• Title/Summary/Keyword: Detecting-efficiency

Search Result 421, Processing Time 0.037 seconds

Triangle Method for Fast Face Detection on the Wild

  • Malikovich, Karimov Madjit;Akhmatovich, Tashev Komil;ugli, Islomov Shahboz Zokir;Nizomovich, Mavlonov Obid
    • Journal of Multimedia Information System
    • /
    • v.5 no.1
    • /
    • pp.15-20
    • /
    • 2018
  • There are a lot of problems in the face detection area. One of them is detecting faces by facial features and reducing number of the false negatives and positions. This paper is directed to solve this problem by the proposed triangle method. Also, this paper explans cascades, Haar-like features, AdaBoost, HOG. We propose a scheme using 12-net, 24-net, 48-net to scan images and improve efficiency. Using triangle method for frontal pose, B and B1 methods for other poses in neural networks are proposed.

Trends on Object Detection Techniques Based on Deep Learning (딥러닝 기반 객체 인식 기술 동향)

  • Lee, J.S.;Lee, S.K.;Kim, D.W.;Hong, S.J.;Yang, S.I.
    • Electronics and Telecommunications Trends
    • /
    • v.33 no.4
    • /
    • pp.23-32
    • /
    • 2018
  • Object detection is a challenging field in the visual understanding research area, detecting objects in visual scenes, and the location of such objects. It has recently been applied in various fields such as autonomous driving, image surveillance, and face recognition. In traditional methods of object detection, handcrafted features have been designed for overcoming various visual environments; however, they have a trade-off issue between accuracy and computational efficiency. Deep learning is a revolutionary paradigm in the machine-learning field. In addition, because deep-learning-based methods, particularly convolutional neural networks (CNNs), have outperformed conventional methods in terms of object detection, they have been studied in recent years. In this article, we provide a brief descriptive summary of several recent deep-learning methods for object detection and deep learning architectures. We also compare the performance of these methods and present a research guide of the object detection field.

Sound Source Tracking Control of a Mobile Robot Using a Microphone Array (마이크로폰 어레이를 이용한 이동 로봇의 음원 추적 제어)

  • Han, Jong-Ho;Han, Sun-Sin;Lee, Jang-Myung
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.18 no.4
    • /
    • pp.343-352
    • /
    • 2012
  • To follow a sound source by a mobile robot, the relative position and orientation of the sound source from the mobile robot have been estimated using a microphone array. In this research, the difference among the traveling times of the sound source to each of three microphones has been used to calculate the distance and orientation of the sound source from the mobile robot which carries the microphone array. The cross-correlation between two signals has been applied for detecting the time difference between two signals, which provides reliable and precise value of the time difference comparing to the conventional methods. To generate the tracking direction to the sound source, fuzzy rules are applied and the results are used to control the mobile robot in a real-time. The efficiency of the proposed algorithm has been demonstrated through the real experiments comparing to the conventional approaches.

The Roughing Tool-Path Generation of Die-Cavity Shape Using the Drill (Drill을 이용한 Die-Cavity 형상의 황삭 가공 경로 생성)

  • Lim, P.;Lee, H. G;Yang, G. E.
    • Proceedings of the Korean Society of Precision Engineering Conference
    • /
    • 2001.04a
    • /
    • pp.398-401
    • /
    • 2001
  • This paper presents rough cutting pat고 drilling. This method has differences from conventional method which uses boundary curve by intersecting object to machine and each cutting plane. Die-cavity shape is drilled in z-map, we select various tool and remove much material in the short time. as a result, this method raise productivity. The major challenges in die-cavity pocketing include : 1)finding an inscribed circle for removing material of unmachined regions, 2) selecting optimal tool and efficiently arranging tool, 3) generating offset surface of shape, 4) determining machined width according to the selected tool, 5) detecting and removing unmachined regions, and 6) linking PJE(path-joining element). Conventional machining method calling contour-map is compared with drilling method using Z-map, for finding efficiency in the view of productivity.

  • PDF

Comparative Study on Detecting Methods for Total Coliform in Sewage Effluent (하수 방류수에서 대장균군의 검출방법의 비교)

  • Lee, Mi-Ae;Sung, Il-Wha
    • Journal of Environmental Health Sciences
    • /
    • v.33 no.5
    • /
    • pp.422-427
    • /
    • 2007
  • The purposes of this study were to investigate the concentration of total coliforms in sewage effluents during the period from August 2004 to October 2005. The removal efficiency range of multi-tube method and plate count method were $31.3{\sim}99.5%$ and $66.8{\sim}99.2%$, respectively. Though a correlation between the multi-tube method and the plate count method in the same sample is low, not only is an experimental procedure very simple, but the time required also is short. The seasonal correlation between methods showed more sensitive spring and summer than autumn and winter. So the study indicated plate count method can be used in rapid and reliance identification of total coliform more than the multi-tube method.

