《電子技術應用》
您所在的位置:首頁 > 通信與網絡 > 設計應用 > 基于雙線性池化的實蠅分類注意力網絡
基于雙線性池化的實蠅分類注意力網絡
2023年電子技術應用第5期
彭瑩瓊1,2,俞融融3,尹乘樂4,洪恩松2,俞小明3,趙雷3,何雯潔2,鄧泓1,2
(1.江西農業(yè)大學 江西省高等學校農業(yè)信息技術重點實驗室與軟件研究所,江西 南昌330045; 2.江西農業(yè)大學 軟件學院,江西 南昌330045;3.江西農業(yè)大學 計算機與信息工程學院,江西 南昌330045; 4.德布勒森大學,匈牙利 德布勒森4032)
摘要: 實蠅是國內外備受關注的檢疫害蟲,種類繁多。不同種類的實蠅外形大小相似,不易鑒別。此外,在實際應用中,鑒別實蠅的可用信息會受遮擋、視角、光影變幻等因素影響,導致實蠅自動識別工作難以進行。提出基于雙線性池化的實蠅分類注意力網絡,用于學習有效的實蠅鑒別特征。該網絡由顯著性特征模塊和跨層雙線性模塊兩個部分組成:顯著性特征模塊通過對不同卷積層進行濾波增強處理,實現特征增強;跨層雙線性模塊基于雙線性池化融合特征,確定注意部位,挖掘判別特征。在具有自然環(huán)境背景的實蠅數據集上進行的實驗表明,該方法效果較好,具有良好的實際應用前景。
中圖分類號:TP391.41;TP18
文獻標志碼:A
DOI: 10.16157/j.issn.0258-7998.233817
中文引用格式: 彭瑩瓊,俞融融,尹乘樂,等. 基于雙線性池化的實蠅分類注意力網絡[J]. 電子技術應用,2023,49(5):8-13.
英文引用格式: Peng Yingqiong,Yu Rongrong,Ying Chengle,et al. Attention networks for fruit fly classification based on bilinear pooling[J]. Application of Electronic Technique,2023,49(5):8-13.
Attention networks for fruit fly classification based on bilinear pooling
Peng Yingqiong1,2,Yu Rongrong3,Ying Chengle4,Hong Ensong2,Yu Xiaoming3,Zhao Lei3,He Wenjie2,Deng Hong1,2
(1.The Colleges and Universities of Jiangxi Province for Key Laboratory of Information Technology in Agriculture and Software Institute, Jiangxi Agricultural University, Nanchang 330045, China; 2.College of Software, Jiangxi Agricultural University, Nanchang 330045, China; 3.College of Computer and Information Engineering, Jiangxi Agricultural University, Nanchang 330045, China; 4.University of Debrecen,Debrecen 4032,Hungary)
Abstract: Fruit fly is a kind of quarantine pest that attracts much attention at home and abroad. There are many kinds of fruit flies. Different kinds of fruit flies are similar in shape and size, which is difficult to identify. In addition, in practical applications, it is difficult to identify fruit flies due to the lack of information about shielding, view-point, changing light and shadow and other factors. This study proposes a bilinear pooled attention network for fruit fly classification to learn effective discriminant characteristics. The network is composed of two parts: saliency feature module and cross-layer bilinear feature module. Saliency feature module realizes feature enhancement by filtering enhancement processing of two different convolution layers. Cross-layer bilinear module is based on bilinear pooling fusion features, determines the attention location, and mines discriminant features. Experiments on fruit fly’s data set with natural environment background show that the method is effective and has good practical application prospect.
Key words : fruit fly detection;bilinear pooling;attention mechanism

0 引言

實蠅作為亞太地區(qū)重要的檢疫性害蟲,具有寄主多、蟲害擴散迅速的特點。該類害蟲能夠寄生于橘、桃、番石榴、楊梅等46個科 250多種水果、蔬菜和花卉。在不注重防控的情況下,實蠅能輕易造成80%到100%的損失。以福建省為例,該省2016年受瓜實蠅、具條實蠅等實蠅害蟲影響,導致約313.48億元經濟損失,其中直接經濟損失約221.74億元,包括生態(tài)損失在內的間接經濟損失約為7.5億元。所以防治實蠅對于減少農業(yè)經濟損失起重要作用。針對實蠅的檢疫與防治,此研究將準確識別實蠅個體類別作為首要任務,為實蠅檢測的實際應用提供思路。


本文詳細內容請下載:http://ihrv.cn/resource/share/2000005300




作者信息:

彭瑩瓊1,2,俞融融3,尹乘樂4,洪恩松2,俞小明3,趙雷3,何雯潔2,鄧泓1,2

(1.江西農業(yè)大學 江西省高等學校農業(yè)信息技術重點實驗室與軟件研究所,江西 南昌330045;2.江西農業(yè)大學 軟件學院,江西 南昌330045;3.江西農業(yè)大學 計算機與信息工程學院,江西 南昌330045;4.德布勒森大學,匈牙利 德布勒森4032)


微信圖片_20210517164139.jpg

此內容為AET網站原創(chuàng),未經授權禁止轉載。