DeepPlastic: An Open Source Image Dataset for Epipelagic Marine Plastic Detection

Deep Plastic

Enhanced Object Detection for Epipelagic Plastic.

This repository contains source code for the method developed in DeepPlastic: Identifying Marine Plastic In The Epipelagic Zone using Computer Vision and Deep Learning

Information:

Paper: [Coming Soon]

YouTube video of Results: https://youtu.be/8zBdFxaK4Os

Object Detection Model

Four models: YOLOv4, YOLOv5, MobileSSD, Faster RCNN Inception V2

Small efficient and high precision models can be used for real-time object detection.

Model architecture and implementation details: https://arxiv.org/

Weights for YOLOv4 and YOLOv5 are provided in the model/

YOLOv4: best. weights; use best.weights

YOLOv5: best.pt; use best.pt

Google Colab Links

Note: Click on File and Save Copy in Drive. If you try to edit my file it'll ask you for permission and send me an email. Please make your own copy.

YOLOv5: https://colab.research.google.com/drive/1_qzbpBWkNfxQ0ny-DvsKicCeM0aFU4eW?usp=sharing

DeepTrash DataSet

1900 training images, 637 test images, 637 validation images (60, 20, 20 split)

Field images taken from Lake Tahoe, San Francisco Bay and Bodega Bay in CA.

Deep Sea images are from JAMSTEK JEDI dataset: http://www.godac.jamstec.go.jp/