• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3820-3841
• /
• 2018

Most of the accidents occur due to drowsiness while driving, avoiding road signs and due to driver's distraction. Driver's distraction depends on various factors which include talking with passengers while driving, mood disorder, nervousness, anger, over-excitement, anxiety, loud music, illness, fatigue and different driver's head rotations due to change in yaw, pitch and roll angle. The contribution of this paper is two-fold. Firstly, a data set is generated for conducting different experiments on driver's distraction. Secondly, novel approaches are presented that use features based on facial points; especially the features computed using motion vectors and interpolation to detect a special type of driver's distraction, i.e., driver's head rotation due to change in yaw angle. These facial points are detected by Active Shape Model (ASM) and Boosted Regression with Markov Networks (BoRMaN). Various types of classifiers are trained and tested on different frames to decide about a driver's distraction. These approaches are also scale invariant. The results show that the approach that uses the novel ideas of motion vectors and interpolation outperforms other approaches in detection of driver's head rotation. We are able to achieve a percentage accuracy of 98.45 using Neural Network.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.143-150
• /
• 2010

Markerless augmented reality system must have the capability to recognize and match natural objects both in indoor and outdoor environment. In this paper, a novel approach is proposed for extracting features and recognizing natural objects using visual descriptors and codebooks. Since the augmented reality applications are sensitive to speed of operation and real time performance, our work mainly focused on recognition of multi-class natural objects and reduce the computing time for classification and feature extraction. SIFT(scale invariant feature transforms) and SURF(speeded up robust feature) are used to extract features from natural objects during training and testing, and their performance is compared. Then we form visual codebook from the high dimensional feature vectors using clustering algorithm and recognize the objects using naive Bayes classifier.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.4
• /
• pp.256-262
• /
• 2004

A key component of an autonomous mobile robot is to localize itself and build a map of the environment simultaneously. In this paper, we propose a vision-based localization and mapping algorithm of mobile robot using fisheye lens. To acquire high-level features with scale invariance, a camera with fisheye lens facing toward to ceiling is attached to the robot. These features are used in mP building and localization. As a preprocessing, input image from fisheye lens is calibrated to remove radial distortion and then labeling and convex hull techniques are used to segment ceiling and wall region for the calibrated image. At the initial map building process, features we calculated for each segmented region and stored in map database. Features are continuously calculated for sequential input images and matched to the map. n some features are not matched, those features are added to the map. This map matching and updating process is continued until map building process is finished, Localization is used in map building process and searching the location of the robot on the map. The calculated features at the position of the robot are matched to the existing map to estimate the real position of the robot, and map building database is updated at the same time. By the proposed method, the elapsed time for map building is within 2 minutes for 50㎡ region, the positioning accuracy is ±13cm and the error about the positioning angle of the robot is ±3 degree for localization.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.767-776
• /
• 2020

GcGAN is a deep learning model to translate styles between images under geometric consistency constraint. However, GcGAN has a disadvantage that it does not properly maintain detailed content of an image, since it preserves the content of the image through limited geometric transformation such as rotation or flip. Therefore, in this study, we propose a new image-to-image translation method, MSGcGAN(Multi-Scale GcGAN), which improves this disadvantage. MSGcGAN, an extended model of GcGAN, performs style translation between images in a direction to reduce semantic distortion of images and maintain detailed content by learning multi-scale images simultaneously and extracting scale-invariant features. The experimental results showed that MSGcGAN was better than GcGAN in both quantitative and qualitative aspects, and it translated the style more naturally while maintaining the overall content of the image.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_1
• /
• pp.693-698
• /
• 2021

As technology advances, there is increasing need for research in different fields where this technology is applied. On of the most researched topic in computer vision is Human activity recognition (HAR), which has widely been implemented in various fields which include healthcare, video surveillance and education. We therefore present in this paper a human activity recognition system based on scale and rotation while employing the Kinect depth sensors to obtain the human skeleton joints. In contrast to previous approaches that use joint angles, in this paper we propose that each limb has an angle with the X, Y, Z axes which we employ as feature vectors. The use of the joint angles makes our system scale invariant. We further calculate the body relative direction in the egocentric coordinates in order to provide the rotation invariance. For the system parameters, we employ 8 limbs with their corresponding angles each having the X, Y, Z axes from the coordinate system as feature vectors. The extracted features are finally trained and tested with the Long short term memory (LSTM) Network which gives us an average accuracy of 98.3%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.2
• /
• pp.55-65
• /
• 2011

In this paper, a novel method of marker detection robust against marker occlusion in augmented reality is proposed. the proposed method consists of four steps. In the first step, in order to effectively detect an occluded marker, we first utilize the Affine-SIFT (ASIFT, Affine-Scale Invariant Features Transform) for detecting matching points between an enrolled marker and an input images with an occluded marker. In the second step, we apply the Principal Component Analysis (PCA) for eliminating outlier of the matching points in the enrolled marker. And then matching points are projected to the first and second axis for longest value and the shortest value of an ellipse are determined by average distance between the projected points and a center of the points. In the third step, Convex-hull vertices including matching points are considered as polygon vertices for estimating a geometric affine transformation. In the final step, by estimating the geometric affine transformation of the points, a marker robust against a marker occlusion is detected. Experimental results have shown that the proposed method effectively detects occlude markers.

