• Smart Media Journal
• /
• v.9 no.4
• /
• pp.9-16
• /
• 2020

Recently, various studies are being conducted to integrate Image Segmentation into smart factory industries and autonomous driving fields. In particular, Image Segmentation systems using deep learning algorithms have been researched and developed enough to learn from large volumes of data with higher accuracy. In order to use image segmentation in the autonomous driving sector, sufficient amount of learning is needed with large amounts of data and the streaming environment that processes drivers' data in real time is important for the accuracy of safe operation through highways and child protection zones. Therefore, we proposed a novel DFCN algorithm that enhanced existing FCN algorithms that could be applied to various road environments, demonstrated that the performance of the DFCN algorithm improved 1.3% in terms of "loss" value compared to the previous FCN algorithms. Moreover, the proposed DFCN algorithm was applied to the existing U-Net algorithm to maintain the information of frequencies in the image to produce better results, resulting in a better performance than the classical FCN algorithm in the autonomous environment.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.2
• /
• pp.132-151
• /
• 2022

Vehicle localization is one of the core technologies for autonomous driving. Image-based localization provides location information efficiently, and various related studies have been conducted. However, the image-based localization methods using feature points or lane information has a limitation that positioning accuracy may be greatly affected by road and driving environments. In this study, we propose a line segment matching framework for accurate vehicle localization. The proposed framework consists of four steps: line segment extraction, merging, overlap area detection, and MSLD-based segment matching. The proposed framework stably performed line segment matching at a sufficient level for vehicle positioning regardless of vehicle speed, driving method, and surrounding environment.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.81-93
• /
• 2022

Recently, there have been many studies on object recognition around the vehicle and recognition of traffic signs and traffic lights in autonomous driving. In particular, such the recognition of traffic lights is one of the core technologies in autonomous driving. Therefore, many studies for such the recognition of traffic lights have been performed, the studies based on various deep learning models have increased significantly in recent. In addition, as a high-quality AI training data set for voice, vision, and autonomous driving is released on AIHub, it makes it possible to develop a recognition model for traffic lights suitable for the domestic environment using the data set. In this study, we developed a recognition model for traffic lights that can be used in Korea using the AIHub's training data set. In particular, in order to improve the recognition performance, we used various models of YOLOv4 and YOLOv5, and performed our recognition experiments by defining various classes for the training data. In conclusion, we could see that YOLOv5 shows better performance in the recognition than YOLOv4 and could confirm the reason from the architecture comparison of the two models.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.39-44
• /
• 2022

This paper presents LiDAR static obstacle map based vehicle position correction algorithm for urban autonomous driving. Real Time Kinematic (RTK) GPS is commonly used in highway automated vehicle systems. For urban automated vehicle systems, RTK GPS have some trouble in shaded area. Therefore, this paper represents a method to estimate the position of the host vehicle using AVM camera, front camera, LiDAR and low-cost GPS based on Extended Kalman Filter (EKF). Static obstacle map (STOM) is constructed only with static object based on Bayesian rule. To run the algorithm, HD map and Static obstacle reference map (STORM) must be prepared in advance. STORM is constructed by accumulating and voxelizing the static obstacle map (STOM). The algorithm consists of three main process. The first process is to acquire sensor data from low-cost GPS, AVM camera, front camera, and LiDAR. Second, low-cost GPS data is used to define initial point. Third, AVM camera, front camera, LiDAR point cloud matching to HD map and STORM is conducted using Normal Distribution Transformation (NDT) method. Third, position of the host vehicle position is corrected based on the Extended Kalman Filter (EKF).The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment and showed better performance than only lane-detection algorithm. It is expected to be more robust and accurate than raw lidar point cloud matching algorithm in autonomous driving.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1307-1312
• /
• 2023

In this paper, we propose a hybrid camera system that combines cameras with different focal lengths and LiDAR (Light Detection and Ranging) sensors to address the core components of autonomous driving perception technology, which include object recognition and distance measurement. We extract objects within the scene and generate precise location and distance information for these objects using the proposed hybrid camera system. Initially, we employ the YOLO7 algorithm, widely utilized in the field of autonomous driving due to its advantages of fast computation, high accuracy, and real-time processing, for object recognition within the scene. Subsequently, we use multi-focal cameras to create depth maps to generate object positions and distance information. To enhance distance accuracy, we integrate the 3D distance information obtained from LiDAR sensors with the generated depth maps. In this paper, we introduce not only an autonomous vehicle platform capable of more accurately perceiving its surroundings during operation based on the proposed hybrid camera system, but also provide precise 3D spatial location and distance information. We anticipate that this will improve the safety and efficiency of autonomous vehicles.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.65-74
• /
• 2024

