• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.493-505
• /
• 2016

Among modern computer vision and video surveillance systems, the pedestrian counting system is a one of important systems in terms of security, scheduling and advertising. In the field of, pedestrian counting remains a variety of challenges such as changes in illumination, partial occlusion, overlap and people detection. During pedestrian counting process, the biggest problem is occlusion effect in crowded environment. Occlusion and overlap must be resolved for accurate people counting. In this paper, we propose a novel pedestrian counting system which improves existing pedestrian tracking method. Unlike existing pedestrian tracking method, proposed method shows that average filter tracking method can improve tracking performance. Also proposed method improves tracking performance through frame compensation and outlier removal. At the same time, we keep various information of tracking objects. The proposed method improves counting accuracy and reduces error rate about S6 dataset and S7 dataset. Also our system provides real time detection at the rate of 80 fps.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.421-429
• /
• 2015

This paper is about an approach for pedestrian detection and tracking with infrared imagery. We used the CUDA(Computer Unified Device Architecture) that is a parallel processing language in order to improve the speed of video-based pedestrian detection and tracking. The detection phase is performed by Adaboost algorithm based on Haar-like features. Adaboost classifier is trained with datasets generated from infrared images. After detecting the pedestrian with the Adaboost classifier, we proposed a particle filter tracking strategies on HSV histogram feature that exploit adaptively at the same time. The proposed approach is implemented on an NVIDIA Jetson TK1 developer board that is full-featured device ideal for software development within the Linux environment. In this paper, we presented the results of parallel processing with the NVIDIA GPU on the CUDA development environment for detection and tracking of pedestrians. We compared the object detection and tracking processing time for night-time images on both GPU and CPU. The result showed that the detection and tracking speed of the pedestrian with GPU is approximately 6 times faster than that for CPU.

• Journal of Digital Contents Society
• /
• v.7 no.2
• /
• pp.117-124
• /
• 2006

In ubiquitous computing environment, a user can access their personalized services at anytime, anywhere, through any possible mobile or fixed terminals in a secure way. If the user wants to move to a different location, they need to stop the video play at the current location and makes a new request at the new location. As well, the user needs to manually search for the last frame to be seen at the previous location. In this paper, we proposed an implementation of multimedia contents streaming service mobility by user's location tracking. User can play video seamlessly while moving from one machine to another along the user's moving trail.

• Journal of the Ergonomics Society of Korea
• /
• v.29 no.4
• /
• pp.655-659
• /
• 2010

The objective of this study is to quantitatively incorporate user observation into usability evaluation of mobile interfaces using monitoring techniques in first- and third-person points of view. In this study, an experiment was conducted to monitor and record users' behavior using Ergoneers Dikablis, a gaze tracking device. The experiment was done with 2 mobile phones each with a button keypad interface and a touchscreen interface for comparative analysis. The subjects included 20 people who have similar experiences and proficiency in using mobile devices. Data from video recordings were coded with Noldus Observer XT to find usage patterns and to gather quantitative data for analysis in terms of effectiveness, efficiency and satisfaction. Results showed that the button keypad interface was generally better than the touchcreen interface. The movements of the fingers and gaze were much simpler when performing given tasks on the button keypad interface. While previous studies have mostly evaluated usability with performance measures by only looking at task results, this study can be expected to contribute by suggesting a method in which the behavioral patterns of interaction is evaluated.

• Korean Journal of Agricultural Science
• /
• v.39 no.4
• /
• pp.483-489
• /
• 2012

Preference of stink bugs to various leguminous seeds was evaluated by using VTS (Video Tracking System) in laboratory. Major soybean stink bugs such as bean bug, Riptortus pedestris (Fabricius), one-banded stink bug, Piezodorus hybneri (Gmelin), eastern green stink bug, Nezara antennata (Scott), and sole bug, Dolycoris baccarum (L.) were significantly most attracted to Cheongjakong, a soybean variety, baited fish-net trap, followed by soybean varieties Ilpumgeomjeongkong and Taekwangkong, a peanut variety Daekwangdangkong, a kidney bean variety Gangnangkong, and a adzuki bean variety Jungwonpat, respectively in a soybean field. VTS observation in laboratory showed that R. pedestris and D. baccarum had significantly higher frequency of visit on Cheongjakong, followed by Ilpumgeomjeongkong. However, P. hybneri, N. antennata and Halyomorpha halys (Stal) had significantly higher number of visits on Cheongjakong, Seonnogkong and Jinpumkong, followed by Ilpumgeomjeongkong. The sojourned time of stink bugs, however, was significantly longer on Cheongjakong regardless of species of the bugs. Accordingly, Cheongjakong was evaluated as the most preferred soybean seed by fish-net trap and VTS. Thus, VTS is found to be an effective means to evaluate the food preference of stink bugs.

