Mr. Lukas Lucks Profile

Lukas Lucks

at Fraunhofer IOSB

SPIE Involvement:

Author

Publications (2)

This will count as one of your downloads.

You will have access to both the presentation and article (if available).

DOWNLOAD NOW

This content is available for download via your institution's subscription. To access this item, please sign in to your personal account.

Email or Username Forgot your username?

Password Forgot your password?

Show

Keep me signed in

No SPIE account? Create an account

Proceedings Article | 9 October 2018 Paper

Evaluation of CNNs for land cover classification in high-resolution airborne images

Gisela Häufel, Lukas Lucks, Melanie Pohl, Dimitri Bulatov, Hendrik Schilling

Proceedings Volume 10790, 1079003 (2018) https://doi.org/10.1117/12.2325604

KEYWORDS: Image segmentation, Classification systems, Buildings, Image classification, Roads, Vegetation, Image resolution, Network architectures, Convolution, Data processing

Read Abstract +

Semantic land cover classification of satellite images or airborne images is becoming increasingly important for applications like urban planning, road net analysis or environmental monitoring. Sensor orientations or varying illumination make classification challenging. Depending on image source and classification task, it is not always easy to name the most discriminative features for a successful performance. To avoid feature selection, we transfer aspects of a feature-based classification approach to Convolutional Neural Networks (CNNs) which internally generate specific features. As land covering classes, we focus on buildings, roads, low (grass) and high vegetation (trees). Two different approaches will be analyzed: The first approach, using InceptionResNetV2, stems from networks used for image recognition. The second approach constitutes a fully convolutional neural network (DeepLabV3+) and is typically used for semantic image segmentation. Before processing, the image needs to be subdivided into tiles. This is necessary to make the data processible for the CNN, as well as for computational reasons. The tiles working with InceptionResNetV2 are derived from a superpixel segmentation. The tiles for working with DeepLabV3+ are overlapping tiles of a certain size. The advantages of this CNN is that its architecture enables to up-sample the classification result automatically and to produce a pixelwise labeling of the image content. As evaluation data for both approaches, we used the ISPRS benchmark of the city Vaihingen, Germany, containing true orthophotos and ground truth labeled for classification.

Proceedings Article | 9 October 2018 Paper

HERACLES: EU-backed multinational project on cultural heritage preservation

Dimitri Bulatov, Lukas Lucks, Jürgen Moßgraber, Melanie Pohl, Peter Solbrig, Gabriele Murchio, Giuseppina Padeletti

Proceedings Volume 10790, 107900D (2018) https://doi.org/10.1117/12.2324661

KEYWORDS: Cultural heritage, Data modeling, Sensors, Unmanned aerial vehicles, 3D modeling, Climate change, Data acquisition

Read Abstract +

In 2016, the European Unions’ Research and Innovation program Horizon 2020 launched the multi-national project called HEritage Resiliance Against CLimatic Events on Site (HERACLES). The goal of this project is to design, validate and promote effective and sustainable solutions against potential threats climatic changes can bring about on the cultural heritage. For this purpose, knowledge and experiences of multiple research facilities and versatile groups of end-users in different European countries will be bundled and synergetically benefited of. In this paper, we will provide an overview about HERACLES project while a particular focus will be put on the activities concerning close-range Remote Sensing data processing. By exploiting image and laser data acquired from UAVs and from the ground, we strive for precise and reliable 3D models that are useful for representation of the scene on the desired level of detail and thus for assessing potential damages and estimating risks. From oblique UAV-borne imagery, we will obtain textured airborne 3D models using photogrammetric methods of image alignment, dense point cloud reconstruction, meshing and texturing. To provide coverage for the objects’ interiors, very dense point clouds from terrestrial laser scans can be additionally captured. A triangle mesh is obtained from these points and textured by means of terrestrial high-resolution photos, whereby the registration took place using a point-based method. We identified two main challenges: first, the reconstruction results from high-resolution UAV images were not always satisfying due to a low coverage; to cope with this, extensive interactive corrections must be undertaken. Moreover, seamless merging of triangle meshes provided by aerial photogrammetric reconstruction and by terrestrial laser scans is cumbersome because of varying density and accuracy of 3D points in both meshes.

My Library

You currently do not have any folders to save your paper to! Create a new folder below.

Folder Name

Folder Description

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks. You are receiving this notice because your organization may not have SPIE eBooks access.*

*Shibboleth/Open Athens users─please sign in to access your institution's subscriptions.

To obtain this item, you may purchase the complete book in print or electronic format on SPIE.org.

ORGANIZATIONAL
Sign in with credentials provided by your organization.

Organizational Username

Organizational Password

Show/Hide Password

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members:

Non-members: ADD TO CART

Keywords/Phrases

Search In:

Publication Years