• Journal of Information Science Theory and Practice
• /
• v.2 no.4
• /
• pp.31-48
• /
• 2014

The proliferation of many interactive Topic Detection and Tracking (iTDT) systems has motivated researchers to design systems that can track and detect news better. iTDT focuses on user interaction, user evaluation, and user interfaces. Recently, increasing effort has been devoted to user interfaces to improve TDT systems by investigating not just the user interaction aspect but also user and task oriented evaluation. This study investigates the combination of the bag of words and named entities approaches implemented in the iTDT interface, called Interactive Event Tracking (iEvent), including what TDT tasks these approaches facilitate. iEvent is composed of three components, which are Cluster View (CV), Document View (DV), and Term View (TV). User experiments have been carried out amongst journalists to compare three settings of iEvent: Setup 1 and Setup 2 (baseline setups), and Setup 3 (experimental setup). Setup 1 used bag of words and Setup 2 used named entities, while Setup 3 used a combination of bag of words and named entities. Journalists were asked to perform TDT tasks: Tracking and Detection. Findings revealed that the combination of bag of words and named entities approaches generally facilitated the journalists to perform well in the TDT tasks. This study has confirmed that the combination approach in iTDT is useful and enhanced the effectiveness of users' performance in performing the TDT tasks. It gives suggestions on the features with their approaches which facilitated the journalists in performing the TDT tasks.

• Journal of Broadcast Engineering
• /
• v.7 no.2
• /
• pp.181-191
• /
• 2002

Video based surveillance systems based on an active camera require a fast algorithm for real time detection and tracking of local motion in the presence of global motion. This paper presents a new fast and efficient motion detection and tracking algorithm using the displaced frame difference (DFD). In the Proposed algorithm, first, a Previous frame is adaptively selected according to the magnitude of object motion, and the global motion is estimated by using only a few confident matching blocks for a fast and accurate result. Then, a DFD is obtained between the current frame and the selected previous frame displaced by the global motion. Finally, a moving object is extracted from the noisy DFD by utilizing the correlation between the DFD and current frame. We implement this algorithm into an active camera system including a pan-tilt unit and a standard PC equipped with an AMD 800MHz processor. The system can perform the exhaustive search for a search range of 120, and achieve the processing speed of about 50 frames/sec for video sequences of 320$\times$240. Thereby, it provides satisfactory tracking results.

• The Journal of Korea Robotics Society
• /
• v.6 no.1
• /
• pp.86-96
• /
• 2011

The human-following is one of the significant procedure in human-friendly navigation of mobile robots. There are many approaches of human-following technology. Many approaches have adopted various multiple sensors such as vision system and Laser Range Finder (LRF). In this paper, we propose detection and tracking approaches for human legs by the use of a single LRF. We extract four simple attributes of human legs. To define the boundary of extracted attributes mathematically, we used a Support Vector Data Description (SVDD) scheme. We establish an efficient leg-tracking scheme by exploiting a human walking model to achieve robust tracking under occlusions. The proposed approaches were successfully verified through various experiments.

• Journal of Integrative Natural Science
• /
• v.9 no.2
• /
• pp.155-160
• /
• 2016

Applying image processing techniques to education, the face of the learner is photographed, and expression and movement are detected from video, and the system which estimates degree of concentration of the learner is developed. For one learner, the measuring system is designed in terms of estimating a degree of concentration from direction of line of learner's sight and condition of the eye. In case of multiple learners, it must need to measure each concentration level of all learners in the classroom. But it is inefficient because one camera per each learner is required. In this paper, position in the face region is estimated from video which photographs the learner in the class by the difference between frames within the motion direction. And the system which detects the face direction by the face part detection by template matching is proposed. From the result of the difference between frames in the first image of the video, frontal face detection by Viola-Jones method is performed. Also the direction of the motion which arose in the face region is estimated with the migration length and the face region is tracked. Then the face parts are detected to tracking. Finally, the direction of the face is estimated from the result of face tracking and face parts detection.

