• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.2
• /
• pp.121-128
• /
• 2013

There have been various research efforts for pedestrian recognition in embedded imaging systems. However, many suffer from their heavy computational complexities. SVM classification method has been widely used for pedestrian recognition. The reduction of candidate region is crucial for low-complexity scheme. In this paper, We propose a real time HOG based pedestrian detection system on GPU which images are captured by a pair of cameras. To speed up humans on road detection, the proposed method reduces a number of detection windows with disparity-search and near-search algorithm and uses the GPU and the NVIDIA CUDA framework. This method can be achieved speedups of 20% or more compared to the recent GPU implementations. The effectiveness of our algorithm is demonstrated in terms of the processing time and the detection performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.7
• /
• pp.793-800
• /
• 2015

We presented a method to perform simultaneously both head-eye calibration and wheel calibration for a mobile robot that has a stereo camera mounted on the pan-tilt mechanism. Such a mobile robot system prevails recently. However, conventional methods are not applicable to this system because they assumed that camera systems were mounted on fixed structures. Building on conventional methods, we devised an iterative linear solution to solve the problem, and achieved satisfactory results in terms of accuracy in addition to efficiency due to simultaneous calibration. Furthermore, the calibration accuracy was improved by nonlinear optimization.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.9
• /
• pp.818-826
• /
• 2015

This paper presents a novel methodology for estimating vehicle ego-motion, i.e. tri-axis linear velocities and angular velocities by using stereo vision sensor and 2G1Y sensor (longitudinal acceleration, lateral acceleration, and yaw rate). The estimated ego-motion information can be utilized to predict future ego-path and improve the accuracy of 3D coordinate of obstacle by compensating for disturbance from vehicle movement representatively for collision avoidance system. For the purpose of incorporating vehicle dynamic characteristics into ego-motion estimation, the state evolution model of Kalman filter has been augmented with lateral vehicle dynamics and the vanishing point estimation has been also taken into account because the optical flow radiates from a vanishing point which might be varied due to vehicle pitch motion. Experimental results based on real-world data have shown the effectiveness of the proposed methodology in view of accuracy.

• The Journal of Korea Robotics Society
• /
• v.11 no.3
• /
• pp.172-182
• /
• 2016

Lane-level vehicle positioning is an important task for enhancing the accuracy of in-vehicle navigation systems and the safety of autonomous vehicles. GPS (Global Positioning System) and DGPS (Differential GPS) are generally used in navigation service systems, which however only provide an accuracy level up to 2~3 m. In this paper, we propose a 3D vision based lane-level positioning technique which can provides accurate vehicle position. The proposed method determines the current driving lane of a vehicle by tracking the 3D position of traffic signs which stand at the side of the road. Using a stereo camera, the 3D tracking paths of traffic signs are computed and their projections to the 2D road plane are used to determine the distance from the vehicle to the signs. Several experiments are performed to analyze the feasibility of the proposed method in many real roads. According to the experimental results, the proposed method can achieve 90.9% accuracy in lane-level positioning.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.6
• /
• pp.1130-1132
• /
• 2007

In this research, 3D position exploring system was developed to detect direction and position of radiation source by using two general CCD camera. This system consists of a radiation detection device, a controlling device, and a monitoring device. A radiation detection device is composed of a collimator, a scintillator, CCD sensor, and radiation shielding part. Incident radiation is firstly collimated with direction and converted into visual lights in a scintillator. The CCD sensor detect the converted visual light and send a signal as an image. This can explore a radiation source with direction and distance from geometrical structure of two sensors. From these information, the developed 3D position exploring system can provide 3D radiation source information. This research will be useful for managing and processing radioactive materials in remote.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.764-781
• /
• 2013

