• 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%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.465-469
• /
• 2017

In this paper we propose a human body tracking method for application of smartphones. The conventional human body tracking method is divided into a sensor-based method and a vision-based method. The sensor-based methods have a weakness in that tracking accuracy is low due to cumulative error of position information. The vision-based method has no cumulative error, but it requires reduction of the computational complexity for application of smartphone. In this paper we use the improved HOG algorithm as a human body tracking method for application of smartphone. The improved HOG algorithm is implemented through downsampling and frame sampling. Gaussian pyramid is applied for downsampling, and uniform sampling is applied for frame sampling. We measured the proposed algorithm on two devices, four resolutions, and four frame sampling intervals. We derive the best detection rate among downsampling and frame sampling parameters that can be applied in realtime.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.750-753
• /
• 2012

A method detecting the position of eyes and tracking a gaze point of eyes in realtime using POSIT is suggested in this paper. This algorithm find out a candidate area of eyes using topological characteristics of eyes and then decides the center of eyes using physical characteristics of eyes. To find the eyes, a nose and a mouth are used for POSIT. The experimental results show that proposed method effectively performed detection of eyes in facial image in FERET databases and gave high performance when used for tracking a gaze point of eyes.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.465-470
• /
• 2002

This paper presents a new model based method for tracking moving object from a moving camera. In the proposed method, binary model is derived from detected object regions and Hausdorff distance between the model and edge image is used as its similarity measure to overcome the target's shape changes. Also, a novel search algorithm and some optimization methods are proposed to enable realtime processing. The experimental results on our test sequences demonstrate the high efficiency and accuracy of our approach.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.7
• /
• pp.749-757
• /
• 1992

In this paper, as a more effective approach for maneuvering target tracking a realtime optical tracking system based of optical JTC(Joint Transform Correlator) which is capable of transforming the massive input target data into a few correlation peaks is implemented. And for real-time implementation the high resolution LCD(Liquid Crystal Display) spatialight modulator is used to construct the optical JTC system, and the mean binarization method is used to reduce the effects of background noises on correlation signal. From the good experimental results on maneuvering targets, the possibility of real-time moving target tarcking system based on optical JTC is a suggested.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.79-84
• /
• 2009

Recently, many researches are being carried out on monitoring animal behaviour and interactions with the environment using sensor networks and for tracing animal chain management and identifying animals using RFID techniques. And we are studying about the management and burglarproof of a pet using GPS technique. But there is a lack of study for providing users intelligence services in zoo using GPS, RFID, and sensor networks. Accordingly, in this paper, we propose a intelligence tracking service of animal situation based on GPS, RFID, and sensor in zoo. Firstly, we present a tracking service scenario of animal situation and system configuration according to this scenario. The proposed service provides users realtime animal situation information of animal like the present location, temperature, image, etc. In addition, we can chase the animals to know a location and situation of animal when the animals escapes from their cages. Next, we implement and test prototype operations of animal tracking system based on this scenario to verify the proposed service.

• Aerospace Engineering and Technology
• /
• v.12 no.2
• /
• pp.1-6
• /
• 2013

A LEO satellite transmits recorded images to a ground station using an X-band antenna during contact. The X-band antenna points to the ground station according to a TPF (tracking parameter file) during communication time. A TPF generation software generates azimuth and elevation profile which make the antenna point to the ground station using satellite orbit and attitude information and mission information including recording and downlink operation. When the satellite passes above the ground station, azimuth velocity increases rapidly so that jitter may occur if the azimuth velocity is in specific range. In case of realtime mission in which the satellite perform recording and downlink simultaneously, azimuth velocity must be lower than specific value to prevent image blur due to jitter effect. The method to point one virtual ground station has limitation of azimuth velocity reduction. In this paper, we propose the azimuth fixing method to reduce azimuth velocity of X-band antenna. The experimental results show that azimuth velocity of the X-band antenna is remarkably reduced using proposed method.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.542-546
• /
• 2009

This paper introduces a Mixed-Reality based Software technology in Smart-Phone Environment. The field of Mixed-Reality in mobile environment is relatively young. but Cause to develop Mobile infra and improvement of mobile device, open-platform mobile OS, the request extended This paper suggest the method for Marker Detection and Marker Tracking method. This method is the one of some kind of a base-technology in Mixed Reality. this method is to effect to location and registration. This paper suggest the method in low CPU computing power. Using a deformable searching area, the method improve computing power. and Using a Cam-shift algorithm, we suggest a calibration free method.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.3
• /
• pp.195-200
• /
• 2012

To steer a camera is done based on system parameters of the vision system. However, the system parameters when they are used might be different from those when they were measured. As one method to compensate for this problem, this research proposes a gaze-steering method based on LMI(Linear Matrix Inequality) that is robust to variations in the system parameters of the vision system. Simulation results show that the proposed method produces less gaze-tracking error than a contemporary linear method and more stable gaze-tracking error than a contemporary nonlinear method. Moreover, the proposed method is fast enough for realtime processing.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.1-20
• /
• 2022

As unmanned aerial vehicle (UAV) technology grew in popularity over the years, it was introduced for air quality monitoring. This can easily be used to estimate the sidewalk emission concentration by calculating road traffic emission factors of different vehicle types. These calculations require a simulation of the spread of pollutants from one or more sources given for estimation. For this purpose, a Gaussian plume dispersion model was developed based on the US EPA Motor Vehicle Emissions Simulator (MOVES), which provides an accurate estimate of fuel consumption and pollutant emissions from vehicles under a wide range of user-defined conditions. This paper describes a methodology for estimating emission concentration on the sidewalk emitted by different types of vehicles. This line source considers vehicle parameters, wind speed and direction, and pollutant concentration using a UAV equipped with a monocular camera. All were sampled over an hourly interval. In this article, the YOLOv5 deep learning model is developed, vehicle tracking is used through Deep SORT (Simple Online and Realtime Tracking), vehicle localization using a homography transformation matrix to locate each vehicle and calculate the parameters of speed and acceleration, and ultimately a Gaussian plume dispersion model was developed to estimate the CO, NOx concentrations at a sidewalk point. The results demonstrate that these estimated pollutants values are good to give a fast and reasonable indication for any near road receptor point using a cheap UAV without installing air monitoring stations along the road.