• Journal of KIISE:Software and Applications
• /
• v.32 no.5
• /
• pp.449-460
• /
• 2005

This paper proposes a method to track persons robustly in illumination changes and partial occlusions in color video frames acquired from a fixed camera. To solve a problem of changing appearance by illumination change, a time-independent intrinsic image is used to remove noises in an frame and is adaptively updated frame-by-frame. We use a hierarchical human model including body color information in order to track persons in occlusion. The tracked human model is recorded into a persons' list for some duration after the corresponding person's exit and is recovered from the list after her reentering. The proposed method was experimented in several indoor and outdoor scenario. This demonstrated the potential effectiveness of an adaptive model-base method that corrected distorted person's color information by lighting changes, and succeeded tracking of persons which was overlapped in a frame.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.63-70
• /
• 2023

Due to the spread of high-definition black boxes and the introduction of mobile applications such as 'Smart Citizens Report' and 'Safety Report', the number of public interest reports for violations of Traffic Law has increased rapidly, resulting in shortage of police personnel to handle them. In this paper, we describe the development of a system that can automatically detect lane violations which account for the largest proportion of public interest reporting videos for violations of traffic laws, using deep learning algorithms. In this study, a method for recognizing a vehicle and a solid line object using a YOLO model and a Lanenet model, a method for tracking an object individually using a deep sort algorithm, and a method for detecting lane change violations by recognizing the overlapping range of a vehicle object's bounding box and a solid line object are described. Using this system, it is expected that the shortage of police personnel in charge will be resolved.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.28 no.2
• /
• pp.89-95
• /
• 2017

Background and Objectives : High-speed videolaryngoscopy (HSV) is the only technique that captures the true intra-cycle vibratory behavior of the vocal folds by capturing full images of the vocal folds. However, it has problems of no immediate feedback during examination, considerable waiting time for digital kymography (DKG), recording duration limited to a few seconds, and extreme demands for storage space. Herein, we demonstrate a new post-processing method that converts HSV images to two-dimensional digital kymography (2D-DKG) images, which adopts the algorithm of 2D videokymography (2D VKG). Materials and Methods : HSV system was used to capture images of vocal folds. HSV images were post-processed in Kay image-process software (KIPS), and conventional DKG images were retrieved. Custom-made post-processing system was used to convert HSV images to 2D-DKG images. The quantitative parameters of the post-processed 2D-DKG images was validated by comparing these parameters with those of the DKG images. Results : Serial HSV images for all phases of vocal fold vibratory movement are included. The images were converted by the scanning method using U-medical image-process software. Similar to conventional DKG, post-processed 2D DKG image from the HSV image can provide quantitative information on vocal fold mucosa vibration, including the various vibratory phases. Differences in amplitude symmetry index, phase symmetry index, open quotient, and close quotient between 2D-DKG and DKG were analyzed. There were no statistical differences between the quantitative parameters of vocal fold vibratory movement in 2D-DKG and DKG. Conclusion : The post-processing method of converting HSV images to 2D DKG images could provide clinical information and storage economy.

• Journal of Broadcast Engineering
• /
• v.14 no.6
• /
• pp.692-702
• /
• 2009

Real-time virtual studios which could run only on expensive workstations are now available for personal computers thanks to the recent development of graphics hardware. Nevertheless, graphics are rendered off-line in the post production stage in film or TV drama productions, because the graphics' quality is still restricted by the real-time hardware. Software-based camera tracking methods taking only the source video into account take much computation time, and often shows unstable results. To overcome this restriction, we propose a system that stores camera motion data from sensors at shooting time as common virtual studios and uses them in the post production stage, named as POVIS(post virtual imaging system). For seamless registration of graphics onto the camera video, precise zoom lens calibration must precede the post production. A practical method using only two planar patterns is used in this work. We present a method to reduce the camera sensor's error due to the mechanical mismatch, using the Kalman filter. POVIS was successfully used to track the camera in a documentary production and saved much of the processing time, while conventional methods failed due to lack of features to track.

• Journal of Broadcast Engineering
• /
• v.16 no.3
• /
• pp.448-461
• /
• 2011

H.264/AVC significantly outperforms the previous video coding standards with many new coding tools. Among these tools, several intra-block coding tools can particularly improve coding efficiency. For intra prediction, H.264/AVC supports most probable mode in the entropy coding process to reduce syntax elements indicating intra prediction modes and most probable mode selection ratio is very high. Also, in general, natural images and videos have many homogeneous regions whose high correlation with neighbouring blocks. In this paper, we propose intra prediction mode SKIP mode using decoder-side prediction to improve the coding efficiency. The proposed method is determined the optimal prediction mode using only neighbouring block's information and coded on the basis of the conventional prediction/transform coding. And the prediction modes are not send to decoder at all. Skipped intra prediction mode is determined by decoder. Experimental results show that the proposed method achieves coding gains of 1.40% for common intermediate format(CIF), 3.24% for 720p sequences against the H.264/AVC JM 17.0 reference software.

