame in video sequence. With the video sequences containing global motion, it is practically impossible to extract exact video objects and to calculate genuine object motions. Therefore, high compression ratio cannot be achieved due to the large motion vectors. This problem can be solved when the global motion compensated frames are used. The existing camera motion estimation methods for global motion compensation have a large amount of computations in common. In this paper, we propose a simple global motion estimation algorithm that consists of linear equations without any repetition. The algorithm uses information .of symmetric points in the frame of the video sequence. The discriminant conditions to distinguish regions belonging to distant view from foreground in the frame are presented. Only for the distant view satisfying the discriminant conditions, the linear equations for the panning, tilting, and zooming parameters are applied. From the experimental results using the MPEG test sequences, we can confirm that the proposed algorithm estimates correct global motion parameters. Moreover the real-time capability of the proposed technique can be applicable to many MPEG-4 and MPEG-7 related areas.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.107-115
• /
• 2011

In this paper, we proposed fast and efficient algorithm for detecting near-duplication based on content based retrieval in large scale video database. For handling large amounts of video easily, we split the video into small segment using scene change detection. In case of video services and copyright related business models, it is need to technology that detect near-duplicates, that longer matched video than to search video containing short part or a frame of original. To detect near-duplicate video, we proposed motion distribution and frame descriptor in a video segment. The motion distribution descriptor is constructed by obtaining motion vector from macro blocks during the video decoding process. When matching between descriptors, we use the motion distribution descriptor as filtering to improving matching speed. However, motion distribution has low discriminability. To improve discrimination, we decide to identification using frame descriptor extracted from selected representative frames within a scene segmentation. The proposed algorithm shows high success rate and low false alarm rate. In addition, the matching speed of this descriptor is very fast, we confirm this algorithm can be useful to practical application.

• Journal of Korea Multimedia Society
• /
• v.14 no.4
• /
• pp.494-503
• /
• 2011

In this paper, we propose a recognition application of facial expression for laughter theraphy on smartphone. It detects face region by using AdaBoost face detection algorithm from the front camera image of a smartphone. After detecting the face image, it detects the lip region from the detected face image. From the next frame, it doesn't detect the face image but tracks the lip region which were detected in the previous frame by using the three step block matching algorithm. The size of the detected lip image varies according to the distance between camera and user. So, it scales the detected lip image with a fixed size. After that, it minimizes the effect of illumination variation by applying the bilateral symmetry and histogram matching illumination normalization. After that, it computes lip eigen vector by using PCA(Principal Component Analysis) and recognizes laughter expression by using a multilayer perceptron artificial network. The experiment results show that the proposed method could deal with 16.7 frame/s and the proposed illumination normalization method could reduce the variations of illumination better than the existing methods for better recognition performance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.1-8
• /
• 2020

Air ducts installed for ventilation inside buildings accumulate contaminants during their service life. Robots are installed to clean the air duct at low cost, but they are still not fully automated and depend on manpower. In this study, an intersection detection algorithm for autonomous driving was applied to an air duct cleaning robot. Autonomous driving of the robot was achieved by calculating the distance and angle between the extracted point and the center point through the intersection detection algorithm from the camera image mounted on the robot. The training data consisted of CAD images of the duct interior as well as the cross-point coordinates and angles between the two boundary lines. The deep learning-based CNN model was applied as a detection algorithm. For training, the cross-point coordinates were obtained from CAD images. The accuracy was determined based on the differences in the actual and predicted areas and distances. A cleaning robot prototype was designed, consisting of a frame, a Raspberry Pi computer, a control unit and a drive unit. The algorithm was validated by video imagery of the robot in operation. The algorithm can be applied to vehicles operating in similar environments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.12
• /
• pp.2213-2220
• /
• 2017

This paper proposes an efficient approach for hardware implementation of moving object detection (MOD) processor using effective Gaussian mixture learning (EGML)-based background subtraction method. Arithmetic units used in background generation were implemented using LUT-based approximation to reduce hardware complexity. Hardware resources used for both background subtraction and Gaussian probability density calculation were shared. The MOD processor was verified by FPGA-in-the-loop simulation using MATLAB/Simulink. The MOD performance was evaluated by using six types of video defined in IEEE CDW-2014 dataset, which resulted the average of recall value of 0.7700, the average of precision value of 0.7170, and the average of F-measure value of 0.7293. The MOD processor was implemented with 882 slices and block RAM of $146{\times}36kbits$ on Virtex5 FPGA, resulting in 60% hardware reduction compared to conventional design based on EGML. It was estimated that the MOD processor could operate with 75 MHz clock, resulting in real-time processing of $800{\times}600$ video with a frame rate of 39 fps.

• Journal of Broadcast Engineering
• /
• v.14 no.6
• /
• pp.661-675
• /
• 2009

The carelessly and illegally copied contents are raising serious social problem as internet and multimedia technologies are advancing. Therefore, development of video copy detection system must be settled without delay. In this paper, we propose the hierarchical video copy detection method that estimates similarity using statistical characteristics between original video and manipulated(transformed) copy video. We rank according to luminance value of video to be robust to spacial transformation, and choose similar videos categorized as candidate segments in huge amount of database to reduce processing time and complexity. The copy videos generally insert black area in the edge of the image, so we remove rig black area and decide copy or not by using statistical characteristics of original video and copied video with center part of frame that contains important information of video. Experiment results show that the proposed method has similar keyframe accuracy to reference method, but we use less memory to save feature information than reference's, because the number of keyframes is less 61% than that of reference's. Also, the proposed method detects if the video is copied or not efficiently despite expansive spatial transformations such as blurring, contrast change, zoom in, zoom out, aspect ratio change, and caption insertion.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.117-124
• /
• 2013

In this paper, we present a new method which efficiently estimates a face direction from a sequences of input video images in real time fashion. For this work, the proposed method performs detecting the facial region and major facial features such as both eyes, nose and mouth by using the Haar-like feature, which is relatively not sensitive against light variation, from the detected facial area. Then, it becomes able to track the feature points from every frame using optical flow in real time fashion, and determine the direction of the face based on the feature points tracked. Further, in order to prevent the erroneously recognizing the false positions of the facial features when if the coordinates of the features are lost during the tracking by using optical flow, the proposed method determines the validity of locations of the facial features using the template matching of detected facial features in real time. Depending on the correlation rate of re-considering the detection of the features by the template matching, the face direction estimation process is divided into detecting the facial features again or tracking features while determining the direction of the face. The template matching initially saves the location information of 4 facial features such as the left and right eye, the end of nose and mouse in facial feature detection phase and reevaluated these information when the similarity measure between the stored information and the traced facial information by optical flow is exceed a certain level of threshold by detecting the new facial features from the input image. The proposed approach automatically combines the phase of detecting facial features and the phase of tracking features reciprocally and enables to estimate face pose stably in a real-time fashion. From the experiment, we can prove that the proposed method efficiently estimates face direction.