• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.1
• /
• pp.47-53
• /
• 2011

To enable the efficient operation of ITS, it is necessary to collect location data for vehicles on the road. In the case of futuristic transportation systems like ubiquitous transportation and smart highway, a method of data collection that is advanced enough to incorporate road lane recognition is required. To meet this requirement, technology based on radio frequency identification (RFID) has been researched. However, RFID may fail to yield accurate location information during high-speed driving because of the time required for communication between the tag and the reader. Moreover, installing tags across all roads necessarily incurs an enormous cost. One cost-saving alternative currently being researched is to utilize GNSS (global navigation satellite system) carrierbased location information where available. For lane recognition using GNSS, a precise digital map for determining vehicle position by lane is needed in addition to the carrier-based GNSS location data. A "precise digital map" is a map containing the location information of each road lane to enable lane recognition. At present, precise digital maps are being created for lane recognition experiments by measuring the lanes in the test area. However, such work is being carried out through comparison with vehicle driving information, without definitions being established for detailed performance specifications. Therefore, this study analyzes the performance requirements of a precise digital map capable of lane recognition based on the accuracy of GNSS location information and the accuracy of the precise digital map. To analyze the performance of the precise digital map, simulations are carried out. The results show that to have high performance of this system, we need under 0.5m accuracy of the precise digital map.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2483-2503
• /
• 2016

Traffic congestion is a severe problem in many modern cities around the world. Real-time and accurate traffic congestion identification can provide the advanced traffic management systems with a reliable basis to take measurements. The most used data sources for traffic congestion are loop detector, GPS data, and video surveillance. Video based traffic monitoring systems have gained much attention due to their enormous advantages, such as low cost, flexibility to redesign the system and providing a rich information source for human understanding. In general, most existing video based systems for monitoring road traffic rely on stationary cameras and multiple vehicle tracking method. However, most commonly used multiple vehicle tracking methods are lack of effective track initiation schemes. Based on the motion of the vehicle usually obeys constant velocity model, a novel vehicle recognition method is proposed. The state of recognized vehicle is sent to the GM-PHD filter as birth target. In this way, we relieve the insensitive of GM-PHD filter for new entering vehicle. Combining with the advanced vehicle detection and data association techniques, this multiple vehicle tracking method is used to identify traffic congestion. It can be implemented in real-time with high accuracy and robustness. The advantages of our proposed method are validated on four real traffic data.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.89-96
• /
• 2017

This Paper proposes a vehicle detection system and a license plate recognition system from CCTV images installed on public roads. Since the environment of this system acquires the image in the general road environment, the stable condition applied to the existing vehicle entry / exit system is not given, and the input image is distorted and the resolution is irregular. At the same time, the viewing angle of the input image is more wide, so that the computation load is high and the recognition accuracy of the plate is likely to be lowered. In this paper, we propose an improved method to detect and recognize a license plate without a separate input control devices. The vehicle and license plate were detected based on the HOG feature descriptor, and the characters inside the license plate were recognized using the k-NN algorithm. Experimental environment was set up for the roads more than 45m away from the CCTV, Experiments were carried out on an entry vehicle capable of visually identifying license plate and Experimental results show good results of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.10
• /
• pp.909-919
• /
• 2014

License plate (LP) detection is the most imperative part of an automatic LP recognition (LPR) system. Typical LPR contains two steps, namely LP detection (LPD) and character recognition. In this paper, we propose an efficient Vehicle-to-LP detection framework which combines with an adaptive GMM (Gaussian Mixture Model) and a cascade of boosted classifiers to make a faster vehicle LP detector. To develop a background model by using a GMM is possible in the circumstance of a fixed camera and extracts the motions using background subtraction. Firstly, an adaptive GMM is used to find the region of interest (ROI) on which motion detectors are running to detect the vehicle area as blobs ROIs. Secondly, a cascade of boosted classifiers is executed on the blobs ROIs to detect a LP. The experimental results on our test video with the resolution of $720{\times}576$ show that the LPD rate of the proposed system is 99.14% and the average computational time is approximately 42ms.