In recent years, image processing technology has played a critical role in the field of autonomous driving. Among them, image recognition technology is essential for the safety and performance of autonomous vehicles. Therefore, this paper aims to develop a hybrid image recognition system to enhance the safety and performance of autonomous vehicles. In this paper, various image recognition technologies are utilized to construct a system that recognizes and tracks objects in the vehicle's surroundings. Machine learning and deep learning algorithms are employed for this purpose, and objects are identified and classified in real-time through image processing and analysis. Furthermore, this study aims to fuse image processing technology with vehicle control systems to improve the safety and performance of autonomous vehicles. To achieve this, the identified object's information is transmitted to the vehicle control system to enable appropriate autonomous driving responses. The developed hybrid image recognition system in this paper is expected to significantly improve the safety and performance of autonomous vehicles. This is expected to accelerate the commercialization of autonomous vehicles.

• Journal of Mechanical Science and Technology
• /
• v.15 no.4
• /
• pp.448-458
• /
• 2001

The primary goal of virtual prototyping is to eliminate the need for fabricating physical prototypes, and to reduce cost and time for developing new products. A virtual prototyping seeks to create a virtual environment where the development of a new model can be flexible as well as rapid, and experiments can be carried out effectively concerning kinematics, dynamics, and control aspects of the model. This paper addresses the virtual environment used for virtual prototyping of a passenger vehicle. It has been developed using the dVISE environment that provides such useful features as actions, events, sounds, and light features. A vehicle model including features, and behaviors is constructed by employing an object-oriented paradigm and contains detailed information about a real-size vehicle. The human model is also implemented not only for visual and reach evaluations of the developed vehicle model, but also for behavioral visualization during a crash test. For the real time driving simulation, a neural network model is incorporated into the virtual environment. The cases of passing bumps with a vehicle are discussed in order to demonstrate the applicability of a set of developed models.

• The Journal of Korea Robotics Society
• /
• v.3 no.3
• /
• pp.186-193
• /
• 2008

We propose a novel real-time obstacle avoidance method for rescue robots. This method, named the ELA(Emergency Level Around), permits the detection of unknown obstacles and avoids collisions while simultaneously steering the mobile robot toward safe position. In the ELA, we consider two sensor modules, PSD(Position Sensitive Detector) infrared sensors taking charge of obstacle detection in short distance and LMS(Laser Measurement System) in long distance respectively. Hence if a robot recognizes an obstacle ahead by PSD infrared sensors first, and judges impossibility to overcome the obstacle based on driving mode decision process, the order of priority is transferred to LMS which collects data of radial distance centered on the robot to avoid the confronted obstacle. After gathering radial information, the ELA algorithm estimates emergency level around a robot and generates a polar histogram based on the emergency level to judge where the optimal free space is. Finally, steering angle is determined to guarantee rotation to randomly direction as well as robot width for safe avoidance. Simulation results from wandering in closed local area which includes various obstacles and different conditions demonstrate the power of the ELA.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1624-1627
• /
• 1997

The 6-DOF parallel manipulator is a closed-kindmatic chain robot manipulator that is capable of providing high structural rigidity and positional accuracy. Because of its advantage, the parallel manipulator have been widely used in many engineering applications such as vehicle/flight driving simulators, rogot maniplators, attachment tool of machining centers, etc. However, the kinematic analysis for the implementation of a real-time controller has some problem because of the lack of an efficient lagorithm for solving its highly nonliner forward kinematic equation, which provides the translational and orientational attitudes of the moveable upper platform from the lenght of manipulator linkages. Generally, Newton-Raphson method has been widely sued to solve the forward kinematic problem but the effectiveness of this methodology depend on how to set initial values. This paper proposes a hybrid method using genetic algorithm(GA) and Newton-Raphson method to solve forward kinematics. That is, the initial values of forward kinematics solution are determined by adopting genetic algorithm which can search grobally optimal solutions. Since determining this values, the determined values are used in Newton-Raphson method for real time calcuation.

• Proceedings of the KIEE Conference
• /
• 2003.10b
• /
• pp.42-44
• /
• 2003

As the industry is developed, uses of various electric motor are increasing from general home to various fields of industry, and the kind becomes various daily. For these reasons, it is required to study the remote control and a package management about change of a speed drive system, the supervision of administration appliance by real time, and the collection and process data together using internet prevailed on industry whole. This paper deals with the development of a Web-Based remote control system for permanent magnet synchronous motor drives. The client/server system using TCP/IP protocols and DSP controller for remote control through internet and the Web interface that users can confirm data and state of PMSM(Permanent Magnet Synchronous Motor) is developed. This system is available for driving, braking, variable speed control and monitoring for PMSM in real time through administration program of Web-Based.