• International Journal of Precision Engineering and Manufacturing
• /
• v.5 no.1
• /
• pp.27-35
• /
• 2004

In the field of machine vision using a single camera mounted on a mobile robot, although the detection and tracking of moving objects from a moving observer, is complex and computationally demanding task. In this paper, we propose a new scheme for a mobile robot to track and capture a moving object using images of a camera. The system consists of the following modules: data acquisition, feature extraction and visual tracking, and trajectory generation. And a single camera is used as visual sensors to capture image sequences of a moving object. The moving object is assumed to be a point-object and projected onto an image plane to form a geometrical constraint equation that provides position data of the object based on the kinematics of the active camera. Uncertainties in the position estimation caused by the point-object assumption are compensated using the Kalman filter. To generate the shortest time trajectory to capture the moving object, the linear and angular velocities are estimated and utilized. The experimental results of tracking and capturing of the target object with the mobile robot are presented.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.113-117
• /
• 2005

This paper describes a visual control scheme, fuzzy logic system for visual servoing of an autonomous mobile robot. An existing communication autonomous mobile robot always needs to keep the object in image to detect the moving object. This is a problem in an autonomous mobile robot for spontaneous activity. To solve it, some features for an object are taken from an image and then use in the design of fuzzy logic system for decision of moving location and direction of visual servoing contrivance(apparatus). So continuous tracking is possible by moving the visual servoing contrivance. We present some simulation results and further studies in the Section of Simulation and Concluding Remarks.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.5
• /
• pp.1220-1228
• /
• 1995

In this paper, we consider the problems of tracking an object in a real image. In evaluating these problems, we explore a new technique based on an active contour model commonly called a snake model, and propose the active bar models to represent target. Using this model, we simplified the target welection problems, reduced the search space of energy surface, and obtained the better performances than those of snake model. This approach improves the numerical stability and the tendency for points to bunch up and speed up the computational efficiency. Representing the object by active bar, we can easily obtain the zeroth, the first, and the second moment and it facilitates the target tracking. Finally, we present the good result for the visual tracking problem.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1134-1139
• /
• 2003

Tracking is a fundamental technique which is able to be applied to gesture recognition, visual surveillance, tangible agent and so forth. Especially, multiple object tracking has been extensively studied in recent years in order to perform many and more complicated tasks. In this paper, we propose a new approach of multiple object tracking which is based on discrete event. We call this system the DEMOT (Discrete Event based Multiple Object Tracking). This approach is based on the fact that a multiple object tracking can have just four situations - initiation, continuation, termination, and overlapping. Here, initiation, continuation, termination, and overlapping constitute a primary event set and this is based on the change of the number of extracted objects between a previous frame and a current frame. This system reduces computational costs and holds down the identity of all targets. We make experiments for this system with respect to the number of targets, each event, and processing period. We describe experimental results that show the successful multiple object tracking by using our approach.

• Journal of Korea Multimedia Society
• /
• v.20 no.6
• /
• pp.893-910
• /
• 2017

In this paper, we propose a simple online multiple object (human) tracking method, LKDeep (Lucas-Kanade feature and Detection based Simple Online Multiple Object Tracker), which can run in fast online enough on CPU core only with acceptable tracking performance for embedded surveillance purpose. The proposed LKDeep is a pragmatic hybrid approach which tracks multiple objects (humans) mainly based on LK features but is compensated by detection on periodic times or on necessity times. Compared to other state-of-the-art multiple object tracking methods based on 'Tracking-By-Detection (TBD)' approach, the proposed LKDeep is faster since it does not have to detect object on every frame and it utilizes simple association rule, but it shows a good object tracking performance. Through experiments in comparison with other multiple object tracking (MOT) methods using the public DPM detector among online state-of-the-art MOT methods reported in MOT challenge [1], it is shown that the proposed simple online MOT method, LKDeep runs faster but with good tracking performance for surveillance purpose. It is further observed through single object tracking (SOT) visual tracker benchmark experiment [2] that LKDeep with an optimized deep learning detector can run in online fast with comparable tracking performance to other state-of-the-art SOT methods.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.72-81
• /
• 2022

