<listing id="kephd"></listing>
<tt id="kephd"></tt>

  • <label id="kephd"></label>
    <meter id="kephd"></meter>

    云南民族大學學報(自然科學版)

    2019, v.28;No.118(06) 624-628

    [打印本頁] [關閉]
    本期目錄(Current Issue) | 過刊瀏覽(Past Issue) | 高級檢索(Advanced Search)

    基于YOLO和排斥力損失函數的行人檢測方法
    A pedestrian detection method combining YOLO and repulsion loss

    周莉莉;段鵬;葉智慧;張靜敏;
    ZHOU Li-li;DUAN Peng;YE Zhi-hui;ZHANG Jing-min;School of Mathematics and Computer Science, Yunnan Minzu University;

    摘要(Abstract):

    針對行人檢測受人體姿態復雜、光照變化、遮擋嚴重等影響,導致檢測效率和精度不高的問題,提出一種基于YOLO和排斥力損失函數的行人檢測方法.首先,對YOLO模型進行改進,主要是設置合適的預選框以及采用較大尺度的特征圖進行特征提取,從而提高其對小物體的檢測性能;然后,對排斥力損失函數進行改進,使其符合行人檢測的應用場景,為接下來的融合檢測提供新的損失函數;最后,將改進的YOLO和排斥力損失函數結合起來,利用YOLO模型速度快的特點提高運行速度,并利用排斥力損失函解決行人遮擋問題.在多個行人檢測數據集上的實驗結果表明:與其他算法相比,能夠更加快速準確地實現行人檢測.
    A pedestrian detection method combining YOLO and repulsion loss is proposed to solve the problem that pedestrian detection is affected by complex human body postures, illumination changes and severe occlusion, resulting in low detection efficiency and accuracy. Firstly, the improved YOLO model aims mainly to set the appropriate pre-selection box and feature extraction with larger scale feature maps to improve the detection performance of small objects. Then, the repulsion loss is improved to match the application scenario of pedestrian detection that provides a new loss function for the next fusion detection. Finally, the improved YOLO and the repulsion loss function are combined to improve the running speed by using the fast speed of YOLO, and the loss function is used to solve the pedestrian occlusion. The experimental results of occlusion problems on multiple pedestrian detection datasets show that this pedestrian detection can be implemented more quickly and accurately than other algorithms.

    關鍵詞(KeyWords): 行人檢測;YOLO;排斥力損失;融合檢測
    pedestrian detection;YOLO;repulsion loss;fusion detection

    Abstract:

    Keywords:

    基金項目(Foundation):

    作者(Author): 周莉莉;段鵬;葉智慧;張靜敏;
    ZHOU Li-li;DUAN Peng;YE Zhi-hui;ZHANG Jing-min;School of Mathematics and Computer Science, Yunnan Minzu University;

    Email:

    DOI:

    參考文獻(References):

    擴展功能
    本文信息
    服務與反饋
    本文關鍵詞相關文章
    本文作者相關文章
    中國知網
    分享
    免费资料大全