• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.262-266
• /
• 2010

Recognizing a license plate of a vehicle has widely been issued. In this thesis, firstly, mean shift algorithm is used to filter and segment a color vehicle image in order to get candidate regions. These candidate regions are then analyzed and classified in order to decide whether a candidate region contains a license plate. We then present an approach to recognize a vehicle's license plate using the Fuzzy ARTMAP neural network, a relatively new architecture of the neural network family. We show that the proposed system is well to recognize the license plate and shows some compute simulations.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.142-147
• /
• 1999

This paper presents a new approach to the dynamic control technique for track vehicle system using neural network-fuzzy control method. The proposed control scheme uses a Gaussian function as a unit function in the neural network-fuzzy, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by simulation for trajectory tracking of the speed and azimuth of a track vehicle.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.1
• /
• pp.42-48
• /
• 2008

The architecture of WSN based Vehicle Speed Measurement System is presented in this paper from Telematics Sensor Network(TSN) to Management System. To verify the feasibility of the system, we implemented the vehicle speed measurement system and evaluated the accuracy of velocity measured by the system in our testbed, an old highway located near Kyungbu highway. The system performed over 95% of accuracy at 80kmph from the measurement. In addition, the battery life time of the sensor node was evaluated by simulation analysis with real measured current consumption profiles. Assuming the maximum average daily traffic in 2005, the battery life time is expected to be over 1.6 year from the simulation result.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.6
• /
• pp.584-593
• /
• 2012

This paper introduces an AVP (Automated Valet Parking) system which applies an autonomous driving concept into the current PAS (Parking Assistant System). The present commercial PAS technology is limited into vehicle. It means vehicle only senses and controls by and for itself to assist the parking. Therefore, the present PAS is restricted to simple parking events. But AVP includes wider parking events and planning because it uses infra-sensor network as well as vehicle sensor. For the realization of AVP, the commercial steering system of a compact vehicle was modified into steer-by-wire structure and various sensors like LRF (Long Range Finder) and camera were installed in a parking area. And local & global server decides where and when the vehicle can go and park in the testing area after recognized the status of environment and vehicle from those sensors. GPS solution was used to validate the AVP performance. More various parking situations, vehicles and obstacles will be considered in the next research stages based on these results. And we expect this AVP solution with more intelligent vehicles can be applied in a big parking lot like a market, an amusement park, etc.

• Journal of Korea Multimedia Society
• /
• v.19 no.12
• /
• pp.1909-1918
• /
• 2016

This paper presents a unified framework for joint Convolutional Neural Network (CNN) based vehicle detection by leveraging multi-spectral image pairs. With the observation that under challenging environments such as night vision and limited light source, vehicle detection in a single color image can be more tractable by using additional far-infrared (FIR) image, we design joint CNN architecture for both RGB and FIR image pairs. We assume that a score map from joint CNN applied to overall image can be considered as confidence of vehicle existence. To deal with various scale ratios of vehicle candidates, multi-scale images are first generated scaling an image according to possible scale ratio of vehicles. The vehicle candidates are then detected on local maximal on each score maps. The generation of overlapped candidates is prevented with non-maximal suppression on multi-scale score maps. The experimental results show that our framework have superior performance than conventional methods with a joint framework of multi-spectral image pairs reducing false positive generated by conventional vehicle detection framework using only single color image.

• Journal of Communications and Networks
• /
• v.15 no.2
• /
• pp.207-216
• /
• 2013

Vehicular ad-hoc networks (VANETs) are self-organizing, self-healing networks which provide wireless communication among vehicular and roadside devices. Applications in such networks can take advantage of the use of simultaneous connections, thereby maximizing the throughput and lowering latency. In order to take advantage of all radio interfaces of the vehicle and to provide good quality of service for vehicular applications, we developed a seamless flow mobility management architecture based on vehicular network application classes with network-based mobility management. Our goal is to minimize the time of flow connection exchange in order to comply with the minimum requirements of vehicular application classes, as well as to maximize their throughput. Network simulator (NS-3) simulations were performed to analyse the behaviour of our architecture by comparing it with other three scenarios. As a result of this work, we observed that the proposed architecture presented a low handover time, with lower packet loss and lower delay.

• Journal of Auto-vehicle Safety Association
• /
• v.16 no.1
• /
• pp.29-34
• /
• 2024

This paper presents a multi-label lane detection method for autonomous vehicles based on deep learning. The proposed algorithm can detect two types of lanes: center lane and normal lane. The algorithm uses a convolution neural network with an encoder-decoder architecture to extract features from input images and produce a multi-label heatmap for predicting lane's label. This architecture has the potential to detect more diverse types of lanes in that it can add the number of labels by extending the heatmap's dimension. The proposed algorithm was tested on an OpenLane dataset and achieved 85 Frames Per Second (FPS) in end to-end inference time. The results demonstrate the usability and computational efficiency of the proposed algorithm for the lane detection in autonomous vehicles.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1997.04a
• /
• pp.68-75
• /
• 1997

This paper presents a new approach to the design of neural-fuzzy controller for the speed and azimuth control of a track vehicle. The proposed control scheme uses a Gaussian function as a unit function in the frzzy-neural network, and back propagaton algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a track vehicle driven by two independent wheels.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.12
• /
• pp.449-454
• /
• 2014

While the era of driverless car has come, Vehicular Ad hoc NETwork(VANET) is getting important. Original VANET has a limit that cannot use computation power, storage space of On Board Unit(OBU) installed in a vehicle efficiently. VANET cloud computing(VCC) solves the limit to focus on using abilities of each vehicle. This article proposes VCC architecture for supplementing user addition and initial cloud creation that have been researched insufficiently.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.79-88
• /
• 2015

In this paper, we examine Ethernet based vehicle network which is recently emerging technology. Current MOST for entertainment will be soon replaced with the emerging Ethernet based vehicle network. Although legacy standard Ethernet has several advantages it is not suitable for vehicle backbone network without any modification. As a result, many researches are happening on extending and modification of the Ethernet function for realtime and reliability. Time-triggered Ethernet, one of many trials known as AS6802, is investigated on the architecture and functionalities. We design the traffic model on Time-triggered Ethernet and analyse the latency of the network. We also consider the QoS requirement and environment of operating configuration for vehicle network.