• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.6
• /
• pp.621-628
• /
• 2015

This paper describes an algorithm for detecting vehicles detection in real time. The proposed algorithm has the technique based on computer vision and image processing. In real, complex environment such as one with road traffic, many algorithms have great difficulty such as low detection rate and increasing computational time due to complex backgrounds and rapid changes. To overcome this problem in this paper, the proposed algorithm consists of the following methods. First, to effectively separate the candidate regions, we use vertical and horizontal edge information, and shadow values from input image sequences. Second, we extracts features by using HOG from the selected candidate regions. Finally, this paper uses the OS fuzzy-ELM based on SLFN to classify the extracted features. The experimental results show that the proposed method perform well for detecting vehicles and improves the accuracy and the computational time of detecting.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.10
• /
• pp.1334-1339
• /
• 2018

Viola & Jones's face detection algorithm is a typical face detection algorithm and shows excellent face detection performance. However, the Viola & Jones's algorithm in images including many faces generates undetected faces and wrong detected faces, such as false faces and duplicate detected faces, due to face diversity. This paper proposes an improved face detection algorithm using a face verification algorithm that eliminates the false detected faces generated from the Viola & Jones's algorithm. The proposed face verification algorithm verifies whether the detected face is valid by evaluating its size, its skin color in the designated area, its edges generated from eyes and mouth, and its duplicate detection. In the face verification experiment of 658 face images detected by the Viola & Jones's algorithm, the proposed face verification algorithm shows that all the face images created in the real person are verified.

• Smart Media Journal
• /
• v.6 no.3
• /
• pp.15-20
• /
• 2017

Recently, the automotive industry has been studied about driver assistance systems for helping drivers to drive their cars easily by integrating them with the IT technology. This study suggests a method of detecting lanes, robust to road condition changes and applicable to lane departure warning and autonomous vehicles mode. The proposed method uses the method of detecting candidate areas by using the Gaussian filter and by determining the Otsu threshold value and edge. Moreover, the proposed method uses lane gradient and width information through the Hough transform to detect lanes. The method uses road lane information detected before to detect dashed lines as well as solid lines, calculates routes in which the lanes will be located in the next frame to draw virtual lanes. The proposed algorithm was identified to be able to detect lanes in both dashed- and solid-line situations, and implement real-time processing where applied to Raspberry Pi 2 which is open source hardware.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.474-480
• /
• 2020

With the advent of the Fourth Industrial Revolution, many new technologies are being utilized. In particular, video signals are used in various fields. However, when transmitting and receiving video signals, salt and pepper noise and additive white Gaussian noise (AWGN) occur for multiple reasons. Failure to remove such noise when performing image processing can cause problems. Generally, filters such as CWMF, MF, and AMF remove noise. However, these filters perform somewhat poorly in the high-density noise domain and cause smoothing, resulting in slightly lower retention of the edge components. In this paper, we propose an algorithm by effectively eliminating salt and pepper noise using a modified weight filter using standard deviation. In order to prove the noise reduction performance of the proposed algorithm, we compared it with the existing algorithm using PSNR and magnified images.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.313-330
• /
• 2021

In an autonomous driving system equipped with a camera and lidar, depth completion techniques enable dense depth estimation. In particular, using self-supervised learning it is possible to train the depth completion network even without ground truth. In actual autonomous driving, such depth completion should have very short latency as it is the input of other algorithms. So, rather than complicate the network structure to increase the accuracy like previous studies, this paper focuses on network latency. We design a U-Net type network with RegNet encoders optimized for GPU computation. Instead, this paper presents several techniques that can increase accuracy during the process of self-supervised learning. The proposed techniques increase the robustness to unreliable lidar inputs. Also, they improve the depth quality for edge and sky regions based on the semantic information extracted in advance. Our experiments confirm that our model is very lightweight (2.42 ms at 1280x480) but resistant to noise and has qualities close to the latest studies.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.83-92
• /
• 2009

