TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

RoboSat: feature extraction from aerial and satellite imagery

80 点作者 danieljh将近 7 年前

5 条评论

danieljh将近 7 年前
Daniel from Mapbox here. Happy to answer questions or talk through design decisions. Interested to hear your feedback.<p>We are mostly focusing on making the process accessible to a broader audience in the geo space, building a solid production-ready end-to-end project.<p>There are more resources and a step-by-step guide for running on openly available drone imagery in Tanzania:<p><a href="https:&#x2F;&#x2F;www.openstreetmap.org&#x2F;user&#x2F;daniel-j-h&#x2F;diary&#x2F;44145" rel="nofollow">https:&#x2F;&#x2F;www.openstreetmap.org&#x2F;user&#x2F;daniel-j-h&#x2F;diary&#x2F;44145</a> <a href="https:&#x2F;&#x2F;www.openstreetmap.org&#x2F;user&#x2F;daniel-j-h&#x2F;diary&#x2F;44321" rel="nofollow">https:&#x2F;&#x2F;www.openstreetmap.org&#x2F;user&#x2F;daniel-j-h&#x2F;diary&#x2F;44321</a>
评论 #17483907 未加载
评论 #17483806 未加载
nl将近 7 年前
Have you released pre-trained models?<p>It would be pretty useful if you did, even as a just basis for transfer learning.<p>Also a description of the model that is used? I assume this is the code[1], which references <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1806.00844" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1806.00844</a>, but the code doesn&#x27;t seem to use WideResnet (although I really know Keras much better than PyTorch so I&#x27;m probably missing something.<p>[1] <a href="https:&#x2F;&#x2F;github.com&#x2F;mapbox&#x2F;robosat&#x2F;blob&#x2F;master&#x2F;robosat&#x2F;unet.py" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mapbox&#x2F;robosat&#x2F;blob&#x2F;master&#x2F;robosat&#x2F;unet.p...</a>
评论 #17484759 未加载
Atanahel将近 7 年前
Interestingly, we&#x27;ve taken the same approach to process historical document (like 18th Venetian manuscripts).<p>We even use a Unet architecture with a pretrained resnet50 encoder, and some postprocessing to go from prob maps to polygons, like this project does. Of course, we are much more limited than what you propose, but it is reassuring our side project took the same course as what bugger entities do.<p><a href="https:&#x2F;&#x2F;dhlab-epfl.github.io&#x2F;dhSegment&#x2F;" rel="nofollow">https:&#x2F;&#x2F;dhlab-epfl.github.io&#x2F;dhSegment&#x2F;</a>
rishabhj_says将近 7 年前
Hi Daniel, in your experience, what features is this model most suited for and with what granularity of imagery? For example, buildings&#x2F;roads with landsat(30m)? Cars with 30cm resolution imagery?
评论 #17488555 未加载
alexcnwy将近 7 年前
Very cool! Does anyone know any good global free satellite imagery datasets?
评论 #17483655 未加载
评论 #17483400 未加载
评论 #17483931 未加载