• Journal of Advanced Navigation Technology
• /
• v.16 no.2
• /
• pp.394-400
• /
• 2012

SURF is a robust local invariant feature descriptor and has been used in many applications such as object recognition. Even though this algorithm has similar matching accuracy compared to the SIFT, which is another popular feature extraction algorithm, it has advantage in matching time. However, these descriptors do not consider relative location information of extracted interesting points to guarantee rotation invariance. Also, since they use gray image of original color image, they do not use the color information of images, either. In this paper, we propose a method for improving matching performance of SURF descriptor using the color and relative location information of interest points. The location information is built from the angles between the line connecting the centers of interest points and the orientation line constructed for the center of each interest points. For the color information, color histogram is constructed for the region of each interest point. We show the performance of our scheme through experiments.

• Journal of Digital Contents Society
• /
• v.12 no.3
• /
• pp.279-289
• /
• 2011

The latest hardware and software techniques are combined to give safe walking guidance and convenient service of realtime walking assistance system for visually impaired person. This system consists of obstacle detection and perception, place recognition, and sign recognition for pedestrian can safely walking to arrive at their destination. In this paper, we exploit the sign object detection system in subway station for sign recognition that one of the important factors of walking assistance system. This paper suggest the adaptive feature map that can be robustly extract the sign object region from complexed environment with light and noise. And recognize a sign using fast zernike moment features which is invariant under translation, rotation and scale of object during walking. We considered three types of signs as arrow, restroom, and exit number and perform the training and recognizing steps through adaboost classifier. The experimental results prove that our method can be suitable and stable for real-time system through yields on the average 87.16% stable detection rate and 20 frame/sec of operation time for three types of signs in 5000 images of sign database.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.3
• /
• pp.630-638
• /
• 2016

In this paper, a feature based panorama image generation algorithm using FAST(Features from Accelerated Segment Test) method that is faster than SIFT(Scale Invariant Feature Transform) and SURF(Speeded Up Robust Features) is proposed. Cylindrical projection is performed to generate natural panorama images with numerous images as input. The occurred error can be minimized by applying RANSAC(Random Sample Consensus) for the matching process. When we synthesize numerous images acquired from different camera angles, we use blending techniques to compensate the distortions by the heterogeneity of border line. In that way, we could get more natural synthesized panorama image. The proposed algorithm can generate natural panorama images regardless the order of input images and tilted images. In addition, the image matching can be faster than the conventional method. As a result of the experiments, distortion was corrected and natural panorama image was generated.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1057-1068
• /
• 2022

This paper compares the combination performance of feature point-based matching algorithms as a study to confirm the matching possibility between image taken by a user and a virtual texture image with the goal of developing mobile-based real-time image positioning technology. The feature based matching algorithm includes process of extracting features, calculating descriptors, matching features from both images, and finally eliminating mismatched features. At this time, for matching algorithm combination, we combined the process of extracting features and the process of calculating descriptors in the same or different matching algorithm respectively. V-World 3D desktop was used for the virtual indoor texture image. Currently, V-World 3D desktop is reinforced with details such as vertical and horizontal protrusions and dents. In addition, levels with real image textures. Using this, we constructed dataset with virtual indoor texture data as a reference image, and real image shooting at the same location as a target image. After constructing dataset, matching success rate and matching processing time were measured, and based on this, matching algorithm combination was determined for matching real image with virtual image. In this study, based on the characteristics of each matching technique, the matching algorithm was combined and applied to the constructed dataset to confirm the applicability, and performance comparison was also performed when the rotation was additionally considered. As a result of study, it was confirmed that the combination of Scale Invariant Feature Transform (SIFT)'s feature and descriptor detection had the highest matching success rate, but matching processing time was longest. And in the case of Features from Accelerated Segment Test (FAST)'s feature detector and Oriented FAST and Rotated BRIEF (ORB)'s descriptor calculation, the matching success rate was similar to that of SIFT-SIFT combination, while matching processing time was short. Furthermore, in case of FAST-ORB, it was confirmed that the matching performance was superior even when 10° rotation was applied to the dataset. Therefore, it was confirmed that the matching algorithm of FAST-ORB combination could be suitable for matching between virtual texture image and real image.