In this paper, an extended snake algorithm using color variance energy is proposed for segmenting an interest object in color image. General snake algorithm makes use of energy in image to segment images into a interesting area and background. There are many kinds of energy that can be used by the snake algorithm. The efficiency of the snake algorithm is depend on what kind of energy is used. A general snake algorithm based on active contour model uses the intensity value as an image energy that can be implemented and analyzed easily. But it is sensitive to noises because the image gradient uses a differential operator to get its image energy. And it is difficult for the general snake algorithm to be applied on the complex image background. Therefore, the proposed snake algorithm efficiently segment an interest object on the color image by adding a color variance of the segmented area to the image energy. This paper executed various experiments to segment an interest object on color images with simple or complex background for verifying the performance of the proposed extended snake algorithm. It shows improved accuracy performance about 12.42 %.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.3
• /
• pp.339-349
• /
• 2017

This paper proposes a four-stage algorithm for detecting lanes on a driving car. In the first stage, it extracts region of interests in an image. In the second stage, it employs a median filter to remove noise. In the third stage, a binary algorithm is used to classify two classes of backgrond and foreground of an input image. Finally, an image erosion algorithm is utilized to obtain clear lanes by removing noises and edges remained after the binary process. However, the proposed lane detection algorithm requires high computational time. To address this issue, this paper presents a parallel implementation of a real-time line detection algorithm on a multi-core architecture. In addition, we implement and simulate 8 different processing element (PE) architectures to select an optimal PE architecture for the target application. Experimental results indicate that 40×40 PE architecture show the best performance, energy efficiency and area efficiency.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.2
• /
• pp.36-44
• /
• 2024

This paper presents the application of Convolutional Neural Networks (CNNs) and Region of Interest (ROI) techniques for concrete crack analysis. Surfaces of concrete structures, such as beams, etc., are exposed to fatigue stress and cyclic loads, typically resulting in the initiation of cracks at a microscopic level on the structure's surface. Early detection enables preventative measures to mitigate potential damage and failures. Conventional manual inspections often yield subpar results, especially for large-scale infrastructure where access is challenging and detecting cracks can be difficult. This paper presents data collection, edge segmentation and ROI techniques application, and analysis of concrete cracks using Convolutional Neural Networks. This paper aims to achieve the following objectives: Firstly, achieving improved accuracy in crack detection using image-based technology compared to traditional manual inspection methods. Secondly, developing an algorithm that utilizes enhanced Sobel edge segmentation and ROI techniques. The algorithm provides automated crack detection capabilities for non-destructive testing.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.6 s.312
• /
• pp.26-33
• /
• 2006

Film restoration is to detect the location and extent of defected regions from a given movie film, and if present, to reconstruct the lost information of each region. It has gained increasing attention by many researchers, to support multimedia service of high quality. In general, an old film is degraded by dust, scratch, flick, and so on. Among these, the most frequent degradation is the scratch. So far techniques for the scratch restoration have been developed, but they have limited applicability when dealing with all kinds of scratches. To fully support the automatic scratch restoration, the system should be developed that can detect all kinds of scratches from a given frame of old films. This paper presents a neurual network (NN)-based texture classifier that automatically detect all kinds of scratches from frames in old films. To facilitate the detection of various scratch sizes, we use a pyramid of images generated from original frames by having the resolution at three levels. The image at each level is scanned by the NN-based classifier, which divides the input image into scratch regions and non-scratch regions. Then, to reduce the computational cost, the NN-based classifier is only applied to the edge pixels. To assess the validity of the proposed method, the experiments have been performed on old films and animations with all kinds of scratches, then the results show the effectiveness of the proposed method.

• Journal of KIISE:Software and Applications
• /
• v.36 no.2
• /
• pp.161-168
• /
• 2009

In this paper, we develop an Intelligent Wheelchair(IW) control system for the people with various disabilities. The aim of the proposed system is to increase the mobility of severely handicapped people by providing an adaptable and effective interface for a power wheelchair. To facilitate a wide variety of user abilities, the proposed system involves the use of face-inclination and mouth-shape information, where the direction of an Intelligent Wheelchair(IW) is determined by the inclination of the user's face, while proceeding and stopping are determined by the shape of the user's mouth. To analyze these gestures, our system consists of facial feature detector, facial feature recognizer, and converter. In the stage of facial feature detector, the facial region of the intended user is first obtained using Adaboost, thereafter the mouth region detected based on edge information. The extracted features are sent to the facial feature recognizer, which recognize the face inclination and mouth shape using statistical analysis and K-means clustering, respectively. These recognition results are then delivered to a converter to control the wheelchair. When assessing the effectiveness of the proposed system with 34 users unable to utilize a standard joystick, the results showed that the proposed system provided a friendly and convenient interface.