In this paper, we propose a highly precise vehicle detection method with low false alarm using billboard sweep stereo matching and multi-stage hypothesis generation. First, we capture stereo images from cameras established in front of the vehicle and obtain the disparity map in which the regions of ground plane or background are removed using billboard sweep stereo matching algorithm. And then, we perform the vehicle detection and tracking on the labeled disparity map. The vehicle detection and tracking consists of three steps. In the learning step, the SVM(support vector machine) classifier is obtained using the features extracted from the gabor filter. The second step is the vehicle detection which performs the sobel edge detection in the image of the left camera and extracts candidates of the vehicle using edge image and billboard sweep stereo disparity map. The final step is the vehicle tracking using template matching in the next frame. Removal process of the tracking regions improves the system performance in the candidate region of the vehicle on the succeeding frames.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.279-286
• /
• 2021

Recently, We are carrying out a policy of physical distancing of at least 1m from each other to prevent the spreading of COVID-19 disease in public places. In this paper, we propose a method for measuring distances between people in real time and an automation system that recognizes objects that are within 1 meter of each other from stereo images acquired by drones or CCTVs according to the estimated distance. A problem with existing methods used to estimate distances between multiple objects is that they do not obtain three-dimensional information of objects using only one CCTV. his is because three-dimensional information is necessary to measure distances between people when they are right next to each other or overlap in two dimensional image. Furthermore, they use only the Bounding Box information to obtain the exact coordinates of human existence. Therefore, in this paper, to obtain the exact two-dimensional coordinate value in which a person exists, we extract a person's key point to detect the location, convert it to a three-dimensional coordinate value using Stereo Vision and Camera Calibration, and estimate the Euclidean distance between people. As a result of performing an experiment for estimating the accuracy of 3D coordinates and the distance between objects (persons), the average error within 0.098m was shown in the estimation of the distance between multiple people within 1m.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.10-16
• /
• 2012

For high speed visual inspection in semiconductor industries, it is essential to acquire two-dimensional images on regions of interests with a large field of view (FOV) and a high resolution simultaneously. In this paper, an imaging system is newly proposed to achieve high quality image in terms of precision and FOV, which is composed of single lens, a beam splitter, two camera sensors, and stereo image grabbing board. For simultaneously acquired object images from two camera sensors, Zhang's camera calibration method is applied to calibrate each camera first of all. Secondly, to find a mathematical mapping function between two images acquired from different view cameras, the matching matrix from multiview camera geometry is calculated based on their image homography. Through the image homography, two images are finally registered to secure a large inspection FOV. Here the inspection system of using multiple images from multiple cameras need very fast processing unit for real-time image matching. For this purpose, parallel processing hardware and software are utilized, such as Compute Unified Device Architecture (CUDA). As a result, we can obtain a matched image from two separated images in real-time. Finally, the acquired homography is evaluated in term of accuracy through a series of experiments, and the obtained results shows the effectiveness of the proposed system and method.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1575-1591
• /
• 2008

In this paper, we propose a new method detecting foot motion capture in order to overlap in realtime foot's 3D virtual model from stereo cameras. In order to overlap foot's virtual model at the same position of the foot, a process of the foot's joint detection to regularly track the foot's joint motion is necessary, and accurate register both foot's virtual model and user's foot in complicated motion is most important problem in this technology. In this paper, we propose a dynamic registration using two types of marker groups. A plane information of the ground handles the relationship between foot's virtual model and user's foot and obtains foot's pose and location. Foot's rotation is predicted by two attached marker groups according to instep of center framework. Consequently, we had implemented our proposed system and estimated the accuracy of the proposed method using various experiments.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2000.04a
• /
• pp.129-133
• /
• 2000

It is reasonable to use the stereo vision and image processing technique to digitize 3D coordinates of grid points and to evaluate surface strains on a sheet metal parts. However this method has its intrinsic problems such as the difficulty in enhancement of bad images inevitable error due to digital image resolution of camera and frame grabber unreliability of strains and thickness evaluated from coarse grid on the corner area with large curvature and the limitation of the area that can be measured at a time. Therefore it is still hard to measure strain distribution over the entire surface of a medium,- or large-sized stamped part at a time even by using an automated strain measurement system. In this study the curvature correction algorithm based on the grid refinement and the geometry assembling algorithm based on the global error minimization (GEM) scheme are suggested. Several applications are presented to show the reliability and efficiency of these algorithms.