The ISPRS benchmark on urban object classification and 3D building reconstruction

By Franz Rottensteiner, Gunho Sohn, Jaewook Jung, Markus Gerke, Caroline Baillard, S. Bénitez, U. Breitkopf. 2012

536 citations recorded by the source corpus.

For more than two decades, many efforts have been made to develop methods for extracting urban objects from data acquired by airborne sensors. In order to make the results of such algorithms more comparable, benchmarking data sets are of paramount importance. Such a data set, consisting of airborne image and laserscanner data, has been made available to the scientific community. Researchers were encouraged to submit results of urban object detection and 3D building reconstruction, which were evaluated based on reference data. This paper presents the outcomes of the evaluation for building detection, tree detection, and 3D building reconstruction. The results achieved by different methods are compared and analysed to identify promising strategies for automatic urban object extraction from current airborne sensor data, but also common problems of state-of-the-art methods.

Subfields: Environmental Engineering, Geology, Ocean Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Environmental Engineering

In Geology

In Ocean Engineering

Citations in the corpus

Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation (2022, background): “dataset [14] to learn the features of the encoder of the net that solves the segmentation.”
A review of deep learning methods for semantic segmentation of remote sensing imagery (2021, background): “Such objects and background need accurate delineation to facilitate further extraction of geometric properties such as width and perimeter (Dechesne et al., 2017; Rottensteiner et al., 2012; Volpi & Ferrari, 2015).”
Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks (2016, methodology): “This approach improves previous results on the ISPRS Vaihingen 2D labeling challenge, reaching 89.4% 3 (cf. Table 3).”
Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery (2020, background): “mote sensing imagery is very helpful for urban management, planing and monitoring [39, 40, 25, 26].”
Self-Supervised Remote Sensing Feature Learning: Learning Paradigms, Challenges, and Future Works (2022, background): “a) Potsdam [254], one of the most popular semantic segmentation datasets in the RS field.”
Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning (2017, methodology): “The ISPRS datasets are the only comparable datasets, but these datasets only use 3–4 spectral bands and 5 object classes.”
Weakly-Supervised Continual Learning for Class-Incremental Segmentation (2022, methodology): “We evaluate our approach on the ISPRS Potsdam & Vaihingen datasets [13] respectively composed of 38 (6000× 6000 pxls, 5cm res.”
Geographical Knowledge-Driven Representation Learning for Remote Sensing Images (2021, methodology): “We demonstrate our method’s effectiveness in semantic segmentation of remote sensing images using the Potsdam and Vaihingen datasets [58].”
FALSE: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image (2022, unknown): “The experiments were selected from the public RSI semantic segmentation dataset ISPRS Potsdam [24], competition dataset CVPR DGLC [25], and Xiangtan dataset [10] from the Gaofen-2 satellite covering Xiangtan, China.”
Unsupervised Single-Scene Semantic Segmentation for Earth Observation (2022, background): “1) Vaihingen dataset, an urban semantic segmentation benchmark [22], [62] acquired over Vaihingen, Germany, with 9 cm/pixel resolution.”
MARE: Self-Supervised Multi-Attention REsu-Net for Semantic Segmentation in Remote Sensing (2021, methodology): “Experimental results on Vaihingen dataset [28] w.”
Contextual classification of lidar data and building object detection in urban areas (2014, methodology): “The performance of our method is evaluated on the LiDAR data set of Vaihingen, Germany (Cramer, 2010), in the context of the ISPRS Test Project on Urban Classification and 3D Building Reconstruction (Rottensteiner et al., 2012).”