Methods and datasets on semantic segmentation: A review

Huang, Yu; Yang, Zhengeng; Tan, Lei; Wang, Yaonan; Sun, Wei; Sun, Mingui; Tang, Yandong

doi:10.1016/j.neucom.2018.03.037

Cited by 202 publications

(90 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, geographic features must be identified and classified. Different techniques have been developed: histogram thresholding, color space clustering, edge detection, region-based approaches, artificial neural networks and semantic segmentation [20,44]. Aiming to extract LULC classes from maps with very different features, the OBIA technique has been used for the classification, with the segmentation of the maps using a region-based approach and successive segment classification using machine learning.…”

Section: Historical Map Digitalizationmentioning

confidence: 99%

New Tools for the Classification and Filtering of Historical Maps

Gobbi

Ciolli

Porta

et al. 2019

IJGI

View full text Add to dashboard Cite

Historical maps constitute an essential information for investigating the ecological and landscape features of a region over time. The integration of heritage maps in GIS models requires their digitalization and classification. This paper presents a semi-automatic procedure for the digitalization of heritage maps and the successive filtering of undesirable features such as text, symbols and boundary lines. The digitalization step is carried out using Object-based Image Analysis (OBIA) in GRASS GIS and R, combining image segmentation and machine-learning classification. The filtering step is performed by two GRASS GIS modules developed during this study and made available as GRASS GIS add-ons. The first module evaluates the size of the filter window needed for the removal of text, symbols and lines; the second module replaces the values of pixels of the category to be removed with values of the surrounding pixels. The procedure has been tested on three maps with different characteristics, the “Historical Cadaster Map for the Province of Trento” (1859), the “Italian Kingdom Forest Map” (1926) and the “Map of the potential limit of the forest in Trentino” (1992), with an average classification accuracy of 97%. These results improve the performance of classification of heritage maps compared to more classical methods, making the proposed procedure that can be applied to heterogeneous sets of maps, a viable approach.

show abstract

Section: Historical Map Digitalizationmentioning

confidence: 99%

New Tools for the Classification and Filtering of Historical Maps

Gobbi

Ciolli

Porta

et al. 2019

IJGI

View full text Add to dashboard Cite

show abstract

“…Then, a CNN could be used as an image-patch classifier to capture the neighborhood context [69,70]. However, these methods are highly demanding in terms of computing resources and do not consider information from a sufficiently wide context for semantic segmentation [12].…”

Section: Semantic Segmentation Via Deep Learningmentioning

confidence: 99%

“…Recently, through technological advances, deep learning has generated results comparable to or in some cases superior to human experts [8][9][10]. For semantic segmentation, by enabling efficient learning and powerful feature representations, deep learning has considerably improved the prediction's reliability for many computer vision applications involving general images and videos [11,12] as well as medical images [13,14]. As an efficient means of deep learning to analyze visual imagery like semantic segmentation, convolutional neural network (CNN) employs a mathematical linear operation called convolution in at least one of its layers in place of general matrix multiplication used in the fully connected neural network to assemble complex patterns using smaller and simpler patterns with less hand-engineered requirement [15].…”

Section: Introductionmentioning

confidence: 99%

“…As for recent developments of semantic segmentation, in 2015, the concept of a fully convolutional network (FCN) was first proposed [16], in which the fully connected layer connected to the last convolutional layers in a CNN is replaced with a low-resolution convolutional layer to improve computing efficiency using CNN. In contrast to previous naïve approaches using convolutional layers as image-patch classifiers or feature extractors for pixelwise classification, FCNs offer considerably improved learning efficiency for semantic segmentation and have driven most recent advances in this field [12]. In addition, SegNet, a deep convolutional encoder-decoder architecture, was also proposed in 2015 [17] to save storage space by copying the pooling indices from the encoding to the decoding layers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images

2019

Remote Sensing

View full text Add to dashboard Cite

Semantic segmentation is a fundamental means of extracting information from remotely sensed images at the pixel level. Deep learning has enabled considerable improvements in efficiency and accuracy of semantic segmentation of general images. Typical models range from benchmarks such as fully convolutional networks, U-Net, Micro-Net, and dilated residual networks to the more recently developed DeepLab 3+. However, many of these models were originally developed for segmentation of general or medical images and videos, and are not directly relevant to remotely sensed images. The studies of deep learning for semantic segmentation of remotely sensed images are limited. This paper presents a novel flexible autoencoder-based architecture of deep learning that makes extensive use of residual learning and multiscaling for robust semantic segmentation of remotely sensed land-use images. In this architecture, a deep residual autoencoder is generalized to a fully convolutional network in which residual connections are implemented within and between all encoding and decoding layers. Compared with the concatenated shortcuts in U-Net, these residual connections reduce the number of trainable parameters and improve the learning efficiency by enabling extensive backpropagation of errors. In addition, resizing or atrous spatial pyramid pooling (ASPP) can be leveraged to capture multiscale information from the input images to enhance the robustness to scale variations. The residual learning and multiscaling strategies improve the trained model’s generalizability, as demonstrated in the semantic segmentation of land-use types in two real-world datasets of remotely sensed images. Compared with U-Net, the proposed method improves the Jaccard index (JI) or the mean intersection over union (MIoU) by 4-11% in the training phase and by 3-9% in the validation and testing phases. With its flexible deep learning architecture, the proposed approach can be easily applied for and transferred to semantic segmentation of land-use variables and other surface variables of remotely sensed images.

show abstract

“…Existing semantic segmentation methods can be divided into three categories: hand‐engineer feature based methods, learned feature based methods, and weakly‐ or semi‐ supervised methods [YYT∗ 18]. Due to recent advancements in deep learning, the second kind of methods has witnessed tremendous progress.…”

Section: Related Workmentioning

confidence: 99%

A Unified Neural Network for Panoptic Segmentation

Yao

Chyau

2019

Computer Graphics Forum

View full text Add to dashboard Cite

In this paper, we propose a unified neural network for panoptic segmentation, a task aiming to achieve more fine‐grained segmentation. Following existing methods combining semantic and instance segmentation, our method relies on a triple‐branch neural network for tackling the unifying work. In the first stage, we adopt a ResNet50 with a feature pyramid network (FPN) as shared backbone to extract features. Then each branch leverages the shared feature maps and serves as the stuff, things, or mask branch. Lastly, the outputs are fused following a well‐designed strategy. Extensive experimental results on MS‐COCO dataset demonstrate that our approach achieves a competitive Panoptic Quality (PQ) metric score with the state of the art.

show abstract

Methods and datasets on semantic segmentation: A review

Cited by 202 publications

References 52 publications

New Tools for the Classification and Filtering of Historical Maps

New Tools for the Classification and Filtering of Historical Maps

Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images

A Unified Neural Network for Panoptic Segmentation

Contact Info

Product

Resources

About