# Plastic water bottle detection model using computer vision in aquatic environments

## TL;DR

This paper presents an automated system using computer vision to detect and count plastic water bottles in rivers and streams.

## Contribution

A novel post-processing algorithm combined with YOLOv8 and Norfair for accurate plastic bottle detection in aquatic environments.

## Key findings

- The model achieved a recall of over 0.947 in test scenarios.
- Only one false positive was recorded during testing.
- The system uses publicly available datasets for training.

## Abstract

Watershed macrotrash contamination is difficult to measure and requires tedious and labor-intensive processes. This work proposes an automated approach to waste counting, focusing on using computer vision, deep learning, and object tracking algorithms to acquire accurate counts of plastic bottles as they advect down rivers and streams. By using a combination of several publicly available labeled trash and plastic bottle image datasets, the model was trained to achieve high performance with the YOLOv8 object detection model. This was paired with the Norfair object tracking library and a novel post-processing algorithm to filter out false positives. The model performed extremely accurately over the test scenarios with just one false positive and recalls in excess of 0.947.