Abstract: In process of pest monitoring and pest control，accurate identification of pests is an important prerequisite for effectively solving pest problems in agricultural field.Relying on expert knowledge and planting experience to diagnose insect pests on crops is inefficient and the level of automation and intelligence is poor.The use of intelligent technologies such as deep learning and computer vision can greatly improve efficiency and accuracy of pest identification process and reduce labor costs.Development status of pest recognition technology based on deep learning was outlined.Implementation principles and advantages of deep learning technology in the field of pest image recognition were analyzed.Latest research progress of domestic and foreign experts and scholars in the field of pest recognition technology based on deep learning were described.Finally，challenges facing this field were summarized and future development direction was forecasted.It could provide an important theoretical reference for further research of pest identification and classification technology in smart agriculture.