吴烽云, 叶雅欣, 陈思宇, 等. 复杂环境下香蕉多目标特征快速识别研究[J]. 华南农业大学学报, 2022, 43(2): 96-104. DOI: 10.7671/j.issn.1001-411X.202108009
    引用本文: 吴烽云, 叶雅欣, 陈思宇, 等. 复杂环境下香蕉多目标特征快速识别研究[J]. 华南农业大学学报, 2022, 43(2): 96-104. DOI: 10.7671/j.issn.1001-411X.202108009
    WU Fengyun, YE Yaxin, CHEN Siyu, et al. Research on fast recognition of banana multi-target features by visual robot in complex environment[J]. Journal of South China Agricultural University, 2022, 43(2): 96-104. DOI: 10.7671/j.issn.1001-411X.202108009
    Citation: WU Fengyun, YE Yaxin, CHEN Siyu, et al. Research on fast recognition of banana multi-target features by visual robot in complex environment[J]. Journal of South China Agricultural University, 2022, 43(2): 96-104. DOI: 10.7671/j.issn.1001-411X.202108009

    复杂环境下香蕉多目标特征快速识别研究

    Research on fast recognition of banana multi-target features by visual robot in complex environment

    • 摘要:
      目的  针对野外环境下断蕾机器人对多特征的变量目标快速识别难题,以及目标受到树叶、遮挡及光照影响精度的问题,提出多特征目标的快速识别方法。
      方法  提出对香蕉果实、果轴和花蕾这3个目标进行多尺度特征提取及模型分类,融合聚类算法设计新的目标候选框参数,提出改进YOLOv3模型及网络结构参数的YOLO-Banana模型;为了平衡速度和准确度,用YOLO-Banana和Faster R-CNN分别对变化尺寸的香蕉多目标进行试验,研究算法对识别精度与速度的影响。
      结果  YOLO-Banana和Faster R-CNN这2种算法识别香蕉、花蕾和果轴的总平均精度分别为91.03%和95.16%,平均每张图像识别所需时间分别为0.237和0.434 s。2种算法精度均高于90%,YOLO-Banana的速度相对快1.83倍,更符合实时作业的需求。
      结论  野外蕉园环境下,采用YOLO-Banana模型进行香蕉多目标识别,可满足断蕾机器人视觉识别的速度及精度要求。

       

      Abstract:
      Objective  Aiming at fast recognition of multi-feature variable target by robot vision in field environment, and considering the problem that the accuracy of target is affected by leaves, shade and light, a fast recognition method of multi-feature target was proposed.
      Method  A multi-scale feature extraction and classification model was proposed for three targets including banana fruit, fruit axis and flower bud. New target candidate box parameters were designed using clustering algorithm. The network structure parameters of YOLOv3 model were optimized and the YOLO-Banana model was proposed. In order to balance the speed and accuracy, YOLO-Banana and Faster R-CNN were used to conduct experiments on banana multi-targets with varying sizes. The effects of algorithms on recognition accuracy and speed were analyzed.
      Result  The average accuracies of YOLO-Banana and Faster R-CNN algorithms on banana fruit, fruit axis and flower bud were 91.03% and 95.16% respectively, average recognition time per photo was 0.237 and 0.434 s respectively. Therefore the accuracies of two algorithms were both above 90%. YOLO-Banana had relatively 1.83 times faster speed than Faster R-CNN, better satisfying the requirement of real-time operation.
      Conclusion  In the wild environment, utilization of YOLO-Banana model for banana multi-target recognition can meet the speed and accuracy requirements for visual recognition by the bud-breaking robots.

       

    /

    返回文章
    返回