Obstacle Avoidance for Mobile Robots Using Predictive Polar Mapping (폴라 맵핑 예측기를 통한 이동로봇의 장애물 회피)

  • Kim, Young-Joong;Kim, Beom-Soo;Lim, Myo-Taeg
    • Proceedings of the KIEE Conference
    • /
    • 2004.07d
    • /
    • pp.2447-2449
    • /
    • 2004
  • This paper presents the predicted polar mapping that is to improve the efficiency of an unexpected moving obstacle detecting system. When the movement of the robot per a step becomes a bit large then static objects or background are detected as moving objects. Thus, the velocity of the robot becomes so slow. Therefore, to enlarge the movement of the robot, we propose the predicted polar mapping that predicts the polar mapped image after robot moves to be admissible. In order to verify experimentally our proposed procedure, we make several comparative tests in the corridor.

  • PDF

Design of Monolithically Integrated Vertical Cavity Laser with Depleted Optical Thyristor for Optically Programmable Gate Array (Optically Programmable Gate Array 구현을 위한 수직 공진형 완전공핍 광싸이리스터)

  • Choi, Woon-Kyung;Kim, Do-Gyun;Choi, Young-Wan
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.58 no.8
    • /
    • pp.1580-1584
    • /
    • 2009
  • We have theoretically analyzed the monolithic integration of vertical cavity lasers with depleted optical thyristor (VCL-DOT) structure and experimentally demonstrated optical logic gates such as AND-gate, OR-gate, and INVERTER implemented by VCL-DOT for an optical programmable gate array. The optical AND and OR gates have been realized by changing a input bias of the single VCL-DOTs and all kinds of optical logic functions are also implemented by adjusting an intensity of the reference input beams into the differential VCL-DOTs. To achieve the high sensitivity, high slope efficiency and low threshold current, a small active region of lasing part and a wide detecting area are simultaneously designed by using a selective oxidation process. The fabricated devices clearly show nonlinear s-shaped current-voltage characteristics and lasing characteristics of a low threshold current with 0.65 mA and output spectrum at 854 nm.

Multiple Pedestrians Detection and Tracking using Histogram and Color Information from a Moving Camera (이동 카메라 영상에서 히스토그램과 컬러 정보를 이용한 다수 보행자 검출 및 추적)

  • 임종석;곽현욱;김욱현
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.41 no.5
    • /
    • pp.193-202
    • /
    • 2004
  • This paper presents a novel histogram and color information based algorithm for detecting and tracking multiple pedestrians from a moving camera. In the proposed method, RGB color histogram is used to detect adjacent pedestrians and RGB mean value is used to track detected pedestrians. Therefore, our algorithm detect contiguous or a few occluded pedestrians and track in case pedestrian's shape change. The experimental results on our test sequences demonstrate the high efficiency of our method.

Application of Directional Wavelet to Ocean Wave Image Analysis (방향 웨이브렛을 적용한 해양파 이미지 분석)

  • Kwon S. H.;Lee H. S.;Park J. S.;Ha M. K.
    • Proceedings of the KSME Conference
    • /
    • 2002.08a
    • /
    • pp.377-380
    • /
    • 2002
  • This paper presents the results of a study investigating methods of interpretation of wave directionality based on wavelet transforms. Two-dimensional discrete wavelet was used for the analysis. The proposed scheme utilizes a single frame of ocean waves to detect their directionality. This fact is striking considering the fact that traditional methods require long time histories of ocean wave elevation measured at various locations. The developed schemes were applied to the data generated from numerical simulations and video images to test the efficiency of the proposed scheme in detecting the directionality of ocean waves.

  • PDF

The Abnormal Condition Monitoring of Rotary Compressor using Acoustic Emission (AE 신호를 이용한 회전형 압축기의 이상상태 감시)

  • Lee Kam-Gyu;Jung Ji-Hong;Kim Jeon-Ha;Kang Myung-Chang;Kim Jeong-Suk
    • Transactions of the Korean Society of Machine Tool Engineers
    • /
    • v.13 no.5
    • /
    • pp.118-123
    • /
    • 2004
  • The compressor has one of important roles in refrigeration cycle and it determines refrigeration efficiency and quality This paper aims to monitor rotary compressors for room air conditioners by using Acoustic Emission(AE) technique. The reliability of rotary compressors has been evaluated through visual inspection on them after long term test. This paper describes methods for acquisition and processing AE raw signal to monitor the state of rotary compressor. A detecting method of abnormal compressor in real time is suggested and special-purpose monitoring system which can be applied to automatic manufacturing line is developed using one-chip microprocessor at low cost.