LIDAR vs dense image matching point clouds in complex urban scenes

Maltezos, Evangelos; Kyrkou, Athanasia; Ioannidis, Charalabos

doi:10.1117/12.2240475

Cited by 14 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two datasets from ALS were taken as reference data. Similar work taking laser scanning data as reference can also be found in (Poon et al 2005;Kraus et al, 2006;Gehrke et al, 2008;Moussa et al, 2013;Remondino et al 2014;Nex et al, 2015;Jaud et al, 2016;Maltezos et al, 2016;Sofia et al, 2016;Ressl et al 2016).…”

Section: Related Worksupporting

confidence: 54%

“…Airborne laser scanning (ALS) and photogrammetry are two main techniques to obtain 3D data representing the surface of the terrain (Höhle and Höhle, 2009). Compared with airborne laser scanning, image acquisition in photogrammetry is mostly cheaper and more efficient in data acquisition flights (Hobi and Ginzler, 2012;Nurminen et al, 2013;Maltezos et al 2016). In many countries photogrammetric image blocks are captured anyway for administrative and planning purposes with decreasing time intervals, so the question is to what extent these data can be used to replace ALS data in various application domains such as Digital Terrain Model (DTM) acquisition (Ressl et al, 2016), forestry mapping (Mura et al, 2015), classification and object extraction (Tomljenovic et al, 2016;Dong et al, 2017), and 3D modeling (Xiong et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A patch-based method for the evaluation of dense image matching quality

Zhang

Gerke²,

Vosselman

et al. 2018

International Journal of Applied Earth Observation and Geoinfor

View full text Add to dashboard Cite

Airborne laser scanning and photogrammetry are two main techniques to obtain 3D data representing the object surface. Due to the high cost of laser scanning, we want to explore the potential of using point clouds derived by dense image matching (DIM), as effective alternatives to laser scanning data. We present a framework to evaluate point clouds from dense image matching and derived Digital Surface Models (DSM) based on automatically extracted sample patches. Dense matching error and noise level are evaluated quantitatively at both the local level and whole block level. Experiments show that the optimal vertical accuracy achieved by dense matching is as follows: the mean offset to the reference data is 0.1 Ground Sampling Distance (GSD); the maximum offset goes up to 1.0 GSD. When additional oblique images are used in dense matching, the mean deviation, the variation of mean deviation and the level of random noise all get improved. We also detect a bias between the point cloud and DSM from a single photogrammetric workflow. This framework also allows to reveal inhomogeneity in the distribution of the dense matching errors due to over-fitted BBA network. Meanwhile, suggestions are given on the photogrammetric quality control.

show abstract

Section: Related Worksupporting

confidence: 54%

Section: Introductionmentioning

confidence: 99%

A patch-based method for the evaluation of dense image matching quality

Zhang

Gerke²,

Vosselman

et al. 2018

International Journal of Applied Earth Observation and Geoinfor

View full text Add to dashboard Cite

show abstract

“…Several state of the art frameworks can be found in literature that enable automatic initiation of NG112 call [29][30]. Such frameworks can fully contribute to critical infrastructure monitoring and buildings in complex urban scenes [31][32]. In detail, the SB112 components are a sensor node and a gateway.…”

Section: B Sb112mentioning

confidence: 99%

Public safety in smart cities under the edge computing concept

Maltezos

Karagiannidis

Dadoukis

et al. 2021

2021 IEEE International Mediterranean Conference on Communications and Networking (MeditCom)

Self Cite

View full text Add to dashboard Cite

The transformation of cities into smart cities is a crucial issue in improving the living conditions of the inhabitants. One of the major goals of the smart city concept is to modernize the urban management utilizing technical tools that offer stateof-the-art technologies. Recent years have disclosed a remarkable proliferation of compute-intensive safety and security applications in smart cities. Such applications continuously generate enormous amounts of data which demand strict latencyaware computational processing capabilities. To address the limitations of cloud computing for enabling real-time smart city environments, edge computing is a viable solution. Initially, this paper, discusses the trends, the requirements and the technologies for public safety in smart cities under an edge computing concept. Then, proposes the concept and the development of an edge computing platform, namely Distributed Edge Computing IoT Platform (DECIoT), integrating to a smart building sensing system with an NG112 call functionality and a chemical precursor spectroscopic system.

show abstract

“…Compared with Light Detection and Ranging (LiDAR), the image-based approach is a passive, pixel-wise, low-cost technology for obtaining the 3D structure of a scene that has a higher density and a finer topography. In difficult matching areas, such as shadows, low textures, and repeated textures, the image-based approach is often inaccurate, while LiDAR point clouds respond better in the above areas (Maltezos et al, 2016). Therefore, the complementary data fusion of LiDAR data and image data is a promising solution for generating dense, accurate, texture-rich point clouds (Huang et al, 2018).…”

Section: Introductionmentioning

confidence: 99%