Performance evaluation of building detection and digital surface model extraction algorithms: Outcomes of the PRRS 2008 Algorithm Performance Contest

Aksoy, Selim; Ozdemir, Bahadir; Eckert, Sandra; Kayitakire, F.; Pesarasi, M.; Aytekin, Orsan; Borel, Christoph C.; Čech, Jan; Christophe, Emmanuel; Düzgün, Şebnem; Erener, Arzu; Ertugay, Kivanc; Hussain, Elima; Inglada, Jordi; Lefèvre, Sébastien; Ok, O.; San, D.; Šára, Radim; Shan, Jie; Soman, Jyothish; Ulusoy, İlkay; Witz, R.

doi:10.1109/prrs.2008.4783173

Cited by 13 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DeepGlobe Building Detection Challenge uses the SpaceNet Building Detection Dataset. Previous competitions on building extraction using satellite data, PRRS 2008 [10] and ISPRS [3,5], were based on small areas (a few km 2 ) and in some cases used a combination of opti-cal data and LiDAR data. The Inria Aerial Image Labeling covered 810km 2 area with 30cm resolution in various European and American cities [35].…”

Section: Building Detectionmentioning

confidence: 99%

See 1 more Smart Citation

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

Demir

Koperski

Lindenbaum

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

742

428

View full text Add to dashboard Cite

Figure 1: DeepGlobe Challenges: Example road extraction, building detection, and land cover classification training images superimposed on corresponding satellite images. AbstractWe present the DeepGlobe 2018 Satellite Image Understanding Challenge, which includes three public competitions for segmentation, detection, and classification tasks on satellite images ( Figure 1). Similar to other challenges in computer vision domain such as DAVIS[21] and COCO[33], DeepGlobe proposes three datasets and corresponding evaluation methodologies, coherently bundled in three competitions with a dedicated workshop co-located with CVPR 2018.We observed that satellite imagery is a rich and structured source of information, yet it is less investigated than everyday images by computer vision researchers. However, bridging modern computer vision with remote sensing data analysis could have critical impact to the way we understand our environment and lead to major breakthroughs in global urban planning or climate change research. Keeping such bridging objective in mind, DeepGlobe aims to bring together researchers from different domains to raise awareness of remote sensing in the computer vision community and vice-versa. We aim to improve and evaluate state-of-the-art satellite image understanding approaches, which can hopefully serve as reference benchmarks for future research in the same topic. In this paper, we analyze characteristics of each dataset, define the evaluation criteria of the competitions, and provide baselines for each task.

show abstract

Section: Building Detectionmentioning

confidence: 99%

“…Multiple performance measures can be applied to score participants. PRRS 2008 [10] challenge used 8 different performance measures. Our evaluation metric for this competition is an F1 score with the matching algorithm inspired by Algorithm 2 in the ILSVRC paper applied to the detection of building footprints [45].…”

Section: Building Detectionmentioning

confidence: 99%

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

Demir

Koperski

Lindenbaum

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

742

428

View full text Add to dashboard Cite

show abstract

“…Similarly, a stereo Ikonos data set with a highly accurate reference digital surface model (DSM) was supplied for comparing different DSM extraction algorithms. Aksoy et al (2008) presented the initial results from nine submissions for the building detection task and three submissions for the DSM extraction task.…”

Section: Introductionmentioning

confidence: 99%

Performance measures for object detection evaluation

Ozdemir

Aksoy

Eckert

et al. 2010

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

a b s t r a c tWe propose a new procedure for quantitative evaluation of object detection algorithms. The procedure consists of a matching stage for finding correspondences between reference and output objects, an accuracy score that is sensitive to object shapes as well as boundary and fragmentation errors, and a ranking step for final ordering of the algorithms using multiple performance indicators. The procedure is illustrated on a building detection task where the resulting rankings are consistent with the visual inspection of the detection maps.

show abstract

“…Segmentation of aerial imagery has been an active research area for more than two decades [4,17]. It is also one of the earliest applications of deep convolutional neural nets (CNN) [19].…”

Section: Introductionmentioning

confidence: 99%

Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery

Sun

Che

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Deep learning is revolutionizing the mapping industry. Under lightweight human curation, computer has generated almost half of the roads in Thailand on Open-StreetMap (OSM) using high resolution aerial imagery. Bing maps are displaying 125 million computer generated building polygons in the U.S. While tremendously more efficient than manual mapping, one cannot map out everything from the air. Especially for roads, a small prediction gap by image occlusion renders the entire road useless for routing. Misconnections can be more dangerous. Therefore computer based mapping often requires local verifications, which is still labor intensive. In this paper, we propose to leverage crowd sourced GPS data to improve and support road extraction from aerial imagery. Through novel data augmentation, GPS rendering, and 1D transpose convolution techniques, we show almost 5% improvements over previous competition winning models, and much better robustness when predicting new areas without any new training data or domain adaptation.

show abstract

Performance evaluation of building detection and digital surface model extraction algorithms: Outcomes of the PRRS 2008 Algorithm Performance Contest

Abstract: Abstract

Cited by 13 publications

References 21 publications

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

Performance measures for object detection evaluation

Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery

Contact Info

Product

Resources

About