• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.728-741
• /
• 2015

Stereo vision has become an important technical issue in the field of 3D imaging, machine vision, robotics, image analysis, and so on. The depth map extraction from stereo video is a key technology of stereoscopic 3D video requiring stereo correspondence algorithms. This is the matching process of the similarity measure for each disparity value, followed by an aggregation and optimization step. Since it requires a lot of computational power, there are significant speed-performance advantages when exploiting parallel processing available on processors. In this situation, multi-core CPU may allow many parallel programming technologies to be realized in users computing devices. This paper proposes parallel implementations for calculating disparity map using a shared memory programming and exploiting the streaming SIMD extension technology. By doing so, we can take advantage both of the hardware and software features of multi-core processor. For the performance evaluation, we implemented a parallel SAD algorithm with OpenMP and SSE2. Their processing speeds are compared with non parallel version on stereoscopic streaming video. The experimental results show that both technologies have a significant effect on the performance and achieve great improvements on processing speed.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.385-392
• /
• 2016

Market analysis for a business plain is required for the success in the modern world. Most important part in this analysis is pedestrian traffic counting. A traditional way for this is counting it in person. However, it causes high labor costs and mistakes. This paper proposes an automatic algorithm to measure the pedestrian traffic count using images with webcam. The proposed algorithm is composed of two parts: pedestrian area detection and movement tracking. In pedestrian area detection, moving blobs are extracted and pedestrian areas are detected using HoG features and Adaboost algorithm. In movement tracking, multi-level matching and false positive removal are applied to track pedestrian areas and count the pedestrian traffic. Multi-level matching is composed of 3 steps: (1) the similarity calculation between HoG area, (2) the similarity calculation of the estimated position with Kalman filtering, and (3) the similarity calculation of moving blobs in the pedestrian area detection. False positive removal is to remove invalid pedestrian area. To analyze the performance of the proposed algorithm, a comparison is performed with the previous human area detection and tracking algorithm. The proposed algorithm achieves 83.6% accuracy in the pedestrian traffic counting, which is better than the previous algorithm over 11%.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.55-66
• /
• 2023

Community portraits can deeply explore the characteristics of community structures and describe the personalized knowledge needs of community users, which is of great practical significance for improving community recommendation services, as well as the accuracy of resource push. The current community portraits generally have the problems of weak perception of interest characteristics and low degree of integration of topic information. To resolve this problem, the reader community portrait method based on the thematic and timeliness characteristics of interest labels (UIT) is proposed. First, community opinion leaders are identified based on multi-feature calculations, and then the topic features of their texts are identified based on the LDA topic model. On this basis, a semantic mapping including "reader community-opinion leader-text content" was established. Second, the readers' interest similarity of the labels was dynamically updated, and two kinds of tag parameters were integrated, namely, the intensity of interest labels and the stability of interest labels. Finally, the similarity distance between the opinion leader and the topic of interest was calculated to obtain the dynamic interest set of the opinion leaders. Experimental analysis was conducted on real data from the Douban reading community. The experimental results show that the UIT has the highest average F value (0.551) compared to the state-of-the-art approaches, which indicates that the UIT has better performance in the smooth time dimension.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.881-895
• /
• 2023

Modern image inpainting techniques based on deep learning have achieved remarkable performance, and more and more people are working on repairing more complex and larger missing areas, although this is still challenging, especially for facial image inpainting. For a face image with a huge missing area, there are very few valid pixels available; however, people have an ability to imagine the complete picture in their mind according to their subjective will. It is important to simulate this capability while maintaining the identity features of the face as much as possible. To achieve this goal, we propose a three-stage network model, which we refer to as the identity and structure feature refinement network (ISFRNet). ISFRNet is based on 1) a pre-trained pSp-styleGAN model that generates an extremely realistic face image with rich structural features; 2) a shallow structured network with a small receptive field; and 3) a modified U-net with two encoders and a decoder, which has a large receptive field. We choose structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), L1 Loss and learned perceptual image patch similarity (LPIPS) to evaluate our model. When the missing region is 20%-40%, the above four metric scores of our model are 28.12, 0.942, 0.015 and 0.090, respectively. When the lost area is between 40% and 60%, the metric scores are 23.31, 0.840, 0.053 and 0.177, respectively. Our inpainting network not only guarantees excellent face identity feature recovery but also exhibits state-of-the-art performance compared to other multi-stage refinement models.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.10
• /
• pp.958-964
• /
• 2015

