Unsupervised Semantic Segmentation of Aerial Images With Application to UAV Localization

Jaimes, Brayan René Acevedo; Ferreira, João Pedro Klock; Castro, Cristiano Leite de

doi:10.1109/lgrs.2021.3113878

Cited by 5 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e experimental results verify the effectiveness of parallax information in street scene semantic segmentation task. Jaimes et al [18] proposed a completely unsupervised semantic segmentation method to solve the problem that deep semantic segmentation networks (DSSNs) are not suitable for the field of label scarcity. ey can find an appropriate number of semantic labels without annotation data sets.…”

Section: Relevant Research Workmentioning

confidence: 99%

A Method of Image Semantic Segmentation Based on PSPNet

Yang¹,

Guo²

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Image semantic segmentation is a visual scene understanding task. The goal is to predict the category label of each pixel in the input image, so as to achieve object segmentation at the pixel level. Semantic segmentation is widely used in automatic driving, robotics, medical image analysis, video surveillance, and other fields. Therefore, improving the effect and accuracy of image semantic segmentation has important theoretical research significance and practical application value. This paper mainly introduces the pyramid scene parsing network PSPNet based on pyramid pooling and proposes a parameter optimization method based on PSPNet model using GPU distributed computing method. Finally, it is compared with other models in the field of semantic segmentation. The experimental results show that the accuracy of the improved PSPNet model in this paper has been significantly improved on Pascal VOC 2012 + 2017 data set.

show abstract

Section: Relevant Research Workmentioning

confidence: 99%

A Method of Image Semantic Segmentation Based on PSPNet

Yang¹,

Guo²

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Next, in step 1.4 we extract color (f c ) and texture (f t ) features from the superpixels, as described in [11]. A graph is mounted in step 1.5 with adjacent superpixels, with the weights, ϕ ij , adapted from [4], but using different features, and calculating their similarities using the features themselves.…”

Section: Methodology a Automatic Scribble Generationmentioning

confidence: 99%

Weaklier Supervised: Semi-automatic Scribble Generation Applied to Semantic Segmentation

Ferreira¹,

Pinto²,

Castro³

2022

Anais Estendidos Do XXXV Conference on Graphics, Patterns and Images (SIBGRAPI Estendido 2022)

View full text Add to dashboard Cite

With many applications regarding semantic segmentation arising, along with the advent of the Deep Semantic Segmentation Networks, the need for large labeled datasets has also largely increased. But labeling thousands of images can be very expensive and time-consuming. Approaches such as weak and semi supervision try do deal with this problem, but the first cannot deal with large datasets and the latter is hard to deal with semantic segmentation. Therefore, in this work we propose a combination of both to create a novel pipeline of weak supervision, with focus in satellite imagery, capable of dealing with large datasets. We propose a pipeline to automatically generate scribbles in images, requiring that the user only label 10% of the images in a given dataset, while a classifier deal with the remaining images. Along with that, we also propose a simple semantic segmentation pipeline, that uses only images with scribbles to train a network. Results show that performance is lower, but similar to a fully supervised pipeline.

show abstract

Analysis of aerial images for identification of houses using big data, UAV photography and neural network

Jia

Sun

2023

Soft Comput

View full text Add to dashboard Cite

Unsupervised Semantic Segmentation of Aerial Images With Application to UAV Localization

Cited by 5 publications

References 19 publications

A Method of Image Semantic Segmentation Based on PSPNet

A Method of Image Semantic Segmentation Based on PSPNet

Weaklier Supervised: Semi-automatic Scribble Generation Applied to Semantic Segmentation

Analysis of aerial images for identification of houses using big data, UAV photography and neural network

Contact Info

Product

Resources

About