【数据科学赛】NASA Harvest Field Boundary Detection Challenge #CV #边界检测 #$5000-CSDN博客

本次挑战由Zindi举办，旨在使用PlanetScope卫星的多光谱观测数据来分类卢旺达东部地区的农田边界。该区域包含加西博和尼亚加塔雷两个区的小型农场。训练数据集由TaQadam团队通过标注人员生成，并由Radiant Earth Foundation整理。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

CompHub 实时聚合多平台的数据类(Kaggle、天池…)和OJ类(Leetcode、牛客…）比赛。本账号会推送最新的比赛消息，欢迎关注！

更多比赛信息见 CompHub主页或点击文末阅读原文

以下内容摘录自比赛主页

Part1赛题介绍

题目

NASA Harvest Field Boundary Detection Challenge

举办平台

Zindi

背景

Small farms (<2ha) produce about 35% of the world’s food, and are mostly found in low- and middle-income countries. Mapping these farms allows policy-makers to allocate resources and monitor the impacts of extreme events on food production and food security. Unfortunately, these field-level maps remain mostly unavailable in low and middle income countries, where the food insecurity risk is highest. Combining machine learning with Earth Observation data from satellites like the PlanetScope constellation can help improve agricultural monitoring, cropland mapping, and disaster risk management for these small farms.

Part2时间安排

Competition closes on 26 February 2023.
Final submissions must be received by 11:59 PM GMT.
We reserve the right to update the contest timeline if necessary.

Part3奖励机制

1st Place: $2 500 USD
2nd Place: $1 500 USD
3rd Place: $1 000 USD

Part4赛题描述

In this challenge, the goal is to classify crop field boundaries using multispectral observations collected by PlanetScope, available through the NICFI basemaps program. Fields are located in Rwanda’s Eastern Province (Intara y’lburasirazuba) and spread over the districts of Gatsibo and Nyagatare. The NASA Harvest Rwanda field boundary training dataset was generated by TaQadam through a team of annotators, and curated by Radiant Earth Foundation.

Part5比赛数据

The dataset for this competition includes a time series of satellite imagery from Planet’s NICFI basemaps (license agreement) and labels for field boundaries that were annotated on the same imagery source. The labels were digitized over Planet Basemaps for the months of March, April (on season) and August (off season) of 2021 by a team of annotators from TaQadam. An additional 3 months of imagery (October, November and December) are added to the time series data and are then matched with corresponding field boundary labels.