The 1st Agriculture-Vision Challenge: Methods and Results

TL;DR

This paper introduces the Agriculture-Vision Challenge, encouraging development of novel algorithms for agricultural semantic segmentation using a large aerial image dataset, highlighting notable methods and results from participating teams.

Contribution

It presents the first challenge dedicated to agricultural aerial image segmentation, providing a dataset and benchmarking platform to foster research in this domain.

Findings

Multiple state-of-the-art methods evaluated

Significant improvements in segmentation accuracy achieved

Open platform for ongoing research and benchmarking

Abstract

The first Agriculture-Vision Challenge aims to encourage research in developing novel and effective algorithms for agricultural pattern recognition from aerial images, especially for the semantic segmentation task associated with our challenge dataset. Around 57 participating teams from various countries compete to achieve state-of-the-art in aerial agriculture semantic segmentation. The Agriculture-Vision Challenge Dataset was employed, which comprises of 21,061 aerial and multi-spectral farmland images. This paper provides a summary of notable methods and results in the challenge. Our submission server and leaderboard will continue to open for researchers that are interested in this challenge dataset and task; the link can be found here.