• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.7-13
• /
• 2021

This paper presents an vulnerable road user (VRU) classification and tracking algorithm using vision and LiDAR sensor fusion method for urban autonomous driving. The classification and tracking for vulnerable road users such as pedestrian, bicycle, and motorcycle are essential for autonomous driving in complex urban environments. In this paper, a real-time object image detection algorithm called Yolo and object tracking algorithm from LiDAR point cloud are fused in the high level. The proposed algorithm consists of four parts. First, the object bounding boxes on the pixel coordinate, which is obtained from YOLO, are transformed into the local coordinate of subject vehicle using the homography matrix. Second, a LiDAR point cloud is clustered based on Euclidean distance and the clusters are associated using GNN. In addition, the states of clusters including position, heading angle, velocity and acceleration information are estimated using geometric model free approach (GMFA) in real-time. Finally, the each LiDAR track is matched with a vision track using angle information of transformed vision track and assigned a classification id. The proposed fusion algorithm is evaluated via real vehicle test in the urban environment.

• Journal of Korea Multimedia Society
• /
• v.18 no.11
• /
• pp.1302-1312
• /
• 2015

Recent research has been devoted and focused on detecting pedestrian and vehicle in intelligent vehicles except for the vulnerable road user(VRUS). In this paper suggest a new projection method which has robustness for rotation invariant and reducing dimensionality for each cell from original image to detect two-wheeler. We applied new weighting values which are calculated by maximum curvature containing very important object shape features and uniform local binary pattern to remove the noise. This paper considered the Adaboost algorithm to make a strong classification from weak classification. Experiment results show that the new approach gives higher detection accuracy than of the conventional method.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.2
• /
• pp.130-135
• /
• 2016

Gait recognition has advantage of non-contact type recognition. But It has disadvantage of low recognition rate when the pedestrian silhouette is changed due to bag or coat. In this paper, we proposed new method using combination of gait energy image feature and thermal face image feature. First, we extracted a face image which has optimal focusing value using human body rate and Tenengrad algorithm. Second step, we extracted features from gait energy image and thermal face image using linear discriminant analysis. Third, calculate euclidean distance between train data and test data, and optimize weights using genetic algorithm. Finally, we compute classification using nearest neighbor classification algorithm. So the proposed method shows a better result than the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.2
• /
• pp.435-442
• /
• 2015

In this paper, we propose a tracking and recognition of pedestrian/vehicle for intelligent multi-visual surveillance system. The intelligent multi-visual surveillance system consists of several fixed cameras and one calibrated PTZ camera, which automatically tracks and recognizes the detected moving objects. The fixed wide-angle cameras are used to monitor large open areas, but the moving objects on the images are too small to view in detail. But, the PTZ camera is capable of increasing the monitoring area and enhancing the image quality by tracking and zooming in on a target. The proposed system is able to determine whether the detected moving objects are pedestrian/vehicle or not using the SVM. In order to reduce the tracking error, an improved camera calibration algorithm between the fixed cameras and the PTZ camera is proposed. Various experimental results show the effectiveness of the proposed system.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.53-59
• /
• 2021

According to the Korean Traffic Accident Analysis System (TAAS), more than 200,000 traffic accidents occur every year. Also, the statistics including auto insurance companies data show 1.3 million traffic accidents. In the case of TAAS, the types of traffic accidents are simply divided into four; frontal collision, side collision, rear collision, and rollover. However, more detailed information is needed to assess for advanced driver assist systems at intersections. For example, directional information is needed, such as whether the vehicle in the car accident way in a straight or a left turn, etc. This study intends to redefine the type of accident with the more clear driving direction and path by referring to the Negligence standards used in automobile insurance accidents. The standards largely divide five categories of car-to-car/motorcycle /pedestrian/cyclist, and highway, and the each category is classified into dozens of types by status of the traffic signal, conflict situations. In order to present more various accident types for auto insurance accidents, the standards are reclassified driving direction and path of vehicles from crash situations. In results, the car-to-car accidents are classified into 33 accident types, car-to-pedestrian accidents have 19 accident types, car-to-motorcycle accidents have 38 accident types, and car-to-cyclist accidents are derived into 26 types.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.668-674
• /
• 2022

