基于SwinS-YOLACT的番茄采摘机器人实时实例分割算法研究
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

山东省重点研发计划项目(2023CXGC010715)和中国机械工业集团有限公司科技专项(ZDZX2023-2)


Real-time Instance Segmentation Algorithm for Tomato Picking Robot Based on SwinS-YOLACT
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    在设施番茄种植环境中,果实重叠遮挡等情况会影响识别精度。因此,本文提出了一种基于YOLACT的实例分割模型,提高识别精度。首先,对果实重叠遮挡的类别进行细分并增加该类数据集,从而接近真实采摘场景,并在采摘决策中改善重叠遮挡对识别精度的影响;其次,采用Simple Cope-Paste数据增强方法提高了模型的泛化能力,降低了环境因素对实例分割效果的干扰;然后,在YOLACT基础上,引用多尺度特征提取技术克服了单一尺度特征提取的局限性,并降低了模型复杂度;最后,引入Swin Transformer中的Swin-S注意力机制,优化了模型对于番茄实例分割的细节特征提取效果。实验结果表明,本文模型能够一定程度上缓解分割结果中出现的漏检、误检问题,其目标检测平均精度为93.9%,相比于YOLACT、YOLO v8-x、Mask R-CNN、InstaBoost分别提升10.4、4.5、16.3、3.9个百分点;平均分割精度为80.6%,相比于上述模型分别提升4.8、1.5、7.3、4.3个百分点;推理速度为25.6f/s。该模型综合性能有较强的鲁棒性,兼顾了精度与速度,可为番茄采摘机器人完成视觉任务提供参考。

    Abstract:

    In the facility tomato planting environment, the accuracy of automatic fruit picking can be affected by overlapping and occlusion of fruits. An instance segmentation model was proposed based on YOLACT to address this issue. Firstly, the categories of fruit overlap and occlusion were subdivided, and the dataset of this type was increased to simulate real picking scenes and improve recognition accuracy in picking decisions. Secondly, the Simple Copy-Paste data enhancement method was employed to enhance the model’s generalization ability and reduce the interference of environmental factors on instance segmentation. Next, based on YOLACT, multiscale feature extraction technology was used to overcome the limitation of single-scale feature extraction and reduce the complexity of the model. Finally, the Swin-S attention mechanism in Swin Transformer was incorporated to optimize the detailed feature extraction effect for tomato instance segmentation. Experimental results demonstrated that this model can alleviate the problems of missed detection and false detection in segmentation results to a certain extent. It achieved an average target detection accuracy of 93.9%, which was an improvement of 10.4, 4.5, 16.3, and 3.9 percentage points compared with that of YOLACT, YOLO v8-x, Mask R-CNN and InstaBoost, respectively. Additionally, the average segmentation accuracy was 80.6%, which was 4.8, 1.5, 7.3, and 4.3 percentage points higher than that of the aforementioned models, respectively. The inference speed of this model was 25.6f/s. Overall, this model exhibited stronger robustness and real-time performance in terms of comprehensive performance, effectively addressing both accuracy and speed requirements. It can serve as a valuable reference for tomato picking robots in performing visual tasks.

    参考文献
    相似文献
    引证文献
引用本文

倪纪鹏,朱立成,董力中,崔学智,韩振浩,赵博.基于SwinS-YOLACT的番茄采摘机器人实时实例分割算法研究[J].农业机械学报,2024,55(10):18-30. NI Jipeng, ZHU Licheng, DONG Lizhong, CUI Xuezhi, HAN Zhenhao, ZHAO Bo. Real-time Instance Segmentation Algorithm for Tomato Picking Robot Based on SwinS-YOLACT[J]. Transactions of the Chinese Society for Agricultural Machinery,2024,55(10):18-30.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-12-07
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-10-10
  • 出版日期:
文章二维码