计算机工程与应用 ›› 2019, Vol. 55 ›› Issue (20): 128-133.DOI: 10.3778/j.issn.1002-8331.1901-0318

• 模式识别与人工智能 • 上一篇    下一篇

改进YOLOV3算法在行人识别中的应用

葛雯,史正伟   

  1. 沈阳航空航天大学 电子与信息工程学院,沈阳 110136
  • 出版日期:2019-10-15 发布日期:2019-10-14

Application of Improved YOLOV3 Algorithm in Pedestrian Identification

GE Wen, SHI Zhengwei   

  1. College of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110136, China
  • Online:2019-10-15 Published:2019-10-14

摘要: 为了避免人与物体之间相互遮挡,对小目标检测不准确,以及复杂光照强度对行人检测的影响,针对这一问题,提出了一种多尺度聚类卷积神经网络MK-YOLOV3算法,来实现对行人的识别与检测。该算法是对YOLOV3进行改进,首先通过简单聚类对图像特征进行提取,得到相应的特征图,再通过抽样[K]-means聚类算法结合核函数确定锚点位置,以达到更好的聚类。针对小目标的浅层特征信息进行多尺度融合,提高小目标的检测效果。仿真结果验证了该算法在VOC数据集上对小目标识别的精度和速度上有较大提高,以及视频智能分析中有较高的召回率和精确度。

关键词: 行人检测, YOLOV3, 卷积神经网络, 特征图

Abstract: In order to avoid the mutual occlusion of human and objects, the inaccurate detection of small targets, and the influence of complex illumination intensity on pedestrian detection, this paper proposes an improvement of multi-scale clustering convolutional neural network MK-YOLOV3 algorithm to realize the recognition and detection of images. The algorithm improves the YOLOV3. Firstly, the image features are extracted by simple clustering, and the corresponding feature maps are obtained. Then the [K]-means clustering algorithm is combined with the kernel function to determine the anchor position to achieve better clustering. Multi-scale fusion is performed on the shallow feature information of small targets to improve the detection effect of small targets. The simulation results verify that the algorithm has a great improvement on the accuracy and speed of small target recognition on VOC dataset, and has a higher recall rate and accuracy in video intelligence analysis.

Key words: pedestrian detection, YOLOV3, convolutional neural network, feature map