Visual Object Tracking is known as the most fundamental problem in the field of computer vision. Object tracking localize the region of target object with bounding box in the video. In this paper, a custom CNN is created to extract object feature that has strong and various information. This network was constructed as a Siamese network for use as a feature extractor. The input images are passed convolution block composed of a bottleneck layers, and features are emphasized. The feature map of the target object and the search area, extracted from the Siamese network, was input as a local proposal network. Estimate the object area using the feature map. The performance of the tracking algorithm was evaluated using the OTB2013 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.611 in Success Plot and 0.831 in Precision Plot were achieved.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.469-470
• /
• 2018

Object tracking is a common task in computer vision, an essential part of various vision-based applications. After several years of development, object tracking in video is still a challenging problem because of various visual properties of objects and surrounding environment. Particle filter is a well-known technique among common approaches, has been proven its effectiveness in dealing with difficulties in object tracking. However, particle filter is a high-complexity algorithms, which is an severe disadvantage because object tracking algorithms are required to run in real time. In this research, we utilize parallel programming to accelerate particle filter-based object tracking algorithms. Experimental results showed that our approach reduced the execution time significantly.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.3 no.4
• /
• pp.344-365
• /
• 2009

The performance of a tracking system is greatly increased if multiple types of sensors are combined to achieve the objective of the tracking instead of relying on single type of sensor. To conduct the multi-modal tracking, we have previously developed a multi-modal sensor-based tracking model where acoustic sensors mainly track the objects and visual sensors compensate the tracking errors [1]. In this paper, we find a network synchronization problem appearing in the developed tracking system. The problem is caused by the different location and traffic characteristics of multi-modal sensors and non-synchronized arrival of the captured sensor data at a processing server. To effectively deliver the sensor data, we propose a time-based packet aggregation algorithm where the acoustic sensor data are aggregated based on the sampling time and sent to the server. The delivered acoustic sensor data is then compensated by visual images to correct the tracking errors and such a compensation process improves the tracking accuracy in ideal case. However, in real situations, the tracking improvement from visual compensation can be severely degraded due to the aforementioned network synchronization problem, the impact of which is analyzed by simulations in this paper. To resolve the network synchronization problem, we differentiate the service level of sensor traffic based on Weight Round Robin (WRR) scheduling at the routers. The weighting factor allocated to each queue is calculated by a proposed Delay-based Weight Allocation (DWA) algorithm. From the simulations, we show the traffic differentiation model can mitigate the non-synchronization of sensor data. Finally, we analyze expected traffic behaviors of the tracking system in terms of acoustic sampling interval and visual image size.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.89-92
• /
• 1996

In this paper, we developed visual tracking algorithm using double active bar. The active bar model to represent the object can reduce the search space of energy surface and better performance than those of snake model. However, the contour will not find global equilibrium when driving force caused by image may be weak. To overcome this problem. Double active bar is proposed for finding the global minimum point without any dependence on initialization. To achieve the goal, an deformable model with two initial contours in attempted to search for a global minimum within two specific initial contours. This approach improve the performance of finding the contour of target. To evaluate the performance, some experiments are executed. We can achieved the good result for tracking a object on noisy image.

• Journal of Welding and Joining
• /
• v.22 no.6
• /
• pp.43-49
• /
• 2004

In this study, a visual sensor system which can detect I-butt weld joint with height variation and includes a seam tracking algorithm was investigated. Three-dimensional position of an object can be acquired by using the method of distance measurement, i.e., an optical trigonometry which results from the spatial relations between the camera, the object and the structured light by a visible laser. Effects of laser intensity and iris number for the image quality as well as object material were investigated for the optical system design. For the image processing, a region of interest is defined from the whole image and a line image of laser is drew by using the gray level difference in the image. From the drew laser line, the weld joint can be recognized in searching the biggest point position calculated from the central difference method. Through a series of welding experiments, a good tracking performance was confirmed under GMA welding.