Pigeon cleaning behavior detection algorithm based on light-weight network

被引：15

作者：

Guo, Jianjun ^{[1
,2
,3
]}

He, Guohuang ^{[1
,2
,3
]}

Deng, Hao ^{[1
,2
,3
]}

Fan, Wenting ^{[1
,2
,3
]}

Xu, Longqin ^{[1
,2
,3
]}

Cao, Liang ^{[1
,2
,3
]}

Feng, Dachun ^{[1
,2
,3
]}

Li, Jingbin ^{[4
]}

Wu, Huilin ^{[5
]}

Lv, Jiawei ^{[1
,2
,3
]}

Liu, Shuangyin ^{[1
,2
,3
]}

Hassan, Shahbaz Gul ^{[1
,2
,3
]}

机构：

[1] Zhongkai Univ Agr & Engn, Guangzhou Key Lab Agr Prod Qual & Safety Traceabil, Guangzhou 510225, Peoples R China

[2] Zhongkai Univ Agr & Engn, Coll Informat Sci & Technol, Guangzhou 510225, Peoples R China

[3] Zhongkai Univ Agr & Engn, Acad Intelligent Agr Engn Innovat, Guangzhou 510225, Peoples R China

[4] Shihezi Univ, Coll Mech & Elect Engn, Shihezi 832000, Peoples R China

[5] Natl S&T Innovat Ctr Modern Agr Ind Guangzhou Shor, Guangzhou, Peoples R China

来源：

COMPUTERS AND ELECTRONICS IN AGRICULTURE | 2022年 / 199卷

基金：

中国国家自然科学基金; 国家科技攻关计划;

关键词：

Target detection; Pigeon cleaning behavior; Light-weight network; YOLO v4; Ghostnet;

D O I：

10.1016/j.compag.2022.107032

中图分类号：

S [农业科学];

学科分类号：

09 ;

摘要：

The behavior of pigeons in the dovecote reflects their environmental comfort and health indicators. In order to solve the problems of time-consuming, labor-consuming, and subjectivity of traditional manual experience, an improved YOLO V4 light-weight target detection algorithm was proposed for row detection of breeding pigeons. Employ SPP, FPN, and PANet networks to strengthen the features retrieved from GhostNet as the backbone. To ensure accuracy, Ghostnet-yolo V4 reduced the model's number of parameters and raised its size to 43 MB. The light-weight feature extraction network GhostNet outperformed MobileNet V1 similar to V3 under the modified model. Faster RCNN, SSD, YOLO V4 and YOLO V3 compression rates were increased by 43.4 percent, 35.8 percent, 70.1 percent, and 69.1 percent, respectively. The improved algorithm has an accuracy of 97.06 percent and a recognition speed of 0.028 s per frame. The improved model can provide a theoretical foundation and technological reference for detecting breeding pigeon behavior in real-time in a dovecote.

引用

页数：14

共 41 条

[41] Warship’s vital parts detection algorithm based on lightweight Anchor-Free network with multi-scale feature fusion
Li C.
Gu J.
Wang L.
Qian K.
Feng Z.
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2022, 48 (10): : 2006 - 2019

← 1 2 3 4 5 →