• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.125-132
• /
• 2023

Roundabouts have strengths in traffic flow and safety but can present difficulties for inexperienced drivers. Demand to acquire and analyze drone images has increased to enhance a traffic environment allowing drivers to deal with roundabouts easily. In this paper, we propose a roundabout traffic analysis system that detects, tracks, and analyzes vehicles using a deep learning-based object detection model (YOLOv7) in drone images. About 3600 images for object detection model learning and testing were extracted and labeled from 1 hour of drone video. Through training diverse conditions and evaluating the performance of object detection models, we achieved an average precision (AP) of up to 97.2%. In addition, we utilized SORT (Simple Online and Realtime Tracking) and OC-SORT (Observation-Centric SORT), a real-time object tracking algorithm, which resulted in an average MOTA (Multiple Object Tracking Accuracy) of up to 89.2%. By implementing a method for measuring roundabout entry speed, we achieved an accuracy of 94.5%.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1415-1429
• /
• 2019

Nowadays object tracking process becoming one of the most challenging task in Computer Vision filed. A CSR-DCF (channel spatial reliability-discriminative correlation filter) tracking algorithm have been proposed on recent tracking benchmark that could achieve stat-of-the-art performance where channel spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process with only two simple standard features, HoGs and Color names. However, there are some cases where this method cannot track properly, like overlapping, occlusions, motion blur, changing appearance, environmental variations and so on. To overcome that kind of complications a new modified version of CSR-DCF algorithm has been proposed by integrating deep learning based object detection and CSRT tracker which implemented in OpenCV library. As an object detection model, according to the comparable result of object detection methods and by reason of high efficiency and celerity of Faster RCNN (Region-based Convolutional Neural Network) has been used, and combined with CSRT tracker, which demonstrated outstanding real-time detection and tracking performance. The results indicate that the trained object detection model integration with tracking algorithm gives better outcomes rather than using tracking algorithm or filter itself.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.186-192
• /
• 2021

Recently, the demand for more precise and demand-oriented customized spatial information is increasing due to the 4th industrial revolution. In particular, the use of 3D spatial information and digital twins which based on spatial information, and research for solving social problems in cities by using such information are continuously conducted. Globally, non-face-to-face services are increasing due to COVID-19, and the national policy direction is also rapidly progressing digital transformation, digitization and virtualization of the Korean version of the New Deal, which means that 3D spatial information has become an important factor to support it. In this study, physical objects for cities defined by world organizations such as ISO, OGC, and ITU were selected and the target of the 3D object model was limited to buildings. Based on CityGML2.0, the data collected using a drone suitable for building a 3D model of a small area is selected to be updated through road name address and building ledger, which are administrative information related to this, and LoD2.5 data is constructed and urban space. It was intended to suggest an object update method for a 3D building among data.

• Journal of Advanced Navigation Technology
• /
• v.23 no.1
• /
• pp.77-83
• /
• 2019

In this paper, we propose an object tracking algorithm based on color histogram and convolutional neural network model. In order to increase the tracking accuracy, we synthesize generic object tracking using regression network algorithm which is one of the convolutional neural network model-based tracking algorithms and a mean-shift tracking algorithm which is a color histogram-based algorithm. Both algorithms are classified through support vector machine and designed to select an algorithm with higher tracking accuracy. The mean-shift tracking algorithm tends to move the bounding box to a large range when the object tracking fails, thus we improve the accuracy by limiting the movement distance of the bounding box. Also, we improve the performance by initializing the tracking start positions of the two algorithms based on the average brightness and the histogram similarity. As a result, the overall accuracy of the proposed algorithm is 1.6% better than the existing generic object tracking using regression network algorithm.

• Journal of Broadcast Engineering
• /
• v.18 no.1
• /
• pp.1-9
• /
• 2013

Accuracy of the 3-D model is essential in model-based camera tracking. However, 3-D object modeling requires dedicated and complicated procedures for precise modeling without any errors. Even if a 3-D model contains a certain level of errors, on the other hand, the tracking errors cause by the modeling errors can be different from its perceptual errors; thus, it is an important aspect that the camera tracking can be successful without precise 3-D modeling if the modeling errors are within the user's permissible range. In this paper, we analyze the tolerance of 3-D object modeling errors by comparing computational matching errors with perceptual matching errors through user evaluations, and also discuss permissible ranges of 3-D object modeling errors.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.185-186
• /
• 2006

