A Motor-Driven and Computer Vision-Based Intelligent E-Trap for Monitoring Citrus Flies

Abstract

Citrus flies are important quarantine pests in citrus plantations. Electronic traps (e-traps) based on computer vision are the most popular types of equipment for monitoring them. However, most current e-traps are inefficient and unreliable due to requiring manual operations and lack of reliable detection and identification algorithms of citrus fly images. To address these problems, this paper presents a monitoring scheme based on automatic e-traps and novel recognition algorithms. In this scheme, the prototype of an automatic motor-driven e-trap is firstly designed based on a yellow sticky trap. A motor autocontrol algorithm based on Local Binary Pattern (LBP) image analysis is proposed to automatically replace attractants in the e-trap for long-acting work. Furthermore, for efficient and reliable statistics of captured citrus flies, based on the differences between two successive sampling images of the e-trap, a simple and effective detection algorithm is presented to continuously detect the newly captured citrus flies from the collected images of the e-trap. Moreover, a Multi-Attention and Multi-Part convolutional neural Network (MAMPNet) is proposed to exploit discriminative local features of citrus fly images to recognize the citrus flies in the images. Finally, extensive simulation experiments validate the feasibility and efficiency of the designed e-trap prototype and its autocontrol algorithm, as well as the reliability and effectiveness of the proposed detection and recognition algorithms for citrus flies.

A real-time remote surveillance system for fruit flies of economic importance: sensitivity and image analysis

“…In addition, the strategy used to obtain images to train the code using the "FF photographic studio" was demonstrated as an appropriate approach. Recently, Huang et al (2021) proposed developing a classification system for citrus FF based on a "multi-attention and multi-part convolutional neural network." They demonstrated the efficacy of their method using a simulation approach.…”

“…S7-S9), flies can be misclassified due to their landing position in the sticky board, or be confused with other insects attracted and trapped in the sticky board, such as stable flies. Huang et al (2021) simulation and training approach, however, may provide a good strategy that can be adopted to improve misclassifications encountered in our developed model and that can be distorted when feeding population dynamic models with scalar data, or mislead alert systems.…”

“…This possibility requires that the e-trap be serviced at a higher frequency than planned, and a new adhesive-board installed once the yellow sticky-board becomes saturated. Huang et al (2021) provides a theoretical solution to solve this situation using a carrousel mechanism rolling a yellow adhesive sticky paper at certain time-frequency. This possibility was considered at the early stages of our e-trap design, but the idea was discharged due to the foreseen complications expected from the addition of a mechanical system into the e-trap.…”

“…In addition, our e-trap was conceived for environments with low FF populations (i.e., FF free and low prevalence areas) and a surveillance system for exotic FF, thus reducing the possibility of the adhesive-board saturation. In any case, Huang et al (2021) mechanical approach may be considered and evaluated in the future if the purpose of our e-trap is extended to IPM and monitoring.…”

Improved Soil Moisture and Electrical Conductivity Prediction of Citrus Orchards Based on IoT Using Deep Bidirectional LSTM

“…Citrus is a widely planted fruit crop throughout the world [1] that grows well in different kinds of environments in many countries [2] such as China, Brazil, and the United States. Among these countries, China's planting area and its production of citrus are the largest, distributed mainly in Guangdong, Guangxi, and Sichuan, making considerable profits every year [3].…”