• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• 한국인공지능학회지
• /
• 제11권3호
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• ETRI Journal
• /
• 제30권5호
• /
• pp.663-673
• /
• 2008

The multi-scenario topology of multi-channel hybrid ubiquitous sensor networks (USNs) is studied and a novel link auto-diversity cross-layer cooperative scheduling scheme is proposed in this paper. The proposed scheme integrates the attributes of the new performance evaluation link auto-diversity air-time metric and the topology space in the given multi-scenario. The proposed scheme is compared with other schemes, and its superiority is demonstrated through simulations. The simulation results show that relative energy consumption, link reception probability, and end-to-end blocking probability are improved. The addressing ratio of success with unchanged parameters and external information can be increased. The network can tolerate more hops to support reliable transportation when the proposed scheme is implemented. Moreover, the scheme can make the network stable. Therefore, the proposed scheme can enhance the average rate performance of the hybrid USN and stabilize the outage probability.

• International journal of advanced smart convergence
• /
• 제7권2호
• /
• pp.95-100
• /
• 2018

In this paper, we propose a binarized multi-scale module to accelerate the speed of the pose estimating deep neural network. Recently, deep learning is also used for fine-tuned tasks such as pose estimation. One of the best performing pose estimation methods is based on the usage of two neural networks where one computes the heat maps of the body parts and the other computes the part affinity fields between the body parts. However, the convolution filtering with a large kernel filter takes much time in this model. To accelerate the speed in this model, we propose to change the large kernel filters with binarized multi-scale modules. The large receptive field is captured by the multi-scale structure which also prevents the dropdown of the accuracy in the binarized module. The computation cost and number of parameters becomes small which results in increased speed performance.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권6호
• /
• pp.736-744
• /
• 2016

Network on chip (NoC) is an emerging technology in the field of multi core interconnection architecture. The routers plays an essential components of Network on chip and responsible for packet delivery by selecting shortest path between source and destination. State-of-the-art NoC designs used routing table to find the shortest path and supports four ports for packet transfer, which consume high power consumption and degrades the system performance. In this paper, the multi port multi core router architecture is proposed to reduce the power consumption and increasing the throughput of the system. The shared buffer is employed between the multi ports of the router architecture. The performance of the proposed router is analyzed in terms of power and current consumption with conventional methods. The proposed system uses Modelsim software for simulation purposes and Xilinx Project Navigator for synthesis purposes. The proposed architecture consumes 31 mW on CPLD XC2C64A processor.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.279-282
• /
• 2003

This paper proposes a medium-access control(MAC) protocol designed for wireless multi-hop sensor networks which is used for connecting physical world and cyber computing space. Wireless multi-hop sensor networks use battery-operated computing and sensing device. We expect sensor networks to be deployed in an ad hoc fashion, with nodes remaining inactive for long time, but becoming suddenly active when specific event is detected. These characteristics of multi-hop sensor networks and applications motivate a MAC that is different from traditional wireless MACs about power conservation scheme, such as IEEE 802.11. Proposed MAC uses a few techniques to reduce energy consumption. Result show that proposed MAC obtains more energy sayings.

• 한국컴퓨터정보학회논문지
• /
• 제24권1호
• /
• pp.167-178
• /
• 2019

In this paper, we study the multi-objectives vehicle and drone routing problem with time windows, MOVDRPTW for short, which is defined in an urban delivery network. We consider the dual modal delivery system consisting of drones and vehicles. Drones are used as a complement to the vehicle and operate in a point to point manner between the depot and the customer. Customers make various requests. They prefer to receive delivery services within the predetermined time range and some customers require fast delivery. The purpose of this paper is to investigate the effectiveness of the delivery strategy of using drones and vehicles together with a multi-objective measures. As experiment datasets, we use the instances generated based on actual courier delivery data. We propose a hybrid multi-objective evolutionary algorithm for solving MOVDRPTW. Our results confirm that the vehicle-drone mixed strategy has 30% cost advantage over vehicle only strategy.

• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.39-47
• /
• 2023

This study compares various transformation techniques for multifocus image fusion. Multi-focus image fusion is a procedure of merging multiple images captured at unalike focus distances to produce a single composite image with improved sharpness and clarity. In this research, the purpose is to compare different popular frequency domain approaches for multi-focus image fusion, such as Discrete Wavelet Transforms (DWT), Stationary Wavelet Transforms (SWT), DCT-based Laplacian Pyramid (DCT-LP), Discrete Cosine Harmonic Wavelet Transform (DC-HWT), and Dual-Tree Complex Wavelet Transform (DT-CWT). The objective is to increase the understanding of these transformation techniques and how they can be utilized in conjunction with one another. The analysis will evaluate the 10 most crucial parameters and highlight the unique features of each method. The results will help determine which transformation technique is the best for multi-focus image fusion applications. Based on the visual and statistical analysis, it is suggested that the DCT-LP is the most appropriate technique, but the results also provide valuable insights into choosing the right approach.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제15권12호
• /
• pp.968-972
• /
• 2009

멀티 코어 프로세서는 현재 많은 고성능 서버에 적용되어 사용되고 있다. 최근 이들 서버는 점차 높은 네트워크 대역폭 활용을 요구하고 있다. 이러한 요구를 만족시키기 위해서는 멀티 코어를 효율적으로 활용하여 네트워크 처리율을 향상시키는 방안이 필요하다. 그러나 현재 운영체제들은 멀티 코어 시스템을 멀티 프로세서 환경과 거의 동일하게 다루고 있으며 아직 멀티 코어의 고유 특성을 고려한 성능 최적화 시도는 미흡한 상태이다. 이러한 문제를 해결하기 위해서 본 논문에서는 멀티 코어의 특성을 최대한으로 고려하여 프로세스 스케줄링을 결정함으로써 통신 성능을 향상시키는 방안에 대해서 연구한다. 제안되는 프로세스 스케줄링은 멀티 코어 프로세서의 캐쉬 구조, 프로세스의 통신 집중도, 그리고 각 코어의 부하를 기반으로 해당 프로세스에게 최적의 코어를 결정하고 스케줄링한다. 제안된 기법은 리눅스 커널에 구현되었으며 측정 결과는 최신 리눅스 커널의 네트워크 처리율을 20%까지 향상시켰으며 프로세서 자원은 55% 더 절약할 수 있음을 보인다.

• 한국컴퓨터정보학회논문지
• /
• 제27권11호
• /
• pp.29-38
• /
• 2022

본 논문에서는 멀티 센서가 장착된 스마트 인솔로 측정한 보행 데이터에 대해 앙상블 딥러닝 네트워크를 이용하여 보행의 타입을 분류하는 시스템을 제안한다. 보행 타입 분류 시스템은 인솔에 의해 측정된 데이터를 정규화하는 부분과 딥러닝 네트워크를 이용하여 보행의 특징을 추출하는 부분, 그리고 추출된 특징을 입력으로 보행의 타입을 분류하는 부분으로 구성되어 있다. 서로 다른 특성을 가지는 CNN과 LSTM을 기반으로 하는 네트워크를 독립적으로 학습하여 두 종류의 보행 특징 맵을 추출하였으며, 각각의 분류 결과를 결합하여 최종적인 앙상블 네트워크의 분류 결과를 도출하였다. 20~30대 성인의 걷기, 뛰기, 빠르게 걷기, 계단 오르기와 내려가기, 언덕 오르기와 내려가기의 7종류의 보행에 대해, 스마트 인솔을 이용하여 실측한 멀티 센서 데이터를 제안한 앙상블 네트워크로 분류해 본 결과 90% 이상의 높은 분류율을 보이는 것을 확인하였다.