• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2S
• /
• pp.629-637
• /
• 2000

The content-based information retrieval for a multimedia database uses feature information extracted from the compressed videos. This paper presents an effective method to detect scene changes from compressed videos. Scene changes are detected with DC values of DCT coefficients in MPEG-1 encoded video sequences. Instead of decoding full frames. partial macroblocks of each frame, horizontal and vertical macroblocks, are decoded to detect scene changes. This method detects abrupt scene changes by decoding minimal number of blocks and saves a lot of computation time. The performance of the proposed algorithm is analyzed based on the precision and the recall. The experimental results show the effectiveness in computation time and detection rate to detect scene changes of various MPEG-1 video streams.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.31-39
• /
• 2003

It is often assumed that text regions in images are characterized by some distinctive or characteristic spatial frequencies. This feature is highly intuitive, and thus appealing as much. We propose a method of detecting horizontal texts in natural scene images. It is based on the use of two features that can be employed separately or in succession: the frequency of edge pixels across vertical and horizontal scan lines, and the fundamental frequency in the Fourier domain. We confirmed that the frequency features are language independent. Also addressed is the detection of quadrilaterals or approximate rectangles using Hough transform. Since texts that is meaningful to many viewers usually appear within rectangles with colors in high contrast to the background. Hence it is natural to assume the detection rectangles may be helpful for locating desired texts correctly in natural outdoor scene images.

• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.539-554
• /
• 2024

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

• Journal of the Institute of Convergence Signal Processing
• /
• v.17 no.1
• /
• pp.18-25
• /
• 2016

As more people have cars, the threat of traffic accidents is posed on men and women of all ages. The main culprit of traffic accidents is driving while intoxicated or drowsy. The method to recognize and prevent the cause of traffic accidents is to use lane detection. In this study, a total of 4,000 frames (day image: 2,900 frames, night image: 1,100 frames) were used to test lane detection. According to the test, in the case of day image, when the threshold of Sobel edge detection technique was detected with second-order differential equation, there was the highest candidate lane detection rate which was 86.1%. In the threshold of Canny edge detection technique, the highest detection rate of 88.0% was found at Low=50, and High=300. In the case of night image, the threshold of Sobel edge detection technique, when horizontal calculation and vertical calculation had second-order differential equation, and when horizontal-vertical calculation had 1.5th-order differential equation, there was the highest detection rate which was 83.1%. In the threshold of Canny edge detection technique, the highest detection rate of 89.9% was found at Low=50, and High=300.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.249-255
• /
• 2013

In this paper, we propose an algorithm to detect scale invariant object from IR image obtained in the sea environment. We create horizontal edge (HL), vertical edge (LH), diagonal edge (HH) of images through 2-D discrete Haar wavelet transform (DHWT) technique after noise reduction using morphology operations. Considering the sea environment, Gaussian blurring to the horizontal and vertical edge images at each level of wavelet is performed and then saliency map is generated by multiplying the blurred horizontal and vertical edges and combining into one image. Then we extract object candidate region by performing a binarization to saliency map. A small area in the object candidate region are removed to produce final result. Experiment results show the feasibility of the proposed algorithm.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.7
• /
• pp.107-116
• /
• 2014

This paper presents camera-based road surface marking detection methods suited to sensor fusion-based positioning system that consists of low-cost GPS (Global Positioning System), INS (Inertial Navigation System), EDM (Extended Digital Map), and vision system. The proposed vision system consists of two parts: lane marking detection and RSM (Road Surface Marking) detection. The lane marking detection provides ROIs (Region of Interest) that are highly likely to contain RSM. The RSM detection generates candidates in the regions and classifies their types. The proposed system focuses on detecting RSM without false detections and performing real time operation. In order to ensure real time operation, the gating varies for lane marking detection and changes detection methods according to the FSM (Finite State Machine) about the driving situation. Also, a single template matching is used to extract features for both lane marking detection and RSM detection, and it is efficiently implemented by horizontal integral image. Further, multiple step verification is performed to minimize false detections.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.1
• /
• pp.17-21
• /
• 2011

This paper presents a real- time detection of on-road succeeding vehicles based on low level edge features and a boosted cascade of Haar-like features. At first, the candidate vehicle location in an image is found by low level horizontal edge and symmetry characteristic of vehicle. Then a boosted cascade of the Haar-like features is applied to the initial hypothesized vehicle location to extract the refined vehicle location. The initial hypothesis generation using simple edge features speeds up the whole detection process and the application of a trained cascade on the hypothesized location increases the accuracy of the detection process. Experimental results on real world road scenario with processing speed of up to 27 frames per second for $720{\times}480$ pixel images are presented.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.2
• /
• pp.94-102
• /
• 2011

In this paper, a novel drowsiness detection algorithm using eye-blink pattern is proposed. The proposed drowsiness detection model using finite automata makes it easy to detect eye-blink, drowsiness and sleep by checking the number of input symbols standing for closed eye state only. Also it increases the accuracy by taking vertical projection histogram after locating the eye region using the feature of horizontal projection histogram, and minimizes the external effects such as eyebrows or black-framed glasses. Experimental results in eye-blinks detection using the JZU eye-blink database show that our approach achieves more than 93% precision and high performance.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.31-40
• /
• 2022

YOLOv4 can be used for detecting parking vehicles in order to check a vehicle in out-door parking space. YOLOv4 has 9 anchor boxes in each of 13x13 grid cells for detecting a bounding box of object. Because anchor boxes are allocated based on each cell, there can be existed small observational error for detecting real objects due to the distance between neighboring cells. In this paper, we proposed YOLOv4 grid cell shift algorithm for improving the out-door parking vehicle detection accuracy. In order to get more chance for trying to object detection by reducing the errors between anchor boxes and real objects, grid cells over image can be shifted to vertical, horizontal or diagonal directions after YOLOv4 basic detection process. The experimental results show that a combined algorithm of a custom trained YOLOv4 and a cell shift algorithm has 96.6% detection accuracy compare to 94.6% of a custom trained YOLOv4 only for out door parking vehicle images.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1997.10a
• /
• pp.791-796
• /
• 1997

Deterioration of pavements or tunnels primarily from the existence of voids under the pavements or tunnel linings. To detect these voids effectively by non-destructive testes, a method using radar was proposed. In this research, the detection of shape of voids by radar image processing is investigate. The experiments and simulation were conducted to detect voids in or under concrete pavements for tunnel linings) with reinforcing bars. From the results, the fundamental algorithm for tracing the voids, improving the horizontal resolution of the object image and detecting shape of objects, was verified.