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

基于輕量化YOLO v8s-GD的自然環(huán)境下百香果快速檢測模型
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號:

基金項目:

福廈泉國家自主創(chuàng)新平臺項目(2023FX0002)


Passion Fruit Rapid Detection Model Based on Lightweight YOLO v8s-GD
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:

    為了提高百香果檢測精度,并將深度學習模型部署在移動平臺上,實現(xiàn)快速實時推理,本文提出一種基于改進YOLO v8s的輕量化百香果檢測模型(YOLO v8s-GD)。使用聚集和分發(fā)機制(GD)替換頸部特征融合網(wǎng)絡,提高模型對百香果圖像特征信息跨層融合能力和模型泛化能力;通過基于層自適應幅度的剪枝(LAMP)修剪模型,損失一定精度換取減小模型體積,減少模型參數(shù)量,以實現(xiàn)在嵌入式設(shè)備上快速檢測;運用知識蒸餾學習策略彌補因剪枝而損失的檢測精度,提高模型檢測性能。實驗結(jié)果表明,對于自然環(huán)境下采集的百香果數(shù)據(jù)集,改進后模型參數(shù)量和內(nèi)存占用量相比原YOLO v8s基線模型分別降低63.88%和62.10%,精確率(Precision)和平均精度(AP)相較于原模型分別提高0.9、2.3個百分點,優(yōu)于其他對比模型。在Jetson Nano和Jetson Tx2嵌入式設(shè)備上實時檢測幀率(FPS)分別為5.78、19.38f/s,為原模型的1.93、1.24倍。因此,本文提出的改進后模型能夠有效檢測復雜環(huán)境下百香果目標,為實際場景中百香果自動采摘等移動端檢測設(shè)備部署和應用提供理論和技術(shù)支持。

    Abstract:

    In order to improve the accuracy of passion fruit detection and deploy the deep learning model on mobile platforms for rapid real-time inference, a lightweight passion fruit detection model was proposed based on an improved YOLO v8s. The model replaced the neck feature fusion network with a Gather-and-distribute mechanism (GD) to enhance cross-layer feature fusion and generalization capabilities for passion fruit images. Additionally, the model was pruned by using layer-adaptive sparsity for the magnitude-based pruning (LAMP), which traded off some accuracy to reduce model size and parameter count, facilitating rapid detection on embedded devices. Knowledge distillation was employed to compensate for the accuracy loss caused by pruning, further enhancing detection performance. Experimental results showed that for a passion fruit dataset collected in natural environments, the improved model reduced parameter count and memory usage by 63.88% and 62.10%, respectively, compared with the original YOLO v8s baseline model. The precision and average precision (AP) of the improved model were increased by 0.9 percentage points and 2.3 percentage points, respectively, outperforming other comparative models. Real-time detection frame rates (FPS) on Jetson Nano and Jetson Tx2 embedded devices were 5.78f/s and 19.38f/s, respectively, which were 1.93 times and 1.24 times higher than that of the original model. Therefore, the proposed improved model effectively detects passion fruit in complex environments, providing theoretical and technical support for the deployment and application of mobile detection devices in scenarios such as automatic passion fruit harvesting.

    參考文獻
    相似文獻
    引證文獻
引用本文

羅志聰,何陳濤,陳登捷,李鵬博,孫奇燕.基于輕量化YOLO v8s-GD的自然環(huán)境下百香果快速檢測模型[J].農(nóng)業(yè)機械學報,2024,55(8):291-300. LUO Zhicong, HE Chentao, CHEN Dengjie, LI Pengbo, SUN Qiyan. Passion Fruit Rapid Detection Model Based on Lightweight YOLO v8s-GD[J]. Transactions of the Chinese Society for Agricultural Machinery,2024,55(8):291-300.

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:2024-05-06
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2024-08-10
  • 出版日期: