• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.31-37
• /
• 2018

Recently, the safety in vehicle also has become a hot topic as self-driving car is developed. In passive safety systems such as airbags and seat belts, the system is being changed into an active system that actively grasps the status and behavior of the passengers including the driver to mitigate the risk. Furthermore, it is expected that it will be possible to provide customized services such as seat deformation, air conditioning operation and D.W.D (Distraction While Driving) warning suitable for the passenger by using occupant information. In this paper, we propose robust vehicle occupant detection algorithm based on RGB-Depth-Thermal camera for obtaining the passengers information. The RGB-Depth-Thermal camera sensor system was configured to be robust against various environment. Also, one of the deep learning algorithms, OpenPose, was used for occupant detection. This algorithm is advantageous not only for RGB image but also for thermal image even using existing learned model. The algorithm will be supplemented to acquire high level information such as passenger attitude detection and face recognition mentioned in the introduction and provide customized active convenience service.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.776-788
• /
• 2020

In this paper, a vehicle type recognition system using deep learning and a license plate recognition system are proposed. In the existing system, the number plate area extraction through image processing and the character recognition method using DNN were used. These systems have the problem of declining recognition rates as the environment changes. Therefore, the proposed system used the one-stage object detection method YOLO v3, focusing on real-time detection and decreasing accuracy due to environmental changes, enabling real-time vehicle type and license plate character recognition with one RGB camera. Training data consists of actual data for vehicle type recognition and license plate area detection, and synthetic data for license plate character recognition. The accuracy of each module was 96.39% for detection of car model, 99.94% for detection of license plates, and 79.06% for recognition of license plates. In addition, accuracy was measured using YOLO v3 tiny, a lightweight network of YOLO v3.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.6
• /
• pp.9-16
• /
• 2017

An Algorithm for Lane Detection and Lane Departure Warning for a Vehicle Driving on Roads is proposed in This Paper. Using Images Obtained from On-board Cameras for Lane Detection has Some Difficulties, e.g. the Increase of Fault Detection Ratio Due to Symbols on Roads, Missing Yellow Lanes in the Tunnel due to a Similar Color Lighting, Missing Some Lanes in Rainy Days Due to Low Intensity of Illumination, and so on. The Proposed Algorithm has been developed Focusing on Solving These Problems. It also has an Additional Function to Determine How much the Vehicle is leaning to any Side between The Lanes and, If Necessary, to Give a Warning to a Driver. Experiments Using an Image Database Built by Collecting with Vehicle On-board Blackbox in Six Different Situations have been conducted for Validation of the Proposed Algorithm. The Experimental Results show a High Performance of the Proposed Algorithm with Overall 97% Detection Success Ratio.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.1
• /
• pp.30-44
• /
• 2022

The advent of deep learning-based algorithms has facilitated researches on target detection from synthetic aperture radar(SAR) imagery. While most of them concentrate on detection tasks for ships with open SAR ship datasets and for aircraft from SAR scenes of airports, there is relatively scarce researches on the detection of SAR ground vehicle targets where several adverse factors such as high false alarm rates, low signal-to-clutter ratios, and multiple targets in close proximity are predicted to degrade the performances. In this paper, a dataset of ground vehicle targets acquired from TerraSAR-X(TSX) satellite SAR images is presented. Then, both detection and instance segmentation are simultaneously carried out on this dataset based on the deep learning-based Mask R-CNN. Finally, this paper shows the future research directions to further improve the performances of detecting the SAR ground vehicle targets.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.4
• /
• pp.36-43
• /
• 2011

