• Title/Summary/Keyword: 물체 인식 향상

Search Result 100, Processing Time 0.035 seconds

Design of Microstrip Patch Antenna using Inset-Fed Layered for Metallic Object in u-Port (U-항만 환경에서 금속부착을 위한 인셋 급전 마이크로패치 안테나 설계)

  • Choi, Yong-Seok;Seong, Hyeon-Kyeong
    • Journal of Satellite, Information and Communications
    • /
    • v.10 no.2
    • /
    • pp.80-85
    • /
    • 2015
  • In this paper, we present, an indstrial RFID layered microstrip patch antenna is designed using an inset feed method in order to improve recognition rates in a long distance as tags are attached to metal object by improving a problem of feeding power in fabricating metal tags and reducing effects of metallic object. The inset feed shows a distinctive characteristic that has no separation between emitters and feed lines differing from a structure with the conventional inductive coupling feed. This structure makes possible to produce a type that presents a low antenna height and enables impedance coupling for tag chips. Although it shows a difficulty in the impedance coupling due to increases in the parasite capacitance between a ground plane and an emitter in an antenna according to decreases in the height of a tag antenna, it may become a merit in designing the tag antenna because the antenna impedance can be determined as an inductive manner if a shorted structure is used for feeding power. Therefore, in this paper the microstrip patch antenna is designed as a modified type and applies the inset feed in order to reduce effects of metallic objects where the antenna is be attached. Also, the antenna uses a multi-layer structure that includes a metal plate between radiator and ground instead of using a single layer.

Real Time Face detection Method Using TensorRT and SSD (TensorRT와 SSD를 이용한 실시간 얼굴 검출방법)

  • Yoo, Hye-Bin;Park, Myeong-Suk;Kim, Sang-Hoon
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.9 no.10
    • /
    • pp.323-328
    • /
    • 2020
  • Recently, new approaches that significantly improve performance in object detection and recognition using deep learning technology have been proposed quickly. Of the various techniques for object detection, especially facial object detection (Faster R-CNN, R-CNN, YOLO, SSD, etc), SSD is superior in accuracy and speed to other techniques. At the same time, multiple object detection networks are also readily available. In this paper, among object detection networks, Mobilenet v2 network is used, models combined with SSDs are trained, and methods for detecting objects at a rate of four times or more than conventional performance are proposed using TensorRT engine, and the performance is verified through experiments. Facial object detector was created as an application to verify the performance of the proposed method, and its behavior and performance were tested in various situations.

A Strategy for improving Performance of Q-learning with Prediction Information (예측 정보를 이용한 Q-학습의 성능 개선 기법)

  • Lee, Choong-Hyeon;Um, Ky-Hyun;Cho, Kyung-Eun
    • Journal of Korea Game Society
    • /
    • v.7 no.4
    • /
    • pp.105-116
    • /
    • 2007
  • Nowadays, learning of agents gets more and more useful in game environments. But it takes a long learning time to produce satisfactory results in game. So, we need a good method to shorten the learning time. In this paper, we present a strategy for improving the learning performance of Q-learning with prediction information. It refers to the chosen action at each status in the Q-learning algorithm, It stores the referred value at the P-table of prediction module, and then it searches some values with high frequency at the table. The values are used to renew second compensation value from the Q-table. Our experiments show that our approach gets the efficiency improvement of average 9% after the middle point of learning experiments, and that the more actions in a status space, the higher performance.

  • PDF

Investigation on Construction Process and Efficiency of Underwater Construction Equipment for Rubble Mound Leveling works (수중 고르기 장비의 건설 공정 및 효율성 분석)

  • Won, Deokhee;Jang, In-Sung;Shin, Changjoo
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.17 no.5
    • /
    • pp.372-378
    • /
    • 2016
  • A mound was constructed to install a caisson and sofa blocks underwater. The mound riprap, which were of uniform grade, size, shape, and specific gravity, formed the foundation for the support superstructure. Also, rubble leveling works were performed before installing structures such as caissons. In this study, underwater construction equipment was developed with a remotely controlled operating system and underwater environment monitoring system for unmanned underwater rubble leveling work. The performance of the developed equipment was verified using on-land and underwater tests. In addition to the performance verification, the construction process and economic efficiency of the equipment should be checked before applying it to the real construction field for commercial purposes. In this paper, a construction process using the developed equipment was proposed and compared with the existing rubble leveling method. The results demonstrated that the new construction method has higher economic efficiency and safety than the existing construction method.

RTLS Implementations in Domestic Ports and Shipyards (항만 및 조선소에서의 RTLS 적용 방안)

  • Kang, Yang-Suk;Choi, Hyung-Rim;Kim, Hyun-Soo;Hong, Soon-Goo;Cho, Min-Je;Park, Jae-Young
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.12 no.2
    • /
    • pp.352-359
    • /
    • 2008
  • RTLS(Real Time Location Systems) is a technology that identifies a location of a target object and provides peat visibility at a work place. Unlike those of the overseas, domestic ports and shipyards have narrow work places and thus, the efficient utilization of these spaces is one of the most important considerations for improving productivity. Companies considering implementation of RTLS should understand its limitations or applicability. In this paper, problems of RTLS such as fading factors which were caused from the features of RF, and limitations caused from the preconditions of RTLS were explained. To overcome those problems, three types of solutions such as movable RTLS, semi-movable RTLS and combined RTLS with other technologies were suggested.

