• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.21-29
• /
• 2020

Accurate estimation of human pose relies on backbone method in which its role is to extract feature map. Up to dated, the method of backbone feature extraction is conducted by the plain convolutional neural networks named by CNN and the residual neural networks named by Resnet, both of which have various architectures and performances. The CNN family network such as VGG which is well-known as a multiple stacked hidden layers architecture of deep learning methods, is base and simple while Resnet which is a bottleneck layers architecture yields fewer parameters and outperform. They have achieved inspired results as a backbone network in human pose estimation. However, they were used then followed by different pose estimation networks named by pose parsing module. Therefore, in this paper, we present a comparison between the plain CNN family network (VGG) and bottleneck network (Resnet) as a backbone method in the same pose parsing module. We investigate their performances such as number of parameters, loss score, precision and recall. We experiment them in the bottom-up method of human pose estimation system by adapted the pose parsing module of openpose. Our experimental results show that the backbone method using VGG network outperforms the Resent network with fewer parameter, lower loss score and higher accuracy of precision and recall.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.31-37
• /
• 2020

Last year's Goseong-Sokcho forest fires have highlighted the limitations of extinguishing work for night-time forest fire and the importance of quick identification for information on the spread of forest fire. However, it is not easy to find services that take into account the characteristics of forest fires, as most existing disaster-related mobile applications and research assume various disaster situations rather than just forest fire situations. Therefore, a system that can provide information quickly is needed, taking into account the characteristics of forest fires and the limitations of extinguishing work. In this paper, we propose evacuation route guidance services that bypass areas where fire has already spread, supplement existing methods of extinguishing work, and provide general information on forest fire situations in real time, by putting drones into forest fire situations. It has been implemented to automate image analysis using the Rekognition service of Amazon Web Service (AWS), and the results of fire detection and the T Map API guide the evacuation path. It is expected that the results of this paper will allow efficient and rapid rescue and extinguishing work to be carried out, and further reduce the damage of human life caused by forest fires.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.3
• /
• pp.35-41
• /
• 2010

In this paper, an Android based ubiquitous interface for controlling service robots is presented. The robot server captures the images for the front view of the robot, makes a map of the environment and its position, produces a graphic image of its pose, and then transmits them to the Android client. The Android client displays them in the LCD panel and transfers control information obtained from touched buttons to the server. In the interface environment, we implement remote moving mode, autonomous moving mode, and remote operation mode for being used for versatile operability to the robot with limited screen of the smart phone. Experimental results show the implementation of the proposed interface in Android installed on Motoroi to control a service robot, and demonstrate its feasibility.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.57-62
• /
• 2017

Recently, the use of electronic control units in vehicle has increased. The ECUs are connected to in vehicle networks to process a large amount of information. In this paper, for an actuator that is interconnected to CAN and FlexRay, a FlexRay-CAN gateway is presented and a data packing algorithm with a bisection method of a FlexRay slot is proposed. And, a network based actuator control system and packing map is implemented. With the proposed packing method, contact force sensor data are transferred within the maximum allowed delay to ensure the stability. The proposed method is useful for control of distributed system.

• International Journal of Internet, Broadcasting and Communication
• /
• v.10 no.3
• /
• pp.136-145
• /
• 2018

The disaster monitoring technique by combination of the measurement method and the fine precision of the sensor collecting the satellite-based information that can determine the displacement space is available in a variety of diagnostic information and the GIS/GNSS by first sensor it is being requested from them. Be large and that the facility is operated nationally distributed torsional displacement of the terrain and facilities caused by such natural disasters progress of various environmental factors and the surroundings. To diagnose this spatial information, which contains the various sensors and instruments tracks the precise fine displacement of the main construction structures and the first reference in the Geospatial or more three-dimensional detailed available map and location information using the installed or the like bridges and tunnels produced to a USN/IoT change at any time, by combining the various positioning analysis of mm-class for the facility main area observed is required to constantly in the real time information of the USN/IoT environment sensor, and to utilize this as a precise fine positioning information by UAV/Drone to the precise fine displacement of the semi-permanent infrastructures. It managed to be efficient management by use of new technologies, analyzing the results presented to a method capable of real-time monitoring for a large structure or facility to construction disaster prevention.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.523-532
• /
• 2002

Recently, with the wide spread of the Internet and development of wireless network technology, it has now become possible to access web pages anytime, anywhere through devices with small display such as PDA But, since most existing web pages are optimized for desktop computers, browsing web pages on the small screen through wireless network requires more scrolling and longer loading time. In this paper, we propose a page reconstruction scheme called PageMap to make it feasible to navigate existing web pages through small screen devices even on the wireless connection. Reconstructed pages reduce the file and page size and thus eventually reduce resource requirements. We have Implemented a prototype system and performed several experiments for typical web sites. We report some of the results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3352-3365
• /
• 2012

