基于双目相机与改进YOLOv3算法的果园行人检测与定位

被引:31
作者
景亮
王瑞
刘慧
沈跃
机构
[1] 江苏大学电气信息工程学院
关键词
果园环境; 行人检测定位; 双目相机; YOLOv3; 特征融合;
D O I
暂无
中图分类号
S24 [农业电气化与自动化]; TP391.41 [];
学科分类号
082804 ; 080203 ;
摘要
针对复杂果园环境中行人难以精确检测并定位的问题,提出了一种双目相机结合改进YOLOv3目标检测算法的行人障碍物检测和定位方法。该方法采用ZED双目相机采集左右视图,通过视差原理获取图像像素点的距离信息;将双目相机一侧的RGB图像作为用树形特征融合模块改进的YOLOv3算法的输入,得到行人障碍物在图像中的位置信息,结合双目相机获得的像素位置信息计算出相对于相机的三维坐标。用卡耐基梅隆大学国家机器人工程中心开放的果园行人检测数据集测试改进的YOLOv3算法,结果表明,准确率和召回率分别达到95.34%和91.52%,高于原模型的94.86%和90.19%,检测速度达到30.26 f/ms。行人检测与定位试验表明,行人障碍物的定位在深度距离方向平均相对误差为1.65%,最大相对误差为3.80%。该方法具有快速性和准确性,可以较好地实现果园环境中的行人检测与定位,为无人驾驶农机的避障决策提供依据。
引用
收藏
页码:34 / 39+25 +25
页数:7
相关论文
共 21 条
  • [1] The Pascal Visual Object Classes (VOC) Challenge
    Everingham, Mark
    Van Gool, Luc
    Williams, Christopher K. I.
    Winn, John
    Zisserman, Andrew
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2010, 88 (02) : 303 - 338
  • [2] Fast r-cnn. Girshick R. Proceedings of the IEEE International Conference on Computer Vision . 2015
  • [3] Faster R-CNN:towards real-time object detection with region proposal networks. Ren S,He K,Girshick R.et al. International Conference on Neural Information Processing Systems . 2015
  • [4] SSD:Single Shot MultiBox Detector. LIU W,ANGUELOV D,ERHAN D,et al. European Conference on Computer Vision 2016 . 2016
  • [5] YOLO9000:Better,Faster,Stronger. Redmon,J,Farhadi,A. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 2017
  • [6] Human activity recognition using mixture of heterogeneous features and sequential minimal optimization. Naveed H,Khan G,Khan AU, et al. International Journal of Machine Learning and Cybernetics . 2019
  • [7] You Only Look Once:Unified,Real-Time Object Detection. Redmon J,Divvala S,Girshick R,et al. Computer Vision and Pattern Recognition . 2016
  • [8] Rich feature hierarchies for accurate object detection and semantic segmentation. Girshick R,Donahue J,Darrell T, et al. Computer Vision and Pattern Recognition (CVPR),2014 IEEE Conference on . 2014
  • [9] Tree-structured kronecker convolutional network for semantic segmentation. WU T,TANG S,ZHANG R,et al. 2019IEEE International Conference on Multimedia and Expo (ICME) . 2019
  • [10] Feature pyramid networks for object detection. Lin T Y,Dollár P,Girshick R,et al. 2017 IEEE Conference on Computer Vision and Pattern Recognition . 2017