• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.1
• /
• pp.87-96
• /
• 2018

In this paper, we propose a method to determine whether there is a defect by using the similarity between ROIs (Region of Interest) of the standard image and ROIs of the image which is corrected in position and rotation after capturing the vehicle headlight. The degree of similarity is determined by the template matching based on the histogram of image, which is a some modification of the method provided by OpenCV where template matching is performed on the raw image not the histogram. The proposed method is compared with the basic method of OpenCV for performance analysis. As a result of the analysis, it was found that the proposed method showed better performance than the OpenCV method, showing the accuracy close to 100%.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.9
• /
• pp.950-956
• /
• 2014

In this paper, the real-time detection method of a DDP (Driving Direction Point) is proposed for an unmanned vehicle to safely follow the center of the road. Since the DDP is defined as a center point between two lanes, the lane is first detected using a web camera. For robust detection of the lane, the binary thresholding and the labeling methods are applied to the color camera image as image preprocessing. From the preprocessed image, the lane is detected, taking the intrinsic characteristics of the lane such as width into consideration. If both lanes are detected, the DDP can be directly obtained from the preprocessed image. However, if one lane is detected, the DDP is obtained from the inverse perspective image to guarantee reliability. To verify the proposed method, several experiments to detect the DDPs are carried out using a 4 wheeled vehicle ERP-42 with a web camera.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.7
• /
• pp.718-723
• /
• 2014

In this paper, we developed the inspection system of electric vehicle battery plate using image processing. Four cameras are used for acquiring the principal parts of the plate, and several steps of image processing for extracting significant dimensions of the plate such as widths and lengths. As a preceding step, calibration of four cameras is carried for compensating distorted images using dot-arrayed sheet. Coordinate systems for four cameras are defined where one coordinate system is assigned to the reference coordinate system to which the others are relatively described. Line information of the edge in the windowed image is extracted using elaborate edge-detection algorithm, and finally the intersection points between lines are extracted to calculate widths and lengths of the plate from which the error status of the battery plate is decided.

• Journal of information and communication convergence engineering
• /
• v.9 no.4
• /
• pp.447-451
• /
• 2011

Recently, various in-vehicle networks have been developed respectively in order to accomplish their own purposes such as CAN and MOST. Especially, the MOST network is usually adapted to provide entertainment service. The car navigation system is also widely used for guiding driving paths to driver. The position for the navigation system is usually acquired by GPS technology. However, the GPS technique has two serious problems. The first is unavailability in urban canyons. The second is inherent positional error rate. The problems have been studied in many literatures. However, the second still leads to incorrect locational information in some area, especially parallel roads. This paper proposes a performance tuning method of image matching algorithm for the car navigation system. The method utilizes images obtained from in-vehicle MOST network and a real-time image matching algorithm which determines the direction of moving vehicle in parallel section of road. In order to accuracy improvement of image matching algorithm, three conditions are applied. The experimental tests show that the proposed system increases the accuracy.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.119-128
• /
• 2021

The most typical method to generate traffic information is installing vehicle detectors and collecting various traffic variables. The information collection accuracy of a vehicle detector affects the reliability of the generated traffic information. The most universal vehicle detector is an image detector. This study installed a magnetic detector in the same position as an image detector and evaluated the accuracy of traffic volume and speed data depending on a variety of environment. Based on the evaluation, more errors occurred as the image detector was placed farther from the camera, whereas more errors were found to occur during the night rather than the day. Although rainfall did not affect the collection of traffic volume, it negatively affected speed data collection. Therefore, an analysis of the camera's view angle and its optimization depending on the camera installation position and height are required to enhance the currently operated image detector performance. It is judged that a separate performance evaluation criterion should be prepared in a bad weather environment.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1044-1050
• /
• 2021

