亚洲一区欧美在线,日韩欧美视频免费观看,色戒的三场床戏分别是在几段,欧美日韩国产在线人成

基于改進YOLO v5的復雜環(huán)境下柑橘目標精準檢測與定位方法
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號:

基金項目:

重慶市杰出青年科學基金項目(2022NSCQ-JQX0030)、宜賓市雙城協(xié)議保障科研經(jīng)費項目(XNDX2022020015)、中央高?;究蒲袠I(yè)務費專項資金項目(XDJH202302)和重慶市研究生科研創(chuàng)新項目(CYB23125)


Accurate Detection and Localization Method of Citrus Targets in Complex Environments Based on Improved YOLO v5
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪問統(tǒng)計
  • |
  • 參考文獻
  • |
  • 相似文獻
  • |
  • 引證文獻
  • |
  • 資源附件
  • |
  • 文章評論
    摘要:

    針對自然環(huán)境下柑橘果實機械化采收作業(yè)環(huán)境復雜和果實狀態(tài)多樣等情況,提出了一種多通道信息融合網(wǎng)絡——YOLO v5-citrus,以解決柑橘果實識別精準度低、果實分類模糊和定位精準度低等難題。將不同的柑橘目標通過不同遮擋條件分為“可采摘”和“難采摘”兩類,這種分類策略可指導機器人在真實果園中順序摘取,提高采摘效率并減少機器人本體和末端執(zhí)行器損壞率。YOLO v5-citrus中,在頸部網(wǎng)絡插入多通道信息融合模塊,對柑橘的深淺特征信息進行處理,提高柑橘采摘狀態(tài)識別精度,同時修改頸部網(wǎng)絡拼接方法,針對目標柑橘大小進行識別,訓練后在識別部分嵌入聚類算法模塊,將訓練部分識別模糊的柑橘目標進行最后區(qū)分。識別后進行深度圖像和彩色圖像的像素對齊,并通過坐標系轉(zhuǎn)換獲取柑橘目標三維坐標。在使用多種增強技術(shù)處理的數(shù)據(jù)集中,YOLO v5-citrus比原始YOLO v5在平均精度均值和精確率上分別提高2.8個百分點與3.7個百分點,表現(xiàn)出更優(yōu)異的泛化能力。與YOLO v7和YOLO v8等其他主流網(wǎng)絡架構(gòu)相比較,保持了更高的檢測精度和更快的檢測速度。通過真實果園的檢測與定位試驗,得到柑橘目標的三維坐標識別定位系統(tǒng)的定位誤差為(1.97mm,0.36mm,9.63mm),滿足末端執(zhí)行器的抓取條件。試驗結(jié)果表明,該模型具有較強的魯棒性,滿足復雜環(huán)境下柑橘狀態(tài)識別要求,可為柑橘園機械采收設備提供技術(shù)支持。

    Abstract:

    Aiming at the challenges of mechanized citrus fruit harvesting in natural environments, such as complex environments and diverse fruit states, a multichannel information fusion network (YOLO -v5-citrus) was developed, to solve the problems of low accuracy of citrus fruit recognition, fuzzy fruit classification and low accuracy of localization. Different citrus targets were categorized into “pickable” and “hard-to-pick” by different occlusion conditions, and this classification strategy guided the robot to pick them sequentially in a real orchard, which improved the picking rate and reduced the damage rate of the robot body and end-effector. In YOLO v5-citrus, a multi-channel information fusion module was inserted into the neck network to process the depth feature information of citrus to improve the recognition accuracy of the citrus picking state. At the same time, the splicing method of the neck network was modified to recognize the size of the target citrus. The clustering algorithm module was embedded in the recognition part after training to make the final distinction between the citrus targets blurred by the recognition in the training part. Pixel alignment of a depth image and a color image was performed after recognition and 3D coordinates of citrus targets were obtained by coordinate system transformation. In the dataset processed using multiple enhancement techniques, YOLO v5-citrus improved mAP and precsion by 2.8 percentage points and 3.7 percentage points, respectively, compared with the original YOLO v5, respectively. It maintained higher detection accuracy and faster detection speed than other mainstream network architectures such as YOLO v7 and YOLO v8. Through the detection and localization test in the real orchard, the localization error of the 3D coordinate recognition localization system for the citrus target was obtained as (1.97mm,0.36mm,9.63mm), which satisfied the grasping condition of the endeffector. The experimental results showed that the model had strong robustness, meeting the requirements of citrus state recognition in complex environments, and can provide technical support for mechanical harvesting equipment in large-field citrus orchards.

    參考文獻
    相似文獻
    引證文獻
引用本文

李麗,梁繼元,張云峰,張官明,淳長品.基于改進YOLO v5的復雜環(huán)境下柑橘目標精準檢測與定位方法[J].農(nóng)業(yè)機械學報,2024,55(8):280-290. LI Li, LIANG Jiyuan, ZHANG Yunfeng, ZHANG Guanming, CHUN Changpin. Accurate Detection and Localization Method of Citrus Targets in Complex Environments Based on Improved YOLO v5[J]. Transactions of the Chinese Society for Agricultural Machinery,2024,55(8):280-290.

復制
分享
文章指標
  • 點擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:2024-04-08
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2024-08-10
  • 出版日期: