Detection of Pictorial Map Objects with Convolutional Neural Networks

Schnürer, Raimund; Sieber, René; Schmid-Lanter, Jost; Öztireli, A. Cengiz; Hurni, Lorenz

doi:10.1080/00087041.2020.1738112

Cited by 14 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We set the anchor stride to eight, which has been favourable to detect smaller objects (e.g. Schnürer et al, 2020). We vary the four sizes for the anchors (minimum: 0.0625, maximum: 2.0) and retain their three aspect ratios (i.e.…”

Section: Methodsmentioning

confidence: 99%

Instance Segmentation, Body Part Parsing, and Pose Estimation of Human Figures in Pictorial Maps

Schnürer

Öztireli

Heitzler

et al. 2021

International Journal of Cartography

Self Cite

View full text Add to dashboard Cite

In recent years, convolutional neural networks (CNNs) have been applied successfully to recognise persons, their body parts and pose keypoints in photos and videos. The transfer of these techniques to artificially created images is rather unexplored, though challenging since these images are drawn in different styles, body proportions, and levels of abstraction. In this work, we study these problems on the basis of pictorial maps where we identify included human figures with two consecutive CNNs: We first segment individual figures with Mask R-CNN, and then parse their body parts and estimate their poses simultaneously with four different UNet++ versions. We train the CNNs with a mixture of real persons and synthetic figures and compare the results with manually annotated test datasets consisting of pictorial figures. By varying the training datasets and the CNN configurations, we were able to improve the original Mask R-CNN model and we achieved moderately satisfying results with the UNet++ versions. The extracted figures may be used for animation and storytelling and may be relevant for the analysis of historic and contemporary maps.

show abstract

Section: Methodsmentioning

confidence: 99%

Instance Segmentation, Body Part Parsing, and Pose Estimation of Human Figures in Pictorial Maps

Schnürer

Öztireli

Heitzler

et al. 2021

International Journal of Cartography

Self Cite

View full text Add to dashboard Cite

show abstract

“…Gan, the generative countermeasure technology in deep learning, can complete similar functions [45] . Some hand drawing functions (pencil drawing) and manual watercolor design) can also complete the design of personalized map symbols and graphic layout through this in-depth learning method [46] . The application of DL technology makes map design introduce strange artistic forms under the condition of ensuring the scientific content, and finds a new way for the combination of science and art.…”

Section: Map Symbol Design and Visual Style Expression Under DL Modelmentioning

confidence: 99%

Some thoughts on deep learning empowering cartography

2022

JGC

View full text Add to dashboard Cite

Cartography includes two major tasks: map making and map application, which is inextricably linked to artificial intelligence technology. The cartographic expert system experienced the intelligent expression of symbolism. After the spatial optimization decision of behaviorism intelligent expression, cartography faces the combination of deep learning under connectionism to improve the intelligent level of cartography. This paper discusses three problems about the proposition of “deep learning + cartography”. One is the consistency between the deep learning method and the map space problem solving strategy, based on gradient descent, local correlation, feature reduction and non-linear nature that answer the feasibility of the combination of “deep learning + cartography”; the second is to analyze the challenges faced by the combination of cartography from its unique disciplinary characteristics and technical environment, involving the non-standard organization of map data, professional requirements for sample establishment, the integration of geometric and geographical features, as well as the inherent spatial scale of the map; thirdly, the entry points and specific methods for integrating map making and map application into deep learning are discussed respectively.

show abstract

“…The main application of deep learning techniques in geographical information science is remote sensing, e.g. (Zhu et al, 2017), but these techniques also prove successful to recognise features from map images Touya and Lokhat, 2018) or to classify map images (Schnürer et al, 2020;Hu et al, 2021). But our focus is on map generalisation (Du et al, 2021;Feng et al, 2019;Courtial et al, 2020a), so we are more interested in deep architectures that can generate a map image.…”

Section: Generating Maps With Deep Learningmentioning

confidence: 99%

Representing Vector Geographic Information As a Tensor for Deep Learning Based Map Generalisation

Courtial

Touya

Zhang

2022

AGILE GIScience Ser.

View full text Add to dashboard Cite

Abstract. Recently, many researchers tried to generate (generalised) maps using deep learning, and most of the proposed methods deal with deep neural network architecture choices. Deep learning learns to reproduce examples, so we think that improving the training examples, and especially the representation of the initial geographic information, is the key issue for this problem. Our article extracts some representation issues from a literature review and proposes different ways to represent vector geographic information as a tensor.We propose two kinds of contributions: 1) the representation of information by layers; 2) the representation of additional information. Then, we demonstrate the interest of some of our propositions with experiments that show a visual improvement for the generation of generalised topographic maps in urban areas.

show abstract

Detection of Pictorial Map Objects with Convolutional Neural Networks

Cited by 14 publications

References 37 publications

Instance Segmentation, Body Part Parsing, and Pose Estimation of Human Figures in Pictorial Maps

Instance Segmentation, Body Part Parsing, and Pose Estimation of Human Figures in Pictorial Maps

Some thoughts on deep learning empowering cartography

Representing Vector Geographic Information As a Tensor for Deep Learning Based Map Generalisation

Contact Info

Product

Resources

About