Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Presentation at ISSDQ 2015 by Guillaume Touya
Search
Guillaume
October 09, 2026
Research
22
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Presentation at ISSDQ 2015 by Guillaume Touya
Guillaume
October 09, 2026
Transcript
35 slides
COMPARING IMAGE-BASED METHODS FOR ASSESSING VISUAL CLUTTER IN GENERALIZED MAPS
G. Touya – B. Decherf – M. Lalanne – M. Dumont COGIT team IGN France ISSDQ 2015 – Geospatial week
Evaluation of map generalization Accept or cancel Initial data Select
situation and algorithms Apply selected process evaluation required Map output
Evaluation of map generalization • User map requirements • Cartographic
rules Generalization constraints
Evaluation of map generalization • User map requirements • Cartographic
rules Generalization constraints « Building area > 0.4 map mm² » « Building granularity > 0.1 map mm » « Building/road distance > 0.1 map mm » « Building alignments should be preserved »
Evaluation of map generalization Constraints number 80 60 40 20
0 1 2 3 4 5 6 7 8 satisfaction scale
Evaluation of map generalization Constraints number 80 60 40 20
0 1 2 3 4 5 6 7 8 Global evaluation is complex! satisfaction scale
[Rylov & Reimer 2014] Using image-based evaluation
Clutter in computer vision Excessive and/or disorganized information
Edge density clutter
[Jégou & Deblonde 2012] Quad-tree based clutter
[Jégou & Deblonde 2012] Quad-tree based clutter
[Rosenholtz et al 2007] Subband entropy clutter Similar to jpeg
compression
[Jégou & Deblonde 2012] Subband entropy clutter
[Bravo & Farid 2008] Segmentation based clutter
Tested maps Initial data 1:15k symbols Initial data 1:50k symbols
Generalized data 1:50k symbols
Tested maps Before and after, manually generalized
[Touya & Duchêne 2011] Tested maps Before and after, automatically
generalized
Experiments
Identifying Too Cluttered Areas Initial map quad tree edges segmentation
Preserving the global amount of information 1:25k 1:100k 1:250k 1:1000k
Edge density Subband entropy 2000 1500 1000 500 0 10.5 10 9.5 9 8.5 8 0.15 0.1 0.05 0 Quad tree Segmentation 4000 3000 2000 1000 0
Preserving the global amount of information 1:25k 1:100k 1:250k 1:1000k
1500 Edge density Subband entropy 15 1000 10 500 5 0 0 0.2 0.15 0.1 0.05 0 Quad tree Segmentation 6000 4000 2000 0
Preserving the global amount of information 1:25k 1:100k Edge density
2000 1500 15 1:250k Subband entropy 10 1000 5 500 0 0 1:25k 1:100k 1:250k 1:25k 1:100k 1:250k Quad tree Segmentation 4000 0,1 0,08 0,06 0,04 0,02 0 3000 2000 1000 0 1:25k 1:100k 1:250k 1:25k 1:100k 1:250k
Handling of occlusions and overlaps Clutter measure Edge density Subband
entropy Quad tree Segmentation Before generalization After generalization 6664 9268 4.1 4.39 0.042 0.062 398 389
Handling of occlusions and overlaps Clutter measure Edge density Subband
entropy Quad tree Segmentation Before generalization After generalization 6664 9268 4.1 4.39 0.042 0.062 398 389
Handling of occlusions and overlaps Initial map Generalized map
Background and foreground Edge density Subband entropy Quad tree Segmentation
initial map 1432 4.91 0.058 1076 no background 2427 2.39 0.028 431 transparency 1543 4.17 0.028 633 paler shades 542 4.95 0.028 927
Background and foreground Edge density Subband entropy Quad tree Segmentation
initial map 1432 4.91 0.058 1076 no background 2427 2.39 0.028 431 transparency 1543 4.17 0.028 633 paler shades 542 4.95 0.028 927
Background and foreground Edge density Subband entropy Quad tree Segmentation
initial map 1432 4.91 0.058 1076 no background 2427 2.39 0.028 431 transparency 1543 4.17 0.028 633 paler shades 542 4.95 0.028 927
[Olsson et al 2011] Background and foreground Including contour lines
Excluding contour lines Legible cell Cluttered cell
Reduction of blank space Clutter measure Before generalization After generalization
Edge density 429 1459 Subband entropy 1.73 1.75 Quad tree 0.032 0.035 Segmentation 1630 1765
Reduction of blank space Clutter measure Before generalization After generalization
Edge density 429 1459 Subband entropy 1.73 1.75 Quad tree 0.032 0.035 Segmentation 1630 1765
Conclusion • Image-based clutter measures can be useful for generalization
evaluation • Clutter measures vary differently with generalization
What’s next? • Test other methods (feature congestion, color clustering,
crowding model…) • Compare with vector-based methods • Combine several complementary methods • Compare to generalization evaluation methods
Any Question? G. Touya – B. Decherf – M. Lalanne
– M. Dumont COGIT team IGN France ISSDQ 2015 – Geospatial week
Implementation detail • All is available in open source Java
platform GeOxygene • Use of OpenIMAJ library [Hare et al 2011] • Test images can be made available on demand for comparisons
More Decks by Guillaume
See All by Guillaume
Presentation at ICC'11 in Paris by Guillaume Touya on CollaGen
gtouya
0
17
ScaleMaster 2.0: a ScaleMaster extension to monitor automatic multi-scales generalizations - Presentation at ICC 2013
gtouya
0
15
Presentation by Guillaume Touya at GIScience conference 2012
gtouya
0
23
Other Decks in Research
See All in Research
山中市政の総括:相反する二つの顔
sishi
0
240
横浜市長(山中氏)の言動にかかる第三者による調査報告書
sishi2026
0
680
TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis
satai
3
130
論文読み会 SNLP2026 Tau2-Bench: Evaluating Conversational Agents in a Dual-Control Environment
s_mizuki_nlp
0
360
ros2-perf-multihost: 分散システムにおける客観的なアーキテクチャ評価フレームワーク
takasehideki
0
360
Who’s Behind the Divide?
sirmatrixpage
1
1.6k
L’albédo:levier d’atténuation du changement climatique dans les systèmes fourragers
institutdelelevage
PRO
0
170
実例から見るLLMのマンガ理解:実務VQAタスクによる長期的文脈と視覚情報の定性評価
kzmssk
0
230
Fixing broken labour markets: What can the UK and US learn from each other?
resolutionfoundation
0
110
最先端NLP勉強会2026 論文紹介:Reasoning with Sampling: Your Base Model is Smarter Than You Think (ICLR 2026 paper)
kogoro
4
980
AI創薬の壁
kanojikajino
1
1.3k
Prithvi-EO-2.0
satai
3
130
Featured
See All Featured
Test your architecture with Archunit
thirion
2
2.5k
Facilitating Awesome Meetings
lara
57
7.2k
The #1 spot is gone: here's how to win anyway
tamaranovitovic
4
1.2k
Optimising Largest Contentful Paint
csswizardry
37
4k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
11
1.1k
Faster Mobile Websites
deanohume
310
32k
We Are The Robots
honzajavorek
0
460
Accessibility Awareness
sabderemane
1
310
The Impact of AI in SEO - AI Overviews June 2024 Edition
aleyda
6
1.3k
svc-hook: hooking system calls on ARM64 by binary rewriting
retrage
2
690
30 Presentation Tips
portentint
PRO
1
480
KATA
mclloyd
PRO
35
16k