Automatic building extraction from very high-resolution image and LiDAR data with SVM algorithm

Karslı, Fevzi; Dihkan, Mustafa; Acar, Hayrettin; Öztürk, Ali

doi:10.1007/s12517-016-2664-7

Cited by 25 publications

(17 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A false negative (FN) is an entity corresponding to an object in the reference that is classified as background, and a false positive (FP) is an entity classified as an object that does not correspond to an object in the reference. A true negative (TN) is an entity belonging to the background both in the classification and in the reference data (Rutzinger et al 2009;Shufelt 1999;Karsli et al 2016).…”

Section: Resultsmentioning

confidence: 99%

Automatic Extraction of Building Boundaries From High Resolution Images With Active Contour Segmentation

Akbulut¹,

Özdemir²,

Acar³

et al. 2018

International Journal of Engineering and Geosciences

Self Cite

View full text Add to dashboard Cite

Building extraction from remotely sensed images plays an important role in many applications such as updating geographical information system, change detection, urban planning, disaster management and 3D building modeling. Automatic extraction of buildings from aerial images is not an easy task because of background complexity, lighting conditions and vegetation cover that reduces separability or visibility of buildings. As a result, automatic building extraction can be a complex process for computer vision and image processing techniques.In order to overcome this difficulty region-based active contour model was used to automatically detect the boundary of buildings for this study. To extract object boundaries, the model grows or shrinks the initial contour in the image. The main objective of this paper is making active contours algorithm perform without user interaction and to detect automatically initial contours to segment buildings with a software coded in