PestNeuroVision

PestNeuroVision is an Android mobile application for detecting agricultural pests using convolutional neural networks and computer vision. Developed as part of a scientific research and technological innovation project, it integrates the YOLO11s object detection model—which runs entirely on-device without requiring an internet connection—to identify various species. This repository contains the AI model pipeline and the Android app source code. This project is distributed under the GNU Affero General Public License v3.0 (AGPL-3.0), with the exception of the images, which retain their original licenses (CC0 1.0 / CC BY 4.0). The fine-tuned YOLO11s weights used in this project, as well as the resulting metrics, are derivative works of the Ultralytics YOLO11 base model, which is also governed by the AGPL-3.0 license. Any modifications or derivative works must also be distributed under the same license, with the source code made publicly available. Detailed copyright information for the images used in this project (original authors and licenses) can be found in the image_credits.csv file, located in the root directory.