• Title/Summary/Keyword: 사전에 정의 된 임계값

Search Result 2, Processing Time 0.03 seconds

Efficient Resource Allocation Scheme for Improving the Throughput in the PB/MC-CDMA System (PB/MC-CDMA 시스템에서 처리량 향상을 위한 효율적인 자원 할당 기법)

  • Lee, Kyujin;Seo, HyoDuck;Han, DooHee
    • Journal of Convergence Society for SMB
    • /
    • v.4 no.1
    • /
    • pp.1-6
    • /
    • 2014
  • PB/MC-CDMA is an efficient system which divides the whole frequency band into several blocks, unlike a conventional MC-CDMA system. We propose an efficient resource allocation scheme in Multi-Block PB/MC-CDMA (Partial Block Multi-Carrier Code Division Multiple Access). This system aims to improve frequency efficiency and maximize the total throughput while satisfying predefined threshold over various channel conditions. Through computer simulations, we confirm that the performance of the proposed system is more effective in terms of throughput.

  • PDF

Vehicle Headlight and Taillight Recognition in Nighttime using Low-Exposure Camera and Wavelet-based Random Forest (저노출 카메라와 웨이블릿 기반 랜덤 포레스트를 이용한 야간 자동차 전조등 및 후미등 인식)

  • Heo, Duyoung;Kim, Sang Jun;Kwak, Choong Sub;Nam, Jae-Yeal;Ko, Byoung Chul
    • Journal of Broadcast Engineering
    • /
    • v.22 no.3
    • /
    • pp.282-294
    • /
    • 2017
  • In this paper, we propose a novel intelligent headlight control (IHC) system which is durable to various road lights and camera movement caused by vehicle driving. For detecting candidate light blobs, the region of interest (ROI) is decided as front ROI (FROI) and back ROI (BROI) by considering the camera geometry based on perspective range estimation model. Then, light blobs such as headlights, taillights of vehicles, reflection light as well as the surrounding road lighting are segmented using two different adaptive thresholding. From the number of segmented blobs, taillights are first detected using the redness checking and random forest classifier based on Haar-like feature. For the headlight and taillight classification, we use the random forest instead of popular support vector machine or convolutional neural networks for supporting fast learning and testing in real-life applications. Pairing is performed by using the predefined geometric rules, such as vertical coordinate similarity and association check between blobs. The proposed algorithm was successfully applied to various driving sequences in night-time, and the results show that the performance of the proposed algorithms is better than that of recent related works.