Group key agreement (GKA) is a cryptographic primitive allowing two or more users to negotiate a shared session key over public networks. Wu et al. recently introduced the concept of asymmetric GKA that allows a group of users to negotiate a common public key, while each user only needs to hold his/her respective private key. However, Wu et al.'s protocol can not resist active attacks, such as fabrication. To solve this problem, Zhang et al. proposed an authenticated asymmetric GKA protocol, where each user is authenticated during the negotiation process, so it can resist active attacks. Whereas, Zhang et al.'s protocol needs a partially trusted certificate authority to issue certificates, which brings a heavy certificate management burden. To eliminate such cost, Zhang et al. constructed another protocol in identity-based setting. Unfortunately, it suffers from the so-called key escrow problem. In this paper, we propose the certificateless authenticated asymmetric group key agreement protocol which does not have certificate management burden and key escrow problem. Besides, our protocol achieves known-key security, unknown key-share security, key-compromise impersonation security, and key control security. Our simulation based on the pairing-based cryptography (PBC) library shows that this protocol is efficient and practical.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3942-3961
• /
• 2019

Recently, the models of deep super-resolution networks can successfully learn the non-linear mapping from the low-resolution inputs to high-resolution outputs. However, for large scaling factors, this approach has difficulties in learning the relation of low-resolution to high-resolution images, which lead to the poor restoration. In this paper, we propose Stage Generative Adversarial Networks (Stage-GAN) with semantic maps for image super-resolution (SR) in large scaling factors. We decompose the task of image super-resolution into a novel semantic map based reconstruction and refinement process. In the initial stage, the semantic maps based on the given low-resolution images can be generated by Stage-0 GAN. In the next stage, the generated semantic maps from Stage-0 and corresponding low-resolution images can be used to yield high-resolution images by Stage-1 GAN. In order to remove the reconstruction artifacts and blurs for high-resolution images, Stage-2 GAN based post-processing module is proposed in the last stage, which can reconstruct high-resolution images with photo-realistic details. Extensive experiments and comparisons with other SR methods demonstrate that our proposed method can restore photo-realistic images with visual improvements. For scale factor ${\times}8$, our method performs favorably against other methods in terms of gradients similarity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1795-1811
• /
• 2019

In order to achieve rapid and accurate detection of vehicle objects in complex traffic conditions, we propose a novel vehicle detection method. Firstly, more contextual and small-object vehicle information can be obtained by our Joint Feature Network (JFN). Secondly, our Evolved Region Proposal Network (EPRN) generates initial anchor boxes by adding an improved version of the region proposal network in this network, and at the same time filters out a large number of false vehicle boxes by soft-Non Maximum Suppression (NMS). Then, our Mask Network (MaskN) generates an example that includes the vehicle occlusion, the generator and discriminator can learn from each other in order to further improve the vehicle object detection capability. Finally, these candidate vehicle detection boxes are optimized to obtain the final vehicle detection boxes by the Fine-Tuning Network(FTN). Through the evaluation experiment on the DETRAC benchmark dataset, we find that in terms of mAP, our method exceeds Faster-RCNN by 11.15%, YOLO by 11.88%, and EB by 1.64%. Besides, our algorithm also has achieved top2 comaring with MS-CNN, YOLO-v3, RefineNet, RetinaNet, Faster-rcnn, DSSD and YOLO-v2 of vehicle category in KITTI dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3121-3143
• /
• 2019

Segmentation plays an important role in the field of image processing and computer vision. Intuitionistic fuzzy C-means (IFCM) clustering algorithm emerged as an effective technique for image segmentation in recent years. However, standard fuzzy C-means (FCM) and IFCM algorithms are sensitive to noise and initial cluster centers, and they ignore the spatial relationship of pixels. In view of these shortcomings, an improved algorithm based on IFCM is proposed in this paper. Firstly, we propose a modified non-membership function to generate intuitionistic fuzzy set and a method of determining initial clustering centers based on grayscale features, they highlight the effect of uncertainty in intuitionistic fuzzy set and improve the robustness to noise. Secondly, an improved nonlinear kernel function is proposed to map data into kernel space to measure the distance between data and the cluster centers more accurately. Thirdly, the local spatial-gray information measure is introduced, which considers membership degree, gray features and spatial position information at the same time. Finally, we propose a new measure of intuitionistic fuzzy entropy, it takes into account fuzziness and intuition of intuitionistic fuzzy set. The experimental results show that compared with other IFCM based algorithms, the proposed algorithm has better segmentation and clustering performance.