Image Guided Surgery(IGS) system has been developed to provide exquisite and objective information to surgeons for surgical operation process. It is necessary that registration technique is important to match between 3D image model reconstructed from image modalities and the object operated by surgeon. Majority techniques of registration in IGS system have been used by recognizing fiducial markers placed on the object. However, this method has been criticized due to its invasive protocol inserting fiducial markers in patient's bone. Therefore, shape-based registration technique using geometric characteristics of the object has been invested to improve the limitation of IGS system. During Total Knee Replacement(TKR) operation, it is challenge to register with high accuracy by using shape-based registration because the area to acquire sample data from knee is limited. We have developed region-based 3D registration technique based on anatomical landmarks on the object and this registration algorithm was evaluated in femur model. It was found that region-based algorithm can improve the accuracy in 3D registration. We expect that this technique can efficiently improve the IGS system.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.6
• /
• pp.63-69
• /
• 2016

In this paper, we proposed the location tracking system based on MS-Based/Assisted(Mobile Station-Based and Assisted) location trigger service model with context-awareness for the intelligent location tracking of moving objects. It provides the proper resulting value that matches the context of users through the analysis about the situation of the user, physical environment, computing resource and the existing information on user input. In order to provide real-time data, we proposed the location tracking system which realizes the intelligent information such as the expecting arrival time and passing the specific area of the moving object by adopting the location trigger. So, it derives to minimize the costs of communication for the mobile object tracking applications. The proposed location tracking system based on context-awareness can be used for realtime monitoring, intelligent alarm/action, setting up of the optimized moving path, dynamic adjustment of strategies and policies. So it has the advantage to develop the application system which is aimed at optimization of the object tracking and movement.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.5
• /
• pp.277-285
• /
• 2016

Moving object detection system has been an emerging research field in various advanced driver assistance systems (ADAS) and surveillance system. In this paper, we propose two optical flow based moving object detection methods at dynamic scenes. Both proposed methods consist of three successive steps; pre-processing, foreground segmentation, and post-processing steps. Two proposed methods have the same pre-processing and post-processing steps, but different foreground segmentation step. Pre-processing calculates mainly optical flow map of which each pixel has the amplitude of motion vector. Dense optical flows are estimated by using Farneback technique, and the amplitude of the motion normalized into the range from 0 to 255 is assigned to each pixel of optical flow map. In the foreground segmentation step, moving object and background are classified by using the optical flow map. Here, we proposed two algorithms. One is Gaussian mixture model (GMM) based background subtraction, which is applied on optical map. Another is adaptive thresholding based foreground segmentation, which classifies each pixel into object and background by updating threshold value column by column. Through the simulations, we show that both optical flow based methods can achieve good enough object detection performances in dynamic scenes.

• Journal of Power System Engineering
• /
• v.13 no.2
• /
• pp.71-82
• /
• 2009

This paper presents a real-time haptic rendering method for a realistic force feedback in a remote environment with varying communication time-delay. The remote environment is assumed as a virtual environment based on a computer graphics, for example, on-line shopping mall, internet game and cyber-education. The properties of a virtual object such as stiffness and viscosity are assumed to be unknown because they are changed according to the contact position and/or a penetrated depth into the object. The DARMAX model based output estimator is proposed to trace the correct impedance of the virtual object in real-time. The output estimator is developed on the input-output relationship. It can trace the varying impedance in real-time by virtue of P-matrix resetting algorithm. And the estimator can trace the correct impedance by using a white noise that prevents the biased input-output information. Realistic output forces are generated in real-time, by using the inputs and the estimated impedance, even though the communication time delay and the impedance of the virtual object are unknown and changed. The generated forces trace the analytical forces computed from the virtual model of the remote environment. Performance is demonstrated by experiments with a 1-dof haptic device and a spring-damper-based virtual model.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.2
• /
• pp.37-42
• /
• 2000

Object technologies like the OMG's CORBA are enabling technologies the aim to facilitate integration implementation of diverse software components in distributed. heterogeneous environment. CORBA and similar object integration technologies define a standard component interconnection and inter-operation model , promote object-oriented principles to encapsulate incompatible component implementations. In this Paper. we present a connector model for software architectural representation of complex component collaborations. Our Connector model is base on research in software achitecture and object-oriented modeling. and part of a design framework for modeling component-based system. We believe the connector concepts to be vary benificial for a clear expression of dependencies between multiple component in Java Bean-based system.