• Title/Summary/Keyword: Motion gradient histogram

Search Result 12, Processing Time 0.019 seconds

A Pedestrian Collision Warning System using a Fuzzy Logic (퍼지로직을 이용한 보행자 충돌 경고 시스템)

  • Kim, Yang Ho;Kim, Kwangsoo;Kwak, Sooyeong
    • Journal of Broadcast Engineering
    • /
    • v.20 no.3
    • /
    • pp.440-448
    • /
    • 2015
  • A pedestrian collision warning system which makes a judgement of pedestrian's intention to help avoiding hitting accidents is proposed. This system uses the image sequences obtained from a car black box as well as vehicle's speed obtained from a GPS. It detects pedestrians, if any, based on the Histogram of Gradient method and extracts several information such as the pedestrian's relative positions, the direction of motion vectors, and distance between vehicle and pedestrian . A fuzzy logic based on these extracted information is applied to analyze the pedestrian's safety levels. When the safety level is determined to be danger, an alarm is triggered to the driver. The performance of the proposed algorithm is tested under various driving scenarios, which shows it works successfully in real-time.

Effects of Arc Number or Rotation Range upon Dose Distribution at RapidArc Planning for Liver Cancer (간암환자를 대상으로 한 래피드아크 치료계획에서 아크수 및 회전범위가 선량분포에 미치는 영향)

  • Park, Hae-Jin;Kim, Mi-Hwa;Chun, Mi-Son;Oh, Yeong-Teak;Suh, Tae-Suk
    • Progress in Medical Physics
    • /
    • v.21 no.2
    • /
    • pp.165-173
    • /
    • 2010
  • In this paper, we evaluated the performance of 3D CRT, IMRT and three kind of RA plannings to investigate the clinical effect of RA with liver cancer case. The patient undergoing liver cancer of small volume and somewhat constant motion were selected. We performed 3D CRT, IMRT and RA plannings such as 2RA, limited triple arcs (3RA) and 3MRA with Eclipse version 8.6.15. The same dose volume objectives were defined for only CTV, PTV and body except heart, liver and partial body in IMRT and RA plannings. The steepness of dose gradient around tumor was determined by the Normal Tissue Objective function with the same parameters in place of respective definitions of dose volume objectives for the normal organs. The approach between the defined dose constraints and the practical DVH of CTV, PTV and Body was the best in 3MRA and the worst in IMRT. The DVHs were almost the same among RAs. Plans were evaluated using Conformity Index (CI), Homogeneity Index (HI) and Quality of coverage (QoC) by RTOG after prescription with dose level surrounding 98% of PTV in the respective plans. As a result, 3MRA planning showed the better favorable indices than that of the others and achieved the lowest MUs. In this study, RA planning is a technique that is possible to obtain the faster and better dose distribution than 3D CRT or IMRT techniques. Our result suggest that 3MRA planning is able to reduce the MUs further, keeping a similar or better targer dose homogeneity, conformity and sparing normal tissue than 2RA or 3RA.