• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.654-662
• /
• 2010

In this paper, we suggest an advanced algorithm, to recognize pedestrian/non-pedestrian using second-stage cascade method, which applies Adaboost algorithm to make a strong classification from weak classifications. First, we extract two feature vectors: (i) Histogram of Oriented Gradient (HOG) which includes gradient information and differential magnitude; (ii) Curvature-HOG which is based on four different curvature features per pixel. And then, a strong classification needs to be obtained from weak classifications for composite recognition method using both HOG and curvature-HOG. In the proposed method, we use one feature vector and one strong classification for the first stage of recognition. For the recognition-failed image, the other feature and strong classification will be used for the second stage of recognition. Based on our experiment, the proposed algorithm shows higher recognition rate compared to the traditional method.

• Information and Communications Magazine
• /
• v.34 no.4
• /
• pp.17-24
• /
• 2017

본고에서는 저가형 관성 센서를 이용하여 실내 항법을 수행하는 여러 방법들에 대해 알아본다. 저가형 관성 센서를 이용한 추측 항법은 휴대성이 뛰어나고 외부의 인프라 없이 구현이 가능하고 가격이 저렴하다는 장점이 있지만, 오차가 빠르게 누적된다는 단점이 있다. 이를 해결하기 위해 사용자의 보행 특성을 이용한 보행자 추측 항법이 제안되었다. 본고에서는 보행자 추측 항법의 두 분류 기법인 걸음-이동방향 결합 기법과 관성 항법-영속도 보정 결합 기법의 원리와 각 기법들의 기술 동향에 대해 다루고자 한다.

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.421-429
• /
• 2015

This paper is about an approach for pedestrian detection and tracking with infrared imagery. We used the CUDA(Computer Unified Device Architecture) that is a parallel processing language in order to improve the speed of video-based pedestrian detection and tracking. The detection phase is performed by Adaboost algorithm based on Haar-like features. Adaboost classifier is trained with datasets generated from infrared images. After detecting the pedestrian with the Adaboost classifier, we proposed a particle filter tracking strategies on HSV histogram feature that exploit adaptively at the same time. The proposed approach is implemented on an NVIDIA Jetson TK1 developer board that is full-featured device ideal for software development within the Linux environment. In this paper, we presented the results of parallel processing with the NVIDIA GPU on the CUDA development environment for detection and tracking of pedestrians. We compared the object detection and tracking processing time for night-time images on both GPU and CPU. The result showed that the detection and tracking speed of the pedestrian with GPU is approximately 6 times faster than that for CPU.

• Journal of Korean Society of Transportation
• /
• v.21 no.5
• /
• pp.41-48
• /
• 2003

Korea Claim Adjustor Association(KCAA) defines the near pedestrian crossing accidents as those accidents that occurred in the area within 25m from pedestrian crossing on the arterial road and within 15m from pedestrian crossing on other classes of road. Accidents between pedestrian crossing and stop line are classified as the accident near pedestrian crossing. Reviewing of current statute and court precedent, three kinds of traffic accidents which are accidents occurred in the pedestrian crossing. near pedestrian crossing and the area between pedestrian crossing and stop line. should be distinguished by different pedestrian contributory negligence. To find out how different they are. we surveyed transportation society members about the contributory negligence of traffic accidents between pedestrian crossing and stop line and the results are as follows : (1) The current two classification of pedestrian crossing accidents and near pedestrian crossing accidents should be changed to three classification of pedestrian crossing accidents that includes accidents on pedestrian crossing, near pedestrian crossing and between pedestrian crossing and the stop line. (2) For the pedestrian's contributory negligence, the least reasonability to pedestrian is accident on the pedestrian crossing. The next one is the accident between pedestrian crossing and stop line and the last is the accident near pedestrian crossing. (3) Pedestrian contributory negligence for accident by space is recommended as 〈table 8〉, 〈table 9〉, 〈table 10〉. (4) Contributory negligence rate of the accident on the pedestrian crossing during red light should be modified to be less than that of near pedestrian crossing.

