thumbnail

Topic

Technologies and technical equipment for agriculture and food industry

Volume

Volume 68 / No. 3 / 2022

Pages : 373-382

Metrics

Volume viewed 0 times

Volume downloaded 0 times

APPLICATION OF A REAL-TIME DETECTION MODEL FOR IDETIFICATION OF CITRUS DURING DIFFERENT GROWTH STAGES IN ORCHARDS

一种实时检测模型在果园不同生长阶段的柑橘识别

DOI : https://doi.org/10.35633/inmateh-68-37

Authors

(*) Changgao XIA XIA

jinagsu university

Wanlei NI NI

jinagsu university

Kun JIANG JIANG

jiangsu university

Xiaofan LI LI

jiangsu university

(*) Corresponding authors:

[email protected] |

Changgao XIA XIA

Abstract

In order to solve the problem of citrus full growth cycle identification in complex scenes, this paper proposed a multi-scale detection model of citrus whole growth cycle in orchard environment. The weighted bi-directional feature pyramid network (BiFPN) is used to combine multiple feature information of high resolution and low- resolution feature layers, and the feature information is extracted by the depth-separable convolution and lightweight New-C3 module. The results show that the average accuracy of the multi-scale detection model proposed in this paper was 91.35%, 92.89%, 94.12%, 90.39% in the young citrus, expanding citrus, ripe citrus and full growth cycle citrus, and the average detection time was 92.60 FPS/s under 1920×1080 image pixels, which meets the real-time detection requirements of citrus orchard.

Abstract in Chinese

为了解决复杂场景下柑橘的全生长周期识别问题,本文提出了一种果园环境下柑橘全生长周期的多尺度检测模型。采用加权双向特征金字塔网络(BiFPN)来融合高分辨率和低分辨率特征层的多项特征信息,且通过深度可分离卷积和轻量型New-C3模块实现特征信息的提取。结果表明,本文提出的多尺度检测模型在生长期、膨果期、成熟期和全生长周期柑橘的平均精度为91.35%,92.89%,94.12%,90.39%,在1920×1080图像像素下的平均检测时间为92.60 FPS/s,满足果园柑橘的实时检测要求。

Indexed in

Clarivate Analytics.
 Emerging Sources Citation Index
Scopus/Elsevier
Google Scholar
Crossref
Road