• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.11
• /
• pp.411-418
• /
• 2022

Incorrectly loaded containers can easily knock down by strong winds. Container collapse accidents can lead to material damage and paralysis of the port system. In this paper, We propose a deep learning-based container loading state and accident risk detection technique. Using Darknet-based YOLO, the container load status identifies in real-time through corner casting on the top and bottom of the container, and the risk of accidents notifies the manager. We present criteria for classifying container alignment states and select efficient learning algorithms based on inference speed, classification accuracy, detection accuracy, and FPS in real embedded devices in the same environment. The study found that YOLOv4 had a weaker inference speed and performance of FPS than YOLOv3, but showed strong performance in classification accuracy and detection accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3086-3103
• /
• 2017

Video images captured by vehicle cameras often contain blurry or dithering frames due to inadvertent motion from bumps in the road or by insufficient illumination during the morning or evening, which greatly reduces the perception of objects expression and recognition from the records. Therefore, a real-time electronic stabilization method to correct fuzzy video from driving recorders has been proposed. In the first stage of feature detection, a coarse-to-fine inspection policy and a scale nonlinear diffusion filter are proposed to provide more accurate keypoints. Second, a new antiblurry binary descriptor and a feature point selection strategy for unintentional estimation are proposed, which brought more discriminative power. In addition, a new evaluation criterion for affine region detectors is presented based on the percentage interval of repeatability. The experiments show that the proposed method exhibits improvement in detecting blurry corner points. Moreover, it improves the performance of the algorithm and guarantees high processing speed at the same time.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.16 no.2
• /
• pp.66-73
• /
• 2008

In this paper, ultrasonic range system which detects parking lot in parking area is studied. The important part for detecting parking lot accurately is to detect the first and second corners of possible parking lot, and for that, new method using multiple echo function is introduced in this paper. Many probabilistic methods have been used to reduce uncertainties of ultrasonic sensor for distance and location of objects. Method using multiple echo, however, gives accurates results as well as simple algorithm. For experiments in parking space, ultrasonic range system was attached to a Pioneer AT-2 and final parking space map was created in a fusion with position information from wheels of a Pioneer AT-2. We will show the results are compared with error of another methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.12
• /
• pp.7302-7308
• /
• 2014

Detecting target objects robustly in natural environments is a difficult problem in the computer vision and image processing areas. This paper suggests a method of robustly detecting target objects in the environments where reflection exists. The suggested algorithm first captures scenes with a stereo camera and extracts the line and corner features representing the target objects. This method then eliminates the reflected features among the extracted ones using a homographic transform. Subsequently, the method robustly detects the target objects by clustering only real features. The experimental results showed that the suggested algorithm effectively detects the target objects in reflection environments rather than existing algorithms.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.536-543
• /
• 2014

Terrain classification is still a challenging issue in image processing, especially with high resolution satellite images. The well-known obstacles include low accuracy in the detection of targets, especially for the case of man-made structures, such as buildings and roads. In this paper, we present an efficient approach to classify and detect building footprints, foliage, grass and road from high resolution grayscale satellite images. Our contribution is to build a strong classifier using AdaBoost based on a combination of co-occurrence and Haar-like features. We expect that the inclusion of Harr-like feature improves the classification performance of the man-made structures, since Haar-like feature is extracted from corner features and rectangle features. Also, the AdaBoost algorithm selects only critical features and generates an extremely efficient classifier. Experimental result indicates that the classification accuracy of AdaBoost classifier is much higher than that of the conventional classifier using back propagation algorithm. Also, the inclusion of Harr-like feature significantly improves the classification accuracy. The accuracy of the proposed method is 98.4% for the target detection and 92.8% for the classification on high resolution satellite images.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1499-1502
• /
• 2002

A method for acquiring an environmental map by integrating distance data obtained by sonars of a moving robot with web interface is proposed. Sonar data contains outliers in some cases such as ultrasonic beam is projected onto a corner of an object. Therefore, the influence of the outliers should be reduced by detecting outliers. In our method, the outliers are detected by two ways: (i) a method considering geometrical .elation among the observed surface and the projected ultrasonic beau, and (ii) a method considering consistency with data obtained by other sonars. By measurement by the sonar, the distance from the sonar to the obstacle is obtained. Assuming the two dimensional space we can know that the inside of the sector, whose renter coincide with the sonar and whose radius is equal to the obtained distance, is the free area, and a part of the arc of this sector is the obstacle area. The generation of the environmental map is done by integrating the free area and the obstacle area obtained by each measurement by the sonars. Before the integration, the outliers detection is done by two ways mentioned above. Experimental results show that obtained maps obtained by our methods with outliers defection are much better than those by a method without outliers detection.

• International conference on construction engineering and project management
• /
• 2013.01a
• /
• pp.558-565
• /
• 2013

The process and efficiency of monitoring building and construction violations is a concern of the construction industry. The detection of violations requires appropriate and sufficiently accurate spatial information to manage and support a comprehensive inspection process and monitor compliance. A building inspection workflow must extract appropriate spatial and measurement in-formation from a variety of sources, identify potential violations across a range of compliance criteria and determine the quality of resulting inspection reports. This paper presents a framework for supporting building inspections using spatial information and methods to detect construction violations and compliance. Current inspection processes involve issues around the identification of building violations, access to building regulations and existing spatial information, integration of a range of spatial and non-spatial information, and the quality of decisions within the inspection workflows. A survey of building inspectors was conducted and used together with the issues identified to establish the requirements for a spatial inspection framework. The results demonstrate how such a framework can support improved decision-making and reduced fieldwork effort in detecting and measuring the accuracy of building violations involving building placements, street offsets and footprint areas.

• Journal of IKEEE
• /
• v.10 no.1 s.18
• /
• pp.40-48
• /
• 2006

This paper presents a new rooftop surface estimation method from 3D line segments. 3D rooftop surface estimation is based on the hierarchical grouping and initiated by 3D line merging for the disconnected 3D line segments. Merged 3D lines are applied to the detection of rooftop by surface estimating technique. To estimate surfaces we detect L-corner and T-corner points, and find fixed reliable junction points. The hypothesis of the possible rooftop surfaces are estimated as polygonal surfaces by these fixed junction points and building's rooftop models are generated by testing the possible surfaces in terms of assumptions of building surface properties. We carried out experiments by synthetic images on Avenches data set and the experimental results showed that we could reliably build 3D model with 3D surfaces, errors of which came up with 0.4 - 1.3 meter, 2.5 times more accurate than the elevation date from the conventional area-based stereo.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.160-170
• /
• 2010

This paper proposes a Haar Wavelet Feature Detector (HWFD) based on the Haar wavelet transform and average box filter. By decomposing the original image using the Haar wavelet transform, the proposed detector obtains the variance information of the image, making it possible to extract more distinctive features from the original image. For detection of interest points that represent the regions whose variance is the highest among their neighbor regions, we apply the average box filter to evaluate the local variance information and use the integral image technique for fast computation. Due to utilization of the Haar wavelet transform and the average box filter, the proposed detector is robust to illumination change, scale change, and rotation of the image. Experimental results show that even though the proposed method detects fewer interest points, it achieves higher repeatability, higher efficiency and higher matching accuracy compared with the DoG detector and Harris corner detector.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.9
• /
• pp.148-157
• /
• 2007

A new method which uses distance fields scheme and marching cube algorithm is proposed in order to get an accurate offset model of arbitrary shapes composed of triangular net. In the method, the space bounding the triangular net is divided into smaller cells. For the efficient calculation of distance fields, valid cells which will generate a portion of offset model are selected previously by the suggested detection algorithm. These valid cells are divided again into much smaller voxels which assure required accuracy. At each voxel distance fields are created by calculating the minimum distances between corner points of voxels and triangular net. After generating the whole distance fields, the offset surface were constructed by using the conventional marching cube algorithm together with mesh smoothing scheme. The effectiveness and validity of this new offset method was demonstrated by performing numerical experiments for the various types of triangular net.