• Journal of Korean Society of Transportation
• /
• v.31 no.6
• /
• pp.53-66
• /
• 2013

The major purpose of this study is to evaluate methodologies to predict the injury severity of pedestrian-vehicle collisions. Methodologies to be evaluated and compared in this study include Binary Logistic Regression(BLR), Ordered Probit Model(OPM), Support Vector Machine(SVM) and Decision Tree(DT) method. Valuable insights into applying methodologies to analyze the characteristics of pedestrian injury severity are derived. For the purpose of identifying causal factors affecting the injury severity, statistical approaches such as BLR and OPM are recommended. On the other hand, to achieve better prediction performance, heuristic approaches such as SVM and DT are recommended. It is expected that the outcome of this study would be useful in developing various countermeasures for enhancing pedestrian safety.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.4
• /
• pp.250-257
• /
• 2011

In this paper, we proposed the method detecting multiple pedestrians using motion information and SVM(Support Vector Machine) from a moving camera image. First, we detect moving pedestrians from both the difference image and the projection histogram which is compensated for the camera ego-motion using corresponding feature sets. The difference image is simple method but it is not detected motionless pedestrians. Thus, to fix up this problem, we detect motionless pedestrians using SVM The SVM works well particularly in binary classification problem such as pedestrian detection. However, it is not detected in case that the pedestrians are adjacent or they move arms and legs excessively in the image. Therefore, in this paper, we proposed the method detecting motionless and adjacent pedestrians as well as people who take excessive action in the image using motion information and SVM The experimental results on our various test video sequences demonstrated the high efficiency of our approach as it had shown an average detection ratio of 94% and False Positive of 2.8%.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.150-157
• /
• 2015

Pedestrian detection has largely been researched as one of the important technologies for autonomous driving vehicle and preventing accidents. There are two categories for pedestrian detection, camera-based and LIDAR-based. LIDAR-based methods have the advantage of the wide angle of view and insensitivity of illuminance change while camera-based methods have not. However, there are several problems with 3D LIDAR, such as insufficient resolution to detect distant pedestrians and decrease in detection rate in a complex situation due to segmentation error and occlusion. In this paper, two methods using GM-PHD filter are proposed to improve the poor rates of pedestrian detection algorithms based on 3D LIDAR. First one improves detection performance and resolution of object by automatic accumulation of points in previous frames onto current objects. Second one additionally enhances the detection results by applying the GM-PHD filter which is modified in order to handle the poor situation to classified multi target. A quantitative evaluation with autonomously acquired road environment data shows the proposed methods highly increase the performance of existing pedestrian detection algorithms.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.162-170
• /
• 2013

In recent years, the interests and needs of the Pedestrian Protection System (PPS), which is mounted on the vehicle for the purpose of traffic safety improvement is increasing. In this paper, we propose a pedestrian candidate window extraction and unit cell histogram based HOG descriptor calculation methods. At pedestrian detection candidate windows extraction stage, the bright ratio of pedestrian and its circumference region, vertical edge projection, edge factor, and PCA reconstruction image are used. Dalal's HOG requires pixel based histogram calculation by Gaussian weights and trilinear interpolation on overlapping blocks, But our method performs Gaussian down-weight and computes histogram on a per-cell basis, and then the histogram is combined with the adjacent cell, so our method can be calculated faster than Dalal's method. Our PCA reconstruction error based pedestrian detection candidate window extraction method efficiently classifies background based on the difference between pedestrian's head and shoulder area. The proposed method improves detection speed compared to the conventional HOG just using image without any prior information from camera calibration or depth map obtained from stereo cameras.

• Journal of Biomedical Engineering Research
• /
• v.38 no.3
• /
• pp.129-136
• /
• 2017

The exoskeleton robot is a technology developed to be used in various fields such as military, industry and medical treatment. The exoskeleton robot works by sensing the movement of the wearer. By recognizing the wearer's daily activities, the exoskeleton robot can assist the wearer quickly and efficiently utilize the system. In this study, LDA, QDA, and kNN are used to classify gait types through kinetic data obtained from subjects. Walking was selected from general walking and stair walking which are mainly performed in daily life. Seven IMUs sensors were attached to the subject at the predetermined positions to measure kinematic factors. As a result, LDA was classified as 78.42%, QDA as 86.16%, and kNN as 87.10% ~ 94.49% according to the value of k.

• Smart Media Journal
• /
• v.4 no.2
• /
• pp.26-33
• /
• 2015

In this paper, we propose an efficient automatic pedestrian removal system from a frame in a video sequence. It firstly finds pedestrians from the frame using a Histogram of Oriented Gradient(HOG) / Linear-Support Vector Machine(L-SVM) classifier, searches for proper background patches, and then the patches are used to replace the deleted pedestrians. Background patches are retrieved from the reference video sequence and a modified feather blender algorithm is applied to make boundaries of replaced blocks look naturally. The proposed system, is designed to automatically detect object and generate natural-looking patches, while most existing systems provide search operation in manual. In the experiment, the average PSNR of the replaced blocks is 19.246