• Journal of Advanced Navigation Technology
• /
• v.17 no.2
• /
• pp.165-170
• /
• 2013

In this paper, we propose the information acquisition and analysis system for a vehicle driver in order to provide the safe driving environments. We first define the list of reckless driving behaviors and propose the recognition system, which recognizes the reckless behaviors, by using the acquired information. The collaboration among the information acquisition, the analysis, and the behavior comparison modules increases the accuracy of the recognition rate. Our system alarms to a vehicle driver in order to notify the potential to confront the dangerous situation due to the abnormal or reckless driving behaviors.

• Korean Journal of Artificial Intelligence
• /
• v.9 no.2
• /
• pp.29-34
• /
• 2021

In this paper, for efficient parking control, in an Arduino environment, an intelligent parking control prototype was implemented to provide parking control and parking guidance information using HC-SR2O4 and RC522. The main elements of intelligent parking control are vehicle recognition sensors, parking control facilities, and integrated operating software. Whether the vehicle is parked on the parking surface may be confirmed through sensor or intelligent camera image analysis. Parking control equipment products include parking guidance and parking available display devices, vehicle number recognition cameras, and intelligent parking assistance systems. This paper applies and implements ultrasonic sensors and RFID concepts based on Arduino, recognizes registered vehicles, and displays empty spaces. When a vehicle enters a parking space to handle this function, the automatic parking management system distinguishes the registered vehicle from the external vehicle through the RC522 sensor. In addition, after checking whether the parking slot is empty, the HC-SR204 sensor is displayed through the LED so that the driver can visually check it. RFID is designed to check the parking status of the server in real time and provide the driver with optimal route service to the parking slot.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.636-639
• /
• 2003

In this paper, we present a robust method for detecting other vehicles from n forward-looking CCD camera in a moving vehicle. This system uses edge and shape information to detect other vehicles. The algorithm consists of three steps: lane detection, ehicle candidate generation, and vehicle verification. First after detecting a lane from the template matching method, we divide the road into three parts: left lane, front lane, and right lane. Second, we set the region of interest (ROI) using the lane position information and extract a vehicle candidate from the ROI. Third, we use local orientation coding (LOC) edge image of the vehicle candidate as input to a pretrained neural network for vehicle recognition. Experimental results from highway scenes show the robustness and effectiveness of this method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.07a
• /
• pp.135-136
• /
• 2017

When driving at night time environment, the whole body of transports does not visible to us. Due to lack of light conditions, there are only two options, which is clearly visible their taillights and break lights. To improve the recognition correctness of vehicle detection, we present an approach to vehicle detection and tracking using finding contour of the object on binary image at night time. Bilateral filtering is used to make more clearly on threshold part. To remove unexpected small noises used morphological opening. In verification stage, paired tail lights are tracked during their existence in the ROI. The accuracy of the test results for vehicle detection is about 93%.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.303-304
• /
• 2006

This paper proposes detection method of vehicles using camera for auto-vehicle-system. Detection method is based on shadow detection and symmetric feature of vehicle. This method consists of three part. First is lane detection. By lane detection, we can reduce the area for vehicle detection. Second part is shadow detection. Shadow has information of vehicle width and position. Third part is symmetry. This feature is helpful for confirming the vehicle.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.17 no.4
• /
• pp.85-94
• /
• 2021

The LPR system's trigger sensor makes problem occasionally due to the heave weight of vehicle or the obsolescence equipment. If we replace the hardware sensor to the deep-learning based software sensor in order to generate the trigger signal, LPR system maintenance would be a lot easier. In this paper we proposed the deep-learning sliding window based object detection and tracking algorithm for the LPR system's trigger signal generation. The gate passing vehicle's license plate recognition results are combined into the normal tracking algorithm to catch the position of the vehicle on the trigger line. The experimental results show that the deep learning sliding window based trigger signal generating performance was 100% for the gate passing vehicles including the 5.5% trigger signal position errors due to the minimum bounding box location errors in the vehicle detection process.