Modern agriculture is facing unique challenges in building a sustainable future for food production, in which the reliable detection of plantations’ threats is of critical importance.
The breadth of existing information sources, and their equivalent sensors, can provide a wealth of data which, to be useful, must be transformed into actionable knowledge.
Approaches based on Information Communication Technologies (ICT) have been shown to be able to help farmers, and related stakeholders, make decisions on problems by examining large volumes of data while assessing multiple criteria.
In this work we address the automated identification (and counting of instances) of the major threat of olive trees and their fruit, the Bactrocera Oleae (a.k.a. Dacus) based on images of the commonly used McPhail trap’s contents.
Accordingly, we introduce* the “Dacus Image Recognition Toolkit” (DIRT), a collection of publicly available data, programming code samples and web-services focused at supporting research aiming at the management the Dacus as well as extensive experimentation on the capability of the proposed dataset in identifying Dacuses using Deep Learning methods.
Experimental results indicated performance accuracy (mAP) of 91.52% in identifying Dacuses in traps’ images featuring various pests. Moreover, the results also indicated a trade-off between images’ attributes affecting detail, file size & complexity of approaches and mAP performance that can be selectively used to better tackle the needs of each usage scenario.
The toolkit is separated into the following parts:
- dataset: that includes all the data data consists of images, the majority of which depict olive fruit fly captures in McPhail traps, collected from year 2015 to 2017 in various locations of Corfu, Greece;
- API: that allows users to query our publicly available rest https API that replies to queries for Dacuses’ identification in user provided images;
- web-interface: that furnishes the API’s functionality for users through a browser;
- programming code samples: for matlab that allow interested researchers to fast-track their use of DIRT’s contents as well as guide them into some rudimentary, research-oriented, experimentation; and
- experimental results*: indicating the usefulness of the proposed dataset at the ability to automatically identify Dacuses in images using as ground-truth manually annotated spatial identification of Dacuses.
The toolkit is currently (may soon be migrated to more suitable hardware-wise server) available at https://hilab.di.ionio.gr/DIRT/.
*The contents of our research paper on “Dacus Image Recognition Toolkit” will be available as soon as peer-reviewing is completed.