• Journal of KIISE:Software and Applications
• /
• v.34 no.3
• /
• pp.255-265
• /
• 2007

In this paper, we propose a new illumination-robust drowsy driver monitoring system with single CCD(Charge Coupled Device) camera for intelligent vehicle in the day and night. For this system that is monitoring driver's eyes during a driving, the eye detection and the measure of eyelid movement are the important preprocesses. Therefore, we propose efficient illumination compensation algorithm to improve the performance of eye detection and also eyelid movement measuring method for efficient drowsy detection in various illumination. For real-time application, Cascaded SVM (Cascaded Support Vector Machine) is applied as an efficient eye verification method in this system. Furthermore, in order to estimate the performance of the proposed algorithm, we collect video data about drivers under various illuminations in the day and night. Finally, we acquired average eye detection rate of over 98% about these own data, and PERCLOS(The percentage of eye-closed time during a period) are represented as drowsy detection results of the proposed system for the collected video data.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.11-19
• /
• 2006

The recent video coding standard H.264 employs the rate-distortion optimization (RDO) method for choosing the best coding mode; however, it causes a large amount of encoding time. Thus, in order to reduce the encoding time, we need a fast mode decision algorithm. In this paper, we propose a fast inter mode decision algorithm considering quantization parameter (QP). The occurrence of best modes depends on QP. In order to reflect these characteristics, we consider the coded block pattern (CBP) which has 0 value when all quantized discrete cosine transform (DCT) coefficients are zero. We also use the early SKIP mode decision and early $16{\times}16$ mode decision methods. By computer simulations, we have verified that the proposed algorithm requires less encoding time than the fast inter mode decision method of the H.264 reference software for the Baseline and Main profiles by 19.6% and 18.8%, respectively.

• International Journal of Highway Engineering
• /
• v.18 no.6
• /
• pp.69-76
• /
• 2016

OBJECTIVES : The objective of this study is to propose a capacity analysis methodology for riverside bike-exclusive roads. METHODS : Three steps were performed to develop a methodology to estimate bikeway capacity. First, we reviewed previous studies on the vehicle-road capacity analysis and proposed their applicability to bikeways. Second, two assumptions were made based on the traffic flow characteristics of bikeways: (1) the capacitated state in bikeways occur within a bicycle platoon, and (2) a bicycle platoon consists of more than three bicycles running in close proximity. In addition, it is assumed that the mean time headway of a bicycle platoon represents the characteristics of the platoon. The normality of the mean-time headway of a bicycle platoon calculated using the central limit theorem leads to the development of a method that estimates the riverside bikeway capacity using data collected from two different riverside bike-exclusive roads (Han-river and Anyangcheon). We used a location-fixed video camera to record videos of running bicycles and wrote a special-purpose software program to code the time-headway data from the videos. RESULTS : Time headways from 189 bicycle platoons were analyzed. The estimated mean-time headway of the capacitated bicycle flow is 1.01 s, from which the capacity of the bikeway is found to be 3578 vehicles/h. CONCLUSIONS : The proposed method that estimates bikeway capacity could be applicable to the analysis of short-range congested area rather than planning the number of lanes. In other words, it determines the sections that are temporarily highly congested and proposes appropriate strategies to mitigate the congestion.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.8
• /
• pp.1760-1768
• /
• 2004

A P2P is a method that can share and exchange on digital resources through a direct connection on personnel without a central server. In this paper, we apply a P2P technology to a traditional electronic commerce method so that a seller and a customer can perform a commercial transaction through a direct communication. As such a result, we propose a new e-Commerce model on P2P environment to assure fairness in commercial transactions. To achieve our goal, we put an escrow server which is responsible for guarantee fair contents delivery and payment for the contents between a seller and a customer. When a customer buys content, he first obtains reputation values implicating reliability for the content and refers to these values to determine purchase. The proposed scheme, we can improve the reliability for the purchasing content and provide the fairness to both a seller and a customer simultaneously.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.03a
• /
• pp.401-408
• /
• 2005

Recently shield TBM tunnellings are being applied to subway construction in Korean cities. Generally these kinds of tunnellings have the problems in the stability of ground such as subsidence because urban subway is constructed in the shallow depth. A sinkhole occurred on the road just above the tunnel during tunneling in Kwangju, so a survey for upper layer of the tunnel was needed. But conventional Ground Probing Radar can't be applicable due to the presence of steel-mesh screen in the shield segment, so no existent geophysical method is applicable in this site. Because the outer surface of each shield segment is electrically insulated, dipole-dipole resistivity method which is popular in engineering site investigation, was tried to this survey for the first time. Specially manufactured flexible ring-type electrodes were installed into the grouting holes at an interval of 2.4 m on the ceiling. The K-Ohm II system which has been developed by KIGAM and tested successfully in many sites, was used in this site. The system consists of 1000Volt-1Ampere constant-current transmitter, optically isolated 24 bit sigma-delta A/D conversion receiver - maximum 12 channel simultaneous measurements, and graphical automatic acquisition software for easy data quality check in real time. Borehole camera logging with circular white LED lighting was also done to investigate the state of the layer. Measured resistivity data lack of some stations due to failing opening lids of holes, shows general high-low trend well. The dipole-dipole resistivity inversion results discriminate (1) one approximately 4 meter diameter cavity (grouted but incompletely hardened, so low resistivity - less than $30{\Omega}m$), (2) weak zone (100-200${\Omega}m$), and (3) hard zone (high resistivity - more than 1000${\Omega}m$) very well for the distance of 320 meters. The 2-D inversion neglects slight absolute 3-D effect, but we can get satisfactory and useful information. Acquired resistivity section and video tapes by borehole camera logging will be reserved and reused if some problem occurs in this site in the future.