Robust Location Tracking Using a Double Layered Particle Filter (이중 구조의 파티클 필터를 이용한 강인한 위치추적)

  • Yun, Keun-Ho;Kim, Dai-Jin;Bang, Sung-Yang
    • Journal of KIISE:Software and Applications
    • /
    • v.33 no.12
    • /
    • pp.1022-1030
    • /
    • 2006
  • The location awareness is an important part of many ubiquitous computing systems, but a perfect location system does not exist yet in spite of many researches. Among various location tracking systems, we choose the RFID system due to its wide applications. However, the sensed RSSI signal is too sensitive to the direction of a RFID reader antenna, the orientation of a RFID tag, the human interference, and the propagation media situation. So, the existing location tracking method in spite of using the particle filter is not working well. To overcome this shortcoming, we suggest a robust location tracking method with a double layered structure, where the first layer coarsely estimates a tag's location in the block level using a regression technique or the SVM classifier and the second layer precisely computes the tag's location, velocity and direction using the particle filter technique. Its layered structure improves the location tracking performance by restricting the moving degree of hidden variables. Many extensive experiments show that the proposed location tracking method is so precise and robust to be a good choice for implementing the location estimation of a person or an object in the ubiquitous computing. We also validate the usefulness of the proposed location tracking method by implementing it for a real-time people monitoring system in a noisy and complicate workplace.

An Enhanced Mobile Object Tracking Method based on Range-hybrid for Low-Density USN Environment (저밀도 USN 환경을 위한 Range-hybrid 기반의 향상된 이동객체 추적기법)

  • Park, Jae-Bok;Cho, Gi-Hwan
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.47 no.2
    • /
    • pp.54-64
    • /
    • 2010
  • Localization is the most important feature in the sensor network environment because it is a basic element enabling people and things to aware the circumference environment. Existing localization methods can be categorized as either range-based or range-free. While range-based is known to be not suitable because of the irregularity of radio propagation and the additional device requirement. range-free is much appropriated for the resource constrained sensor network because it can actively locate by means of the communication radio. But its location accuracy is just depended on the density of circumference nodes; it is very low in low-density sensor network environment. This paper proposes a mobile object tracking method, named DRTS(Distributed Range-hybrid Tracking Scheme), with combining range-based and range-free. It is optimally making use of the location, communication range, and received signal strength from circumference nodes. Especially, it can greatly improve the mobile tracking accuracy by adapting a new prediction method, named EGP(Estimative Gird Points) into the proposed location estimation method. The simulation results show that our method outperforms the other localization and tracking methods in the tracking accuracy point of view.

The Effects of 4D-Frame Teaching upon Mathematically Gifted Elementary Students' Mathematical Creativity and Spatial Sense (4D 프레임 활용 학습이 초등 수학영재학생의 공간감각 및 수학적 창의성에 미치는 영향)

  • Lee, Ju Yong;Choi, Jae Ho
    • Education of Primary School Mathematics
    • /
    • v.16 no.1
    • /
    • pp.1-20
    • /
    • 2013
  • The aim of this study was to develop a gifted educational program in math-gifted class in elementary school using recently developed 4D-frame. This study identified how this program impacted on spatial sense and mathematical creativity for mathematically gifted students. The investigation attempted to contribute to the developments for the gifted educational program. To achieve the aim, the study analysed the 5 and 6th graders' figure learning contents from a revised version of the 2007 national curriculum. According to this analysis, twelve learning sections were developed on the basis of 4D-frame in the math-gifted educational program. The results of the study is as follows. First, a learning program using 4D-frame for spatial sense from mathematically gifted elementary school students was statistically significant. A sub-factor of spatial visualization called mental rotation and sub-factors of spatial orientations such as sense of distance and sense of spatial perception were statistically significant. Second, the learning program that uses 4D-frame for mathematical creativity was statistically significant. The sub-factors of mathematical creativity such as fluency, flexibility and originality were all statistically significant. Third, the manipulation properties of 4D-frame helped to understand the characteristics of various solid figures. Through the math discussions in the class, participants' error correction was promoted. The advantage of 4D-frame including easier manipulation helped participants' originality for their own sculpture. In summary, this found that the learning program using 4D-frame attributed to improve the spatial sense and mathematical creativity for mathematically gifted students in elementary school. These results indicated that the writers' learning program will help to develop the programs for the gifted education program in the future.

Saliency Attention Method for Salient Object Detection Based on Deep Learning (딥러닝 기반의 돌출 객체 검출을 위한 Saliency Attention 방법)

  • Kim, Hoi-Jun;Lee, Sang-Hun;Han, Hyun Ho;Kim, Jin-Soo
    • Journal of the Korea Convergence Society
    • /
    • v.11 no.12
    • /
    • pp.39-47
    • /
    • 2020
  • In this paper, we proposed a deep learning-based detection method using Saliency Attention to detect salient objects in images. The salient object detection separates the object where the human eye is focused from the background, and determines the highly relevant part of the image. It is usefully used in various fields such as object tracking, detection, and recognition. Existing deep learning-based methods are mostly Autoencoder structures, and many feature losses occur in encoders that compress and extract features and decoders that decompress and extend the extracted features. These losses cause the salient object area to be lost or detect the background as an object. In the proposed method, Saliency Attention is proposed to reduce the feature loss and suppress the background region in the Autoencoder structure. The influence of the feature values was determined using the ELU activation function, and Attention was performed on the feature values in the normalized negative and positive regions, respectively. Through this Attention method, the background area was suppressed and the projected object area was emphasized. Experimental results showed improved detection results compared to existing deep learning methods.

Development of Deep Learning Structure for Defective Pixel Detection of Next-Generation Smart LED Display Board using Imaging Device (영상장치를 이용한 차세대 스마트 LED 전광판의 불량픽셀 검출을 위한 딥러닝 구조 개발)

  • Sun-Gu Lee;Tae-Yoon Lee;Seung-Ho Lee
    • Journal of IKEEE
    • /
    • v.27 no.3
    • /
    • pp.345-349
    • /
    • 2023
  • In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.