ROOF TYPE SELECTION BASED ON PATCH-BASED CLASSIFICATION USING DEEP LEARNING FOR HIGH RESOLUTION SATELLITE IMAGERY

3D building reconstruction from remote sensing image data from satellites is still an active research topic and very valuable for 3D city modelling. The roof model is the most important component to reconstruct the Level of Details 2 (LoD2) for a building in 3D modelling. While the general solution for roof modelling relies on the detailed cues (such as lines, corners and planes) extracted from a Digital Surface Model (DSM), the correct detection of the roof type and its modelling can fail due to low quality of the DSM generated by dense stereo matching. To reduce dependencies of roof modelling on DSMs, the pansharpened satellite images as a rich resource of information are used in addition. In this paper, two strategies are employed for roof type classification. In the first one, building roof types are classified in a state-of-the-art supervised pre-trained convolutional neural network (CNN) framework. In the second strategy, deep features from deep layers of different pre-trained CNN model are extracted and then an RBF kernel using SVM is employed to classify the building roof type. Based on roof complexity of the scene, a roof library including seven types of roofs is defined. A new semi-automatic method is proposed to generate training and test patches of each roof type in the library. Using the pre-trained CNN model does not only decrease the computation time for training significantly but also increases the classification accuracy.

Download Full-text

A DETAILED STUDY ABOUT DIGITAL SURFACE MODEL GENERATION USING HIGH RESOLUTION SATELLITE STEREO IMAGERY

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsannals-iii-1-69-2016 ◽

2016 ◽

Vol III-1 ◽

pp. 69-76 ◽

Cited By ~ 3

Author(s):

K. Gong ◽

D. Fritsch

Keyword(s):

High Resolution ◽

Stereo Matching ◽

Research Area ◽

Surface Model ◽

Polynomial Coefficients ◽

Rational Polynomial ◽

Dense Stereo Matching ◽

Stereo Imagery ◽

Satellite Sensors ◽

High Resolution Satellite Imagery

Photogrammetry is currently in a process of renaissance, caused by the development of dense stereo matching algorithms to provide very dense Digital Surface Models (DSMs). Moreover, satellite sensors have improved to provide sub-meter or even better Ground Sampling Distances (GSD) in recent years. Therefore, the generation of DSM from spaceborne stereo imagery becomes a vivid research area. This paper presents a comprehensive study about the DSM generation of high resolution satellite data and proposes several methods to implement the approach. The bias-compensated Rational Polynomial Coefficients (RPCs) Bundle Block Adjustment is applied to image orientation and the rectification of stereo scenes is realized based on the Project-Trajectory-Based Epipolarity (PTE) Model. Very dense DSMs are generated from WorldView-2 satellite stereo imagery using the dense image matching module of the C/C++ library LibTsgm. We carry out various tests to evaluate the quality of generated DSMs regarding robustness and precision. The results have verified that the presented pipeline of DSM generation from high resolution satellite imagery is applicable, reliable and very promising.

Download Full-text

A DETAILED STUDY ABOUT DIGITAL SURFACE MODEL GENERATION USING HIGH RESOLUTION SATELLITE STEREO IMAGERY

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-iii-1-69-2016 ◽

2016 ◽

Vol III-1 ◽

pp. 69-76

Author(s):

K. Gong ◽

D. Fritsch

Keyword(s):

High Resolution ◽

Stereo Matching ◽

Research Area ◽

Surface Model ◽

Polynomial Coefficients ◽

Rational Polynomial ◽

Dense Stereo Matching ◽

Stereo Imagery ◽

Satellite Sensors ◽

High Resolution Satellite Imagery

Download Full-text

AIRCRAFT BASED REAL TIME BUNDLE ADJUSTMENT AND DIGITAL SURFACE MODEL GENERATION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-w13-1643-2019 ◽

2019 ◽

Vol XLII-2/W13 ◽

pp. 1643-1647

Author(s):

P. d’Angelo ◽

F. Kurz

Keyword(s):

Real Time ◽

Stereo Matching ◽

Bundle Adjustment ◽

Surface Model ◽

Time Data ◽

Solution Quality ◽

Camera System ◽

Dense Stereo Matching ◽

Surface Models ◽

Real Time Data Processing

<p><strong>Abstract.</strong> This paper introduces a system for real-time generation of digital surface models (DSM) based on an optical multi-camera system flown on board of a manned airplane or helicopter. The system consists of high end consumer cameras, GNSS/IMU system, and on-board computers for real-time data processing. Usually, generation of digital surface models from aerial imagery is done in an off-line process, leading to delayed availability of height data. The proposed system processes data in real time on board of the aircraft and downlinks the generated DSM to a ground station. This paper evaluates the GNSS/IMU on-line solution quality and its impact on dense stereo matching. The proposed real time sliding window based bundle adjustment significantly improves image orientations and DSM quality, allowing generation of detailed digital surface models with a resolution of 2*GSD. Experiments using two flight patterns are conducted over the city of Landsberg and the resulting DSMs are evaluated against a LiDAR generated reference point cloud. The online bundle adjustment is shown to minimize the effect of systematic GNSS/IMU offsets while adding only a limited delay.</p>