After the occurrence of several passenger ship accidents in Korea, various systems are being developed for passenger ship safety management. A total of 162 passenger ships operate along the coast of Korea, of which 105 (65 %) are car-ferries with open vehicle decks. The car-ferry has a navigation pattern that passes through 2 to 4 islands. Safety inspections at the departure point(home port) are carried out by the crew, the operation supervisor of the operation management office, and the maritime safety supervisor. In some cases, self-inspections are carried out for safety inspections at layovers. As with any system, there are institutional and practical limitations. To this end, this study was conducted to suggest a method of detecting a vehicle using image processing and linking it to the calculations for ship stability. For vehicle detection, a method using a difference image and one using machine learning were used. However, a limitation was observed in these methods that the vehicle could not be identified due to strong background lighting from the pier and the ship in the cases where the camera was backlit such as during sunset or at night. It appears necessary to secure sufficient image data and upgrade the program for stable image processing.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.1
• /
• pp.13-20
• /
• 2016

In this study, we propose a method to regulate parking violations using computer vision technology. A still color image of the parked vehicle under question is obtained by a camera mounted on enforcement vehicles. The acquired image is preprocessed through a morphological algorithm and binarized. The vehicle's shadows are detected from the binarized image, and lanes are identified using the information from the yellow parking lines that are drawn on the load. Whether parking is illegal is determined by the conformity of the lanes and the vehicle's shadow.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.3
• /
• pp.269-279
• /
• 2020

Traffic estimation mainly involves surveying equipment such as automatic vehicle classification, vehicle detection system, toll collection system, and personnel surveys through CCTV (Closed Circuit TeleVision), but this requires a lot of manpower and cost. In this study, we proposed a method of estimating traffic volume using deep learning and stereo CCTV to overcome the limitation of not detecting the entire vehicle in case of single CCTV. COCO (Common Objects in Context) dataset was used to train deep learning models to detect vehicles, and each vehicle was detected in left and right CCTV images in real time. Then, the vehicle that could not be detected from each image was additionally detected by using affine transformation to improve the accuracy of traffic volume. Experiments were conducted separately for the normal road environment and the case of weather conditions with fog. In the normal road environment, vehicle detection improved by 6.75% and 5.92% in left and right images, respectively, than in a single CCTV image. In addition, in the foggy road environment, vehicle detection was improved by 10.79% and 12.88% in the left and right images, respectively.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1131-1142
• /
• 2018

The autonomous vehicles are being developed and operated widely because of the advantages of reducing the traffic accident and saving time and cost for driving. The vehicle localization is an essential component for autonomous vehicle operation. In this paper, localization algorithm based on sensor fusion is developed for cost-effective localization using in-vehicle sensors, GNSS, an image sensor and reference images that made in advance. Information of the reference images can overcome the limitation of the low positioning accuracy that occurs when only the sensor information is used. And it also can acquire estimated result of stable position even if the car is located in the satellite signal blockage area. The particle filter is used for sensor fusion that can reflect various probability density distributions of individual sensors. For evaluating the performance of the algorithm, a data acquisition system was built and the driving data and the reference image data were acquired. Finally, we can verify that the vehicle positioning can be performed with an accuracy of about 0.7 m when the route image and the reference image information are integrated with the route path having a relatively large error by the satellite sensor.

• Journal of Convergence for Information Technology
• /
• v.8 no.6
• /
• pp.375-380
• /
• 2018

This paper proposes a classification method using the Convolutional Neural Network(CNN) which can obtain the type of trucks from the input image without the feature extraction step. To automatically classify vehicle images according to the type of truck cargo box, the top view images of the vehicle are used as input image and we design the structure of the CNN suitable for the input images. Learning images and correct output results is generated and the weights of neural network are obtained through the learning process. The actual image is input to the CNN and the output of the CNN is calculated. The classification performance is evaluated through comparison CNN output with actual vehicle types. Experimental results show that vehicle images could be classified with more than 90 percent accuracy according to the type of cargo box and this method can be used for pre-classification for inspecting loading defect.