基于双线性注意力网络的农业灯诱害虫细粒度图像识别研究

姚青,姚波,吕军,唐健,冯晋,朱旭华

Research on Fine-Grained Image Recognition of Agricultural Light- Trap Pests Based on Bilinear Attention Network

YAO Qing,YAO Bo,LÜ Jun,TANG Jian,FENG Jin,ZHU XuHua

图8 5个模型的19种农业灯诱害虫精准率 A1-铜绿丽金龟 Anomala corpulenta;A2-灰胸突鳃金龟 Hoplosternu incanus;A3-大黑鳃金龟Holotrichia oblita;B1-蝼蛄Gryllotalpa spps;B2-中华蟋蟀Gryllus chinensis;B3-黄足猎蝽Sirthenea flavipes;C1-榆黄足毒蛾Ivela ochropoda;C2-杨雪毒蛾Stilprotia salicis;D1-槐尺蛾Semiothisa cinerearia;D2-格庶尺蛾Semiothisa hebesata;E1-棉铃虫 Helicoverpa armigera;E2-烟青虫Heliothis assulta;E3-劳氏粘虫Leucania loreyi;F1-二化螟Chilo suppressalis;F2-草地螟Loxostege stieticatis;F3-金黄镰翅野螟Circobotys aurealis;F4-稻纵卷叶螟Cnaphalocrocis medinalis;F5-玉米螟Pyrausta nubilalis;F6-大螟Sesamia inferens

Fig. 8 Precision of 19 species agricultural light-trap pests on 5 models