Download Full-text

Building Roof Component Extraction from Panchromatic Satellite Images Using a Clustering-Based Method

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsarchives-xl-3-247-2014 ◽

2014 ◽

Vol XL-3 ◽

pp. 247-252 ◽

Cited By ~ 2

Author(s):

T. Partovi ◽

R. Bahmanyar ◽

T. Krauß ◽

P. Reinartz

Keyword(s):

Satellite Images ◽

Surface Model ◽

Reconstruction Method ◽

Reconstruction Problem ◽

Building Roof ◽

Building Model ◽

3D Building Model ◽

Fully Automatic ◽

Active Research ◽

Automatic Systems

Developing fully automatic systems is still an active research topic in 3D building model reconstruction. While a general solution to the building reconstruction problem relies on collecting and grouping the modeling cues (e.g., lines, corners, planes) from Digital Surface Model (DSM) data, failure in finding the cues due to noise in the DSM and the object complexities is a big challenge. In this paper, we introduce a clustering-based method for cue discovery from Pan-chromatic satellite images which reduces the dependencies of the reconstruction techniques on DSM data. Experimental results show that the proposed method is not only able to effectively refine building masks by discriminating building boundaries from nearby clutter, but also is able to determine the roof types (e.g., pitched, flat). The latter, allows to establish a reconstruction method to reduces the search effort and the failure probability regions in finding a particular cue by leading the system to an appropriate area.

Download Full-text

Dense stereo matching by region growing based on disparity space sampling

Journal of Computer Applications ◽

10.3724/sp.j.1087.2009.02690 ◽

2009 ◽

Vol 29 (10) ◽

pp. 2690-2692

Author(s):

Bao-hai YANG ◽

Xiao-li LIU ◽

Dai-feng ZHA

Keyword(s):

Stereo Matching ◽

Region Growing ◽

Dense Stereo Matching ◽

Disparity Space

Download Full-text

Intelligent vehicle modeling design based on image processing

International Journal of Advanced Robotic Systems ◽

10.1177/1729881421993347 ◽

2021 ◽

Vol 18 (1) ◽

pp. 172988142199334

Author(s):

Guangchao Zhang ◽

Junrong Liu

Keyword(s):

Image Data ◽

Front Face ◽

Intelligent Vehicle ◽

Surface Model ◽

Data Sets ◽

Face Modeling ◽

Shape Coefficient ◽

Automotive Market ◽

Modeling Analysis ◽

Family Analysis

With the urgent demand of consumers for diversified automobile modeling, simple, efficient, and intelligent automobile modeling analysis and modeling method is an urgent problem to be solved in current automobile modeling design. The purpose of this article is to analyze the modeling preference and trend of the current automobile market in time, which can assist the modeling design of new models of automobile main engine factories and strengthen their branding family. Intelligent rapid modeling shortens the current modeling design cycle, so that the product rapid iteration is to occupy an active position in the automotive market. In this article, aiming at the family analysis of automobile front face, the image database of automobile front face modeling analysis was created. The database included two data sets of vehicle signs and no vehicle signs, and the image data of vehicle front face modeling of most models of 22 domestic mainstream brands were collected. Then, this article adopts the image classification processing method in computer vision to conduct car brand classification training on the database. Based on ResNet-8 and other model architectures, it trains and classifies the intelligent vehicle brand classification database with and without vehicle label. Finally, based on the shape coefficient, a 3D wireframe model and a curved surface model are obtained. The experimental results show that the 3D curve model can be obtained based on a single image from any angle, which greatly shortens the modeling period by 92%.

Download Full-text

Spatio-Temporal Change Monitoring of Outside Manure Piles Using Unmanned Aerial Vehicle Images

Drones ◽

10.3390/drones5010001 ◽

2020 ◽

Vol 5 (1) ◽

pp. 1

Author(s):

Geonung Park ◽

Kyunghun Park ◽

Bonggeun Song

Keyword(s):

Point Source ◽

Laser Scanning ◽

Image Data ◽

Surface Model ◽

Point Source Pollution ◽

Efficient Management ◽

Aerial Vehicle ◽

Spatio Temporal ◽

Agricultural Areas ◽

Water Quality Deterioration

Water quality deterioration due to outdoor loading of livestock manure requires efficient management of outside manure piles (OMPs). This study was designed to investigate OMPs using unmanned aerial vehicles (UAVs) for efficient management of non-point source pollution in agricultural areas. A UAV was used to acquire image data, and the distribution and cover installation status of OMPs were identified through ortho-images; the volumes of OMP were calculated using digital surface model (DSM). UAV- and terrestrial laser scanning (TLS)-derived DSMs were compared for identifying the accuracy of calculated volumes. The average volume accuracy was 92.45%. From April to October, excluding July, the monthly average volumes of OMPs in the study site ranged from 64.89 m3 to 149.69 m3. Among the 28 OMPs investigated, 18 were located near streams or agricultural waterways. Establishing priority management areas among the OMP sites distributed in a basin is possible using spatial analysis, and it is expected that the application of UAV technology will contribute to the efficient management of OMPs and other non-point source pollutants.

Download Full-text