• Journal of Mechanical Science and Technology
• /
• v.17 no.8
• /
• pp.1140-1147
• /
• 2003

We have examined the effect on neck-muscle activation of altering whole body posture. A Rhesus monkey (Macaca mulatta) was trained to produce sinusoidal (0.25 Hz) head tracking movements in the sagittal plane when seated with trunk and head vertical or while standing in the quadrupedal position. Video-fluoroscopic images of cervical vertebral motion, and electromyographic (EMG) responses were recorded simultaneously. Results demonstrated that vertebral motion varied with body posture, occurring synchronously between all joints in the upright position and primarily at skull-$C_1$ when in the quadrupedal position. Muscle EMG activation was significantly greater (P<0.001) in the quadrupedal position than when upright for all muscles except semispinalis cervicis. Peak activation of all the muscles occurred prior to peak head extension in the quadrupedal position, suggesting synchronous activity between muscles. Data suggest that, when upright, muscles were activated in functional groupings defined by their anatomical arrangement. In the quadrupedal position, gravity acting on the horizontally oriented head produced greater activation and a collective response of the muscles.

• Journal of Korea Multimedia Society
• /
• v.17 no.5
• /
• pp.556-565
• /
• 2014

This paper proposes a method to track object of real-time video transferred through single web-camera and to recognize risk-situation and human actions. The proposed method recognizes human basic actions that human can do in daily life and finds risk-situation such as faint and falling down to classify usual action and risk-situation. The proposed method models the background, obtains the difference image between input image and the modeled background image, extracts human object from input image, tracts object's motion and recognizes human actions. Tracking object uses the moment information of extracting object and the characteristic of object's recognition is moment's change and ratio of object's size between frames. Actions classified are four actions of walking, waling diagonally, sitting down, standing up among the most actions human do in daily life and suddenly falling down is classified into risk-situation. To test the proposed method, we applied it for eight participants from a video of a web-cam, classify human action and recognize risk-situation. The test result showed more than 97 percent recognition rate for each action and 100 percent recognition rate for risk-situation by the proposed method.

• Journal of Yeungnam Medical Science
• /
• v.35 no.1
• /
• pp.63-69
• /
• 2018

Background: Kinovea software that tracking semi-automatically the motion in video screen has been used to study motion-related tasks in several studies. However, the validation of this software in open field test to assess locomotor activity have not been studied yet. Therefore, this study aimed to examine the reliability and validity of this software in analyzing locomotor activities. Methods: Thirty male Institute Cancer Research mice were subjected in this study. The results examined by this software and the classical method were compared. Test-retest reliability and inter-rater reliability were analyzed with Pearson's correlation coefficient and intraclass correlation coefficient (ICC). The validity of this software was analyzed with Pearson's correlation coefficient. Results: This software showed good test-retest reliability (ICC=0.997, 95% confidence interval [CI]=0.975-0.994, p<0.001). This software also showed good inter-rater reliability (ICC=0.987, 95% CI=0.973-0.994, p<0.001). Furthermore, in three analyses for the validity of this software, there were significant correlations between two methods (Pearson's correlation coefficient=0.928-0.972, p<0.001). In addition, this software showed good reliability and validity in the analysis locomotor activity according to time interval. Conclusion: This study showed that this software in analyzing drug-induced locomotor activity has good reliability and validity. This software can be effectively used in animal study using the analysis of locomotor activity.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.149-152
• /
• 2016

In this paper, we propose an algorithm to track human body of input video from a single camera. The proposed method gets the difference image between gray image of input image and one of background image and also the difference image between hue image of input image and one of background image. Then we combine the results, splits foreground and background and detect human body objects. Then each object is numbered and is tracked. The proposed method tracks each object using the intensity and hue histogram of local area in objects. The proposed method is applied to video from a camera and tracked well the hided objects and the overlapped objects.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.409-419
• /
• 2023

Structural integrity can be accessed from dynamic deformations of structures. Moreover, dynamic deformations can be acquired from non-contact sensors such as video cameras. Kanade-Lucas-Tomasi (KLT) algorithm is one of the commonly used methods for motion tracking. However, averaging throughout the extracted features would induce bias in the measurement. In addition, pixel-wise measurements can be converted to physical units through camera intrinsic. Still, the depth information is unreachable without prior knowledge of the space information. The assigned homogeneous coordinates would then mismatch manually selected feature points, resulting in measurement errors during coordinate transformation. In this study, a two-stage optimization method for video-based measurements is proposed. The manually selected feature points are first optimized by minimizing the errors compared with the homogeneous coordinate. Then, the optimized points are utilized for the KLT algorithm to extract displacements through inverse projection. Two additional criteria are employed to eliminate outliers from KLT, resulting in more reliable displacement responses. The second-stage optimization subsequently fine-tunes the geometry of the selected coordinates. The optimization process also considers the number of interpolation points at different depths of an image to reduce the effect of out-of-plane motions. As a result, the proposed method is numerically investigated by using a truss bridge as a physics-based graphic model (PBGM) to extract high-accuracy displacements from recorded videos under various capturing angles and structural conditions.