• Journal of Information Technology Applications and Management
• /
• v.11 no.4
• /
• pp.169-179
• /
• 2004

There are many inductive loop detectors under the highways in Korea. Among the other detectors, some are image detectors. Almost all image detectors are focused one or two lane of the road and are measuring traffic information. This paper proposes to an algorithm for detecting traffic information automatically from CCTV camera images installed on the highway. The information which is counted in one lane or two contains some critical errors by occlusion frequently in case of passing larger vehicles. In this paper, we use a tracking algorithm in which the detection area include all lanes, then the traffic informations are collected from the vehicles individually using difference images in this detection area. This tracking algorithm is better than lane by lane detecting algorithm. The experiment have been conducted two different real road scenes for 20 minutes. For the experiments, the images are provided with CCTV camera which was installed at Kiheung Interchange upstream of Kyongbu highway, and video recording images at Chungkye Tunnel. For image processing, images captured by frame-grabber board 30 frames per second, 640${\times}$480 pixels resolution and 256 gray-levels to reduce the total amount of data to be Interpreted.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.11
• /
• pp.976-983
• /
• 2002

We presents a modified variable dimension filter with input estimation for maneuvering target tracking. The conventional variable dimension filter with input estimation(VDIE) consists of the input estimation(IE) technique and the variable dimension(VD) filter. In the VDIE, the IE technique is used for estimation of a maneuver onset time and its magnitude in the least square sense. The detection of the maneuver is declared according to the estimated magnitude of the maneuver. The VD filter structure is applied for the adaptation to the maneuver of the target after compensating the filter parameter with respect to the estimated maneuver when the detection of the maneuver is declared. The VDIE is known as one of the best maneuvering target tracking filter based on a single filter. However, it requires too much computational burden since the IE technique is performed at every sampling instance and thus it is computationally inefficient. We propose another variable dimension filter with input estimation named 'Modified VDIE' which combines VD filter with If technique. Modified VDIE has less computational load than the original one by separating maneuver detection and input estimation. Simulation results show that the proposed VDIE is more efficient and outperforms in terms of computational load.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1491-1494
• /
• 2002

The paper introduces a novel system of two hands real-time tracking based on the unrestricted hand skin segmentation by multi color systems. After corer-based segmentation and pre-processing operation, a label set of regions is created to locate the two hands automatically. By the normalization, template matching is used to find out the left or right hand. An improved fast self-adaptive tracking algorithm is applied and Canny filter is used for hand detection.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.7
• /
• pp.17-24
• /
• 2015

In this paper, we propose a method to solve ghosting problem. To generate adaptive background, using an exponentially decreasing number of frames, may improve object detection performance. To extract moving objects from the background by using a differential image, detection error may be caused by object rotations or environmental changes. A ghosting problem can be issue-driven when there are outdoor environmental changes and moving objects. We studied that a differential image by adaptive background may reduce the ghosting problem. In experimental results, we test that our method can solve the ghosting problem.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.1-6
• /
• 2003

In this Paper, the moving image is detected by a collision preventive system. The noise of these images is reduced by a mean filter. In case of detecting a movement with a binary difference image the moving area is detected exactly by the labeling and the projective method. When the image move slowly with the tracking mode of the system, the center of the tracking window move to the previous tracking window. And the tracking windows are divided into a tracking mode and a coasting mode which are determine by the Contrast-Difference Correlation of the date obtained from a difference image. The coasting mode determine whether continue the tracking step or not comparing the coasting-time values to reducing the error by the disturbance. The coasting and tracking of these moving images are verified by the result of the simulation.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.107-112
• /
• 2018

In this paper, optical flow based keypoint detection and tracking technique is proposed for the collaboration between flying drone with vision system and ground robots. There are many challenging problems in target detection research using moving vision system, so we combined the improved FAST algorithm and Lucas-Kanade method for adopting the better techniques in each feature detection and optical flow motion tracking, which results in 40% higher in processing speed than previous works. Also, proposed image binarization method which is appropriate for the given marker helped to improve the marker detection accuracy. We also studied how to optimize the embedded system which is operating complex computations for intelligent functions in a very limited resources while maintaining the drone's present weight and moving speed. In a future works, we are aiming to develop collaborating smarter robots by using the techniques of learning and recognizing targets even in a complex background.