• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.66-72
• /
• 2014

Histogram of oriented gradient (HOG) feature is widely used in vision-based pedestrian detection. The interpolation is the most important technique in HOG feature calculation to provide high detection rate. In interpolation technique of HOG feature calculation, two nearest orientation bins to gradient orientation for each pixel and the corresponding weights are required. In this paper, therefore, an efficient gradient orientation bin and weight calculation circuit for HOG feature is proposed. In the proposed circuit, pre-calculated values are defined in tables to avoid the operations of tangent function and division, and the size of tables is minimized by utilizing the characteristics of tangent function and weights for each gradient orientation. Pipeline architecture is adopted to the proposed circuit to accelerate the processing speed, and orientation bins and the corresponding weights for each pixel are calculated in two clock cycles by applying efficient coarse and fine search schemes. Since the proposed circuit calculates gradient orientation for each pixel with the interval of $1^{\circ}$ and determines both orientation bins and weights required in interpolation technique, it can be utilized in HOG feature calculation to support interpolation technique to provide high detection rate.

• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.395-403
• /
• 2016

Recently, Image processing has been used in many areas. In the image processing techniques that a lot of research is tracking of moving object in real time. There are a number of popular methods for tracking an object such as HOG(Histogram of Oriented Gradients) to track pedestrians, and Codebook to subtract background. However, object extraction has difficulty because that a moving object has dynamic background in the image, and occurs severe lighting changes. In this paper, we propose a method of object extraction using depth image and color image features based on ROI(Region of Interest). First of all, we look for the feature points using the color image after setting the ROI a range to find the location of object in depth image. And we are extracting an object by creating a new contour using the convex hull point of object and the feature points. Finally, we compare the proposed method with the existing methods to find out how accurate extracting the object is.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2124-2148
• /
• 2017

Accurate facial expression recognition (FER) requires reliable signal filtering and the effective feature extraction. Considering these requirements, this paper presents a novel approach for FER which is robust to noise. The main contributions of this work are: First, to preserve texture details in facial expression images and remove image noise, we improved the anisotropic diffusion filter by adjusting the diffusion coefficient according to two factors, namely, the gray value difference between the object and the background and the gradient magnitude of object. The improved filter can effectively distinguish facial muscle deformation and facial noise in face images. Second, to further improve robustness, we propose a new feature descriptor based on a combination of the Histogram of Oriented Gradients with the Canny operator (Canny-HOG) which can represent the precise deformation of eyes, eyebrows and lips for FER. Third, Canny-HOG's block and cell sizes are adjusted to reduce feature dimensionality and make the classifier less prone to overfitting. Our method was tested on images from the JAFFE and CK databases. Experimental results in L-O-Sam-O and L-O-Sub-O modes demonstrated the effectiveness of the proposed method. Meanwhile, the recognition rate of this method is not significantly affected in the presence of Gaussian noise and salt-and-pepper noise conditions.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.654-662
• /
• 2010

In this paper, we suggest an advanced algorithm, to recognize pedestrian/non-pedestrian using second-stage cascade method, which applies Adaboost algorithm to make a strong classification from weak classifications. First, we extract two feature vectors: (i) Histogram of Oriented Gradient (HOG) which includes gradient information and differential magnitude; (ii) Curvature-HOG which is based on four different curvature features per pixel. And then, a strong classification needs to be obtained from weak classifications for composite recognition method using both HOG and curvature-HOG. In the proposed method, we use one feature vector and one strong classification for the first stage of recognition. For the recognition-failed image, the other feature and strong classification will be used for the second stage of recognition. Based on our experiment, the proposed algorithm shows higher recognition rate compared to the traditional method.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.13-20
• /
• 2024

This paper introduces a method for generating model images that can identify specific cylindrical medicine containers in videos and investigates data collection techniques. Previous research had separated object detection from specific object recognition, making it challenging to apply automated image stitching. A significant issue was that the coordinate-based object detection method included extraneous information from outside the object area during the image stitching process. To overcome these challenges, this study applies the newly released YOLOv8 (You Only Look Once) segmentation technique to vertically rotating pill bottles video and employs the ORB (Oriented FAST and Rotated BRIEF) feature matching algorithm to automate model image generation. The research findings demonstrate that applying segmentation techniques improves recognition accuracy when identifying specific pill bottles. The model images created with the feature matching algorithm could accurately identify the specific pill bottles.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.4
• /
• pp.1807-1823
• /
• 2016

