Automated garden-insect recognition using improved lightweight convolution network  

作　　者：Zhankui Yang Xinting Yang Ming Li Wenyong Li 

机构地区：[1]College of Computer Science and Technology,Beijing University of Technology,Beijing 100124,China [2]National Engineering Research Center for Information Technology in Agriculture,Beijing 100089,China [3]National Engineering Laboratory for Quality and Safety Traceability Technology and Application of Agricultural Products,Beijing 100089,China

出　　处：《Information Processing in Agriculture》2023年第2期256-266,共11页农业信息处理（英文）

基　　金：National Natural Science Foundation of China(Grand No:61601034);National Natural Science of China(Grand No:31871525);Promotion and Innovation of Beijing Academy of Agriculture and Forestry Sciences.

摘　　要：Automated recognition of insect category,which currently is performed mainly by agriculture experts,is a challenging problem that has received increasing attention in recent years.The goal of the present research is to develop an intelligent mobile-terminal recognition system based on deep neural networks to recognize garden insects in a device that can be conveniently deployed in mobile terminals.State-of-the-art lightweight convolutional neural networks(such as SqueezeNet and ShuffleNet)have the same accuracy as classical convolutional neural networks such as AlexNet but fewer parameters,thereby not only requiring communication across servers during distributed training but also being more feasible to deploy on mobile terminals and other hardware with limited memory.In this research,we connect with the rich details of the low-level network features and the rich semantic information of the high-level network features to construct more rich semantic information feature maps which can effectively improve SqueezeNet model with a small computational cost.In addition,we developed an off-line insect recognition software that can be deployed on the mobile terminal to solve no network and the timedelay problems in the field.Experiments demonstrate that the proposed method is promising for recognition while remaining within a limited computational budget and delivers a much higher recognition accuracy of 91.64%with less training time relative to other classical convolutional neural networks.We have also verified the results that the improved SqueezeNet model has a 2.3%higher than of the original model in the open insect data IP102.

关 键 词：Insect classification Mobile-terminal recognition SqueezeNet model Deep lightweight convolution NETWORK 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]