In this paper, an object recognition method based on the depth information from the RGB-D camera, Xtion, is proposed for an indoor mobile robot. First, the RANdom SAmple Consensus (RANSAC) algorithm is applied to the point cloud obtained from the RGB-D camera to detect and remove the floor points. Next, the removed point cloud is classified by the k-means clustering method as each object's point cloud, and the normal vector of each point is obtained by using the k-d tree search. The obtained normal vectors are classified by the trained multi-layer perceptron as 18 classes and used as features for object recognition. To distinguish an object from another object, the similarity between them is measured by using Levenshtein distance. To verify the effectiveness and feasibility of the proposed object recognition method, the experiments are carried out with several similar boxes.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.416-422
• /
• 2021

Due to the large differences in human activity within classes, the large similarity between classes, and the problems of visual angle and occlusion, it is difficult to extract features manually, and the detection rate of human behavior is low. In order to better solve these problems, an improved Faster R-CNN-based detection algorithm is proposed in this paper. It achieves multi-object recognition and localization through a second-order detection network, and replaces the original feature extraction module with Dense-Net, which can fuse multi-level feature information, increase network depth and avoid disappearance of network gradients. Meanwhile, the proposal merging strategy is improved with Soft-NMS, where an attenuation function is designed to replace the conventional NMS algorithm, thereby avoiding missed detection of adjacent or overlapping objects, and enhancing the network detection accuracy under multiple objects. During the experiment, the improved Faster R-CNN method in this article has 84.7% target detection result, which is improved compared to other methods, which proves that the target recognition method has significant advantages and potential.

• Mycobiology
• /
• v.50 no.5
• /
• pp.302-316
• /
• 2022

Many Apiospora species have been isolated from bamboo plants - to date, 34 bambusicolous Apiospora species have been recorded. They are known as saprophytes, endophytes, and plant pathogens. In this study, 242 bambusicolous Apiospora were isolated from various bamboo materials (branches, culms, leaves, roots, and shoots) and examined using DNA sequence similarity based on the internal transcribed spacer, 28S large subunit ribosomal RNA gene, translation elongation factor 1-alpha, and beta-tubulin regions. Nine Apiospora species (Ap. arundinis, Ap. camelliae-sinensis, Ap. hysterina, Ap. lageniformis sp. nov., Ap. paraphaeosperma, Ap. pseudohyphopodii sp. nov., Ap. rasikravindrae, Ap. saccharicola, and Ap. sargassi) were identified via molecular analysis. Moreover, the highest diversity of Apiospora was found in culms, and the most abundant species was Ap. arundinis. Among the nine Apiospora species, two (Ap. hysterina and Ap. paraphaeosperma) were unrecorded in Korea, and the other two species (Ap. lageniformis sp. nov. and Ap. pseudohyphopodii sp. nov.) were potentially novel species. Here, we describe the diversity of bambusicolous Apiospora species in bamboo organs, construct a multi-locus phylogenetic tree, and delineate morphological features of new bambusicolous Apiospora in Korea.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.67-75
• /
• 2009

Multi-layered video coding that provides scalability across the visual content has emerged for easily adaptive service over current heterogeneous network. However, the network is still error prone environment so that video service may suffer packet loss or erroneous decoding of the video. Especially distortion caused by the burst error may propagate to several pictures until intra refreshing, which will raise a terrific degradation of picture quality. To overcome the problem at terminal independently, we propose a new error concealment algorithm for the multi-layered video coding. The proposed method uses the similarity of between layers in the multi-layered video coding and POCS (Projections Onto Convex Sets) which is a powerful error concealment tool, but heavily dependent on initial values. To find adequate initial value which can reduce iteration times as well as achieve high performance, we took consideration into both features of layered approach coding and the correlation in neighbor blocks. The simulation results show that the proposed concealment method works well.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.6
• /
• pp.485-494
• /
• 2017

This study focuses on automatic image registration between multiple IR images using simple preprocessing method and modified local feature extraction algorithm. The input images were preprocessed by using the median and absolute value after histogram equalization, and it could be effectively applied to reduce the brightness difference value between images by applying the similarity of extracted features to the concept of angle instead of distance. The results were evaluated using visual and inverse RMSE methods. The features that could not be achieved by the existing local feature extraction technique showed high image matching reliability and application convenience. It is expected that this method can be used as one of the automatic registration methods between multi-sensor images under specific conditions.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.48-57
• /
• 2007

Eye localization is necessary for face recognition and related application areas. Most of eye localization algorithms reported thus far still need to be improved about precision and computational time for successful applications. In this paper, we propose an improved eye localization method based on multi-scale Gator feature vector models. The proposed method first tries to locate eyes in the downscaled face image by utilizing Gabor Jet similarity between Gabor feature vector at an initial eye coordinates and the eye model bunch of the corresponding scale. The proposed method finally locates eyes in the original input face image after it processes in the same way recursively in each scaled face image by using the eye coordinates localized in the downscaled image as initial eye coordinates. Experiments verify that our proposed method improves the precision rate without causing much computational overhead compared with other eye localization methods reported in the previous researches.