The forward collision of vehicles in high speed can cause a chain collisions and high fatality rate. Most of the forward collisions are caused by insufficient braking distance due to detection time of driver and safe distance. Also, accumulated detection time of driver is cause of chain collisions after the forward collision. The FVCWS prevents the forward collision by maintaining the safety distance inter-vehicle and reducing detection time of driver. However the FVCWS can cause chain collisions because the system that interacts only forward vehicle has accumulated detection time of driver. In this paper, we analyze forward and chain collisions of normal vehicles and FVCWS vehicles on static traveling scenario. And then, we analyze and compare V2V based FVCWS with them after explaining the system. The V2V FVCWS reduces detection time of driver alike FVCWS as well as remove accumulated detection time of driver by broadcasting emergence message to backward vehicles at the same time. Therefore, the system decrease possibility of forward and chain collisions. All backward normal vehicles and 3~4 backward FVCWS vehicles have possibility of forward and chain collisions in result of analysis. However V2V FVCWS vehicles almost do not chain collisions in the result.

• The KIPS Transactions:PartB
• /
• v.18B no.5
• /
• pp.255-264
• /
• 2011

In this paper, we propose a forward vehicle detection algorithm using column detection and bird's-eye view mapping based on stereo vision. The algorithm can detect forward vehicles robustly in real complex traffic situations. The algorithm consists of the three steps, namely road feature-based column detection, bird's-eye view mapping-based obstacle segmentation, obstacle area remerging and vehicle verification. First, we extract a road feature using maximum frequent values in v-disparity map. And we perform a column detection using the road feature as a new criterion. The road feature is more appropriate criterion than the median value because it is not affected by a road traffic situation, for example the changing of obstacle size or the number of obstacles. But there are still multiple obstacles in the obstacle areas. Thus, we perform a bird's-eye view mapping-based obstacle segmentation to divide obstacle accurately. We can segment obstacle easily because a bird's-eye view mapping can represent the position of obstacle on planar plane using depth map and camera information. Additionally, we perform obstacle area remerging processing because a segmented obstacle area may be same obstacle. Finally, we verify the obstacles whether those are vehicles or not using a depth map and gray image. We conduct experiments to prove the vehicle detection performance by applying our algorithm to real complex traffic situations.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.4
• /
• pp.244-250
• /
• 2008

This paper describes the design and implementation of an unmanned ground vehicle (UGV) and also estimates how well autonomous navigation and remote control of UGV can be performed through the optimized arbitration of several sensor data, which are acquired from vision, obstacle detection, positioning system, etc. For the autonomous navigation, lane detection and tracing, global positioning, and obstacle avoidance are necessarily required. In addition, for the remote control, two types of experimental environments are established. One is to use a commercial racing wheel module, and the other is to use a haptic device that is useful for a user application based on virtual reality. Experimental results show that autonomous navigation and remote control of the designed UGV can be achieved with more effectiveness and accuracy using the proper arbitration of sensor data and navigation plan.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.9
• /
• pp.723-732
• /
• 2016

This paper proposes an approach to fused navigation of an unmanned surface vehicle(USV) and to detection of the outlier or interference of global positioning system(GPS). The method fuses available sensor measurements through extended Kalman filter(EKF) to find the location and attitude of the USV. The method uses error covariance of EKF for detection of GPS outlier or interference. When outlier or interference of the GPS is detected, the method excludes GPS data from navigation process. The measurements to be fused for the navigation are GPS, acceleration, angular rate, magnetic field, linear velocity, range and bearing to acoustic beacons. The method is tested through simulated data and measurement data produced through ground navigation. The results show that the method detects GPS outlier or interference as well as the GPS recovery, which frees navigation from the problem of GPS abnormality.

• 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.

• Journal of information and communication convergence engineering
• /
• v.18 no.3
• /
• pp.147-154
• /
• 2020

In this study, we created a system that can determine the number of vehicles entering and departing a charging station in real time for solving waiting time problems during refueling. Accordingly, we use the You Only Look Once object detection algorithm to detect and count the number of vehicles in the charging station and send the data to the Firebase Realtime Database. The result is shown using an Android application that provides a map function with the Kakao Maps API at the user interface side. Our system has an accuracy of 91% and an average response time of 3.1 s. Therefore, this system can be used by drivers to determine the availability of a charging station and to identify the charging station with the least waiting time for charging their vehicle.