Local Binary Pattern (LBP) and its variants have powerful discriminative capabilities but most of them just consider each LBP code independently. In this paper, we propose sub oriented histograms of LBP for smoke detection and image classification. We first extract LBP codes from an image, compute the gradient of LBP codes, and then calculate sub oriented histograms to capture spatial relations of LBP codes. Since an LBP code is just a label without any numerical meaning, we use Hamming distance to estimate the gradient of LBP codes instead of Euclidean distance. We propose to use two coordinates systems to compute two orientations, which are quantized into discrete bins. For each pair of the two discrete orientations, we generate a sub LBP code map from the original LBP code map, and compute sub oriented histograms for all sub LBP code maps. Finally, all the sub oriented histograms are concatenated together to form a robust feature vector, which is input into SVM for training and classifying. Experiments show that our approach not only has better performance than existing methods in smoke detection, but also has good performance in texture classification.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1D
• /
• pp.111-120
• /
• 2009

Restructuring urban land use patterns from the motor-oriented to transit-oriented ones is a contemporary trend in urban planning and transportation. It is expected that transforming urban land use patterns to be transit and walking friendly would resolve various urban problems such as heavy energy consumptions, air pollutions, and traffic congestions. Korean cities have much potentials for developing transit-oriented urban environments in terms of its density and civil service levels, but the level of transit usage levels and the environmental quality of cities are not good enough for supporting such transition. The purpose of this study is to analyze the urban transit center areas and identify the problems to be solved to create transit-oriented urban environments. Case studies of four urban transit center areas in Seoul Metropolitan region were conducted to examine the spatial characteristics of urban transit center areas and identify their problems. Development density, land use diversity, walk-ability and transit connectivity were the primary feature of interests.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.7
• /
• pp.337-352
• /
• 2017

Clone-and-own reuse is an approach to creating new software variants by copying and modifying existing software products. A family of legacy software products developed by clone-and-own reuse often requires high maintenance cost and tends to be error-prone due to patch-ups without refactoring and structural degradation. To overcome these problems, many organizations that have used clone-and-own reuse now want to migrate their legacy products to software product line (SPL) for more systematic reuse and management of software asset. However, with most of existing methods, variation points are embedded directly into design and code rather than modeled and managed separately; variation points are not created ("engineered") systematically based on a variability model. This approach causes the following problems: it is difficult to understand the relationships between variation points, thus it is hard to maintain such code and the asset tends to become error-prone as it evolves. Also, when SPL evolves, design/code assets tend to be modified directly in an ad-hoc manner rather than engineered systematically with appropriate refactoring. To address these problems, we propose a feature-oriented method for extracting a SPL asset from a family of legacy applications. With the approach, we identify and model variation points and their relationships in a feature model separate from implementation, and then extract and manage a SPL asset from legacy applications based on the feature model. We have applied the method to a family of legacy Notepad++ products and demonstrated the feasibility of the method.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.24 no.66
• /
• pp.1-10
• /
• 2001

Simulation-Based Expert System(SIMBES) is a very effective tool to solve complex antral hard problems. The SIMBES model includes a simulator, a feature extractor, a machine learning system, a performance evaluator, and a Knowledge-Based Expert System(KBES). Since SIMBES depends on Problem domains, a schedule-based material requirements planning problem, which is NP-hard, was selected to exemplify the SIMBES model. To implement the SIMBES application in Smalltalk paradigm, a system class hierarchy was constructed. The hierarchy consists of five large classes such as Job Generator, Job Scheduler, Job Evaluator, Inference Engine, and Executive System. Several classes inside these classes were identified. Additionally, instance protocols about all classes have been described in terms of messages and pseudo methods. These protocols can be implemented easily by any other object-oriented languages. Furthermore, these results may be used as a skeletal system to develop a new SIMBES efficiently, especially when the application is related to other scheduling problems.