Scribble-Based Weakly Supervised Deep Learning for Road Surface Extraction From Remote Sensing Images

نویسندگان

چکیده

Road surface extraction from remote sensing images using deep learning methods has achieved good performance, while most of the existing are based on fully supervised learning, which requires a large amount training data with laborious per-pixel annotation. In this article, we propose scribble-based weakly road method named ScRoadExtractor, learns easily accessible scribbles such as centerlines instead densely annotated ground truths. To propagate semantic information sparse to unlabeled pixels, introduce label propagation algorithm, considers both buffer-based properties networks and color spatial super-pixels, produce proposal mask categories road, nonroad, unknown. The mask, along auxiliary boundary prior detected images, is utilized train dual-branch encoder–decoder network designed for precise segmentation. We perform experiments three diverse sets that comprised high-resolution satellite aerial across world. results demonstrate ScRoadExtractor exceeds classic scribble-supervised segmentation by 20% intersection over union (IoU) indicator outperforms state-of-the-art at least 4%.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Mixture Distributions for Weakly Supervised Classification in Remote Sensing Images

For its simplicity and efficiency, the bag-of-words representation based on appearance features is widely used in image and text classification. Its drawback is that shape patterns of the image are neglected. This paper presents a novel image classification approach using a bag-of-words representation of textons while taking into account spatial information. A generative probabilistic modeling ...

متن کامل

Weakly supervised object extraction with iterative contour prior for remote sensing images

This article presents a weakly supervised approach based on Markov random field model for the extraction of objects (e.g., aircrafts) in optical remote sensing images. This approach is capable of localizing and then segmenting objects in optical remote sensing images by relying only on several object samples without artificial labels. However, unlike direct combinations of object detection and ...

متن کامل

Deep Residual Learning for Weakly-Supervised Relation Extraction

Deep residual learning (ResNet) (He et al., 2016) is a new method for training very deep neural networks using identity mapping for shortcut connections. ResNet has won the ImageNet ILSVRC 2015 classification task, and achieved state-of-theart performances in many computer vision tasks. However, the effect of residual learning on noisy natural language processing tasks is still not well underst...

متن کامل

Weakly supervised learning from images and videos∗

With the amount of on-line available digital content growing daily, large-scale, weakly supervised learning is becoming more and more important. In this talk we present some recent results for weakly supervised learning from images and videos. Standard approaches to object category localization require bounding box annotations of object instances. This time-consuming annotation process is sides...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Transactions on Geoscience and Remote Sensing

سال: 2022

ISSN: ['0196-2892', '1558-0644']

DOI: https://doi.org/10.1109/tgrs.2021.3061213