Machine learning techniques using visual data have high usability in fields of industry and service such as scene recognition, fault detection, security and user analysis. Among these, user analysis through the videos from CCTV is one of the practical way of using vision data. Also, many studies about lightweight artificial neural network have been published to increase high usability for mobile and embedded environment so far. In this study, we propose the network combining the object detection and classification for mobile graphic processing unit. This network detects pedestrian and face, classifies age and gender from detected face. Proposed network is constructed based on MobileNet, YOLOv2 and skip connection. Both detection and classification models are trained individually and combined as 2-stage structure. Also, attention mechanism is used to improve detection and classification ability. Nvidia Jetson Nano is used to run and evaluate the proposed system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.93-99
• /
• 2017

The rate of traffic accidents that occurred in Korea last year is 10 out of every 100,000 people, ranking it 6th among the 35 OECD member countries. The accident rate of children with disabilities and elderly people is also high. The purpose of this study is to introduce traffic safety facilities which have been developed for the reduction of traffic accidents in non-urban areas in Korea through an analysis of the related literature, the accident factors using traffic accident analysis system data and traffic accident characteristics. Traffic safety integrated facilities for ICT-based pedestrian crossings are subject to cross-sectional coverage of child protection zones. The smart safety fence prevents vehicles from parking illegally and informs pedestrians that there is an access vehicle on the pedestrian crossing. The smart bump is designed to warn drivers who are not aware of the pedestrians. In order to standardize the appropriate form and size of the traffic safety facilities for pedestrian crossings, we constructed a standard model for each type, considering the road function, press classification, power, lane number, geometric form, etc. As a result, the rate of traffic accidents involving vulnerable people was reduced. In addition, it is anticipated that the maintenance costs will be reduced by the use of a solar power supply and their compatibility with the existing installed safety fences.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.11
• /
• pp.6676-6684
• /
• 2014

This paper analyzed an existing literature review of street environment, density, accessibility, and diversity in terms of not the street level, but also the urban context level. In addition, this paper examined Jane Jacobs' theory (1961) regarding the relevance between the diversity of facilities and increasing volume of pedestrians. To find the explanation ability and significance among variables, this paper employed Enter's method of Regression Analysis in the industrial classification of restaurant business and liquor business. This empirical analysis of both theories of Jacobs (1961) and MacCormac (1983) had a different signification from existing research. Jacobs (1961) suggested the relevance among various facilities for increasing the volume of pedestrians, and MacCormac (1983) explained the different impact by industrial classification. In future research, the subdividing of industrial classification is necessary for a more precise and specific analysis.

• The Journal of Korea Robotics Society
• /
• v.12 no.2
• /
• pp.217-227
• /
• 2017

Crosswalk detection is an important part of the Pedestrian Protection System in autonomous vehicles. Different methods of crosswalk detection have been introduced so far using crosswalk edge features, the distance between crosswalk blocks, laser scanning, Hough Transformation, and Fourier Transformation. However, most of these methods failed to detect crosswalks accurately, when they are damaged, faded away or partly occluded. Furthermore, these methods face difficulties when applying on real road environment where there are lot of vehicles. In this paper, we solve this problem by first using a region based binarization technique and x-axis histogram to detect the candidate crosswalk areas. Then, we apply Support Vector Machine (SVM) based classification method to decide whether the candidate areas contain a crosswalk or not. Experiment results prove that our method can detect crosswalks in different environment conditions with higher recognition rate even they are faded away or partly occluded.

• The Journal of Korea Robotics Society
• /
• v.7 no.2
• /
• pp.113-119
• /
• 2012

In this paper we propose the method that detects moving objects in autonomous navigation vehicle using LRF sensor data. Object detection and tracking methods are widely used in research area like safe-driving, safe-navigation of the autonomous vehicle. The proposed method consists of three steps: data segmentation, mobility classification and object tracking. In order to make the raw LRF sensor data to be useful, Occupancy grid is generated and the raw data is segmented according to its appearance. For classifying whether the object is moving or static, trajectory patterns are analysed. As the last step, Markov chain Monte Carlo (MCMC) method is used for tracking the object. Experimental results indicate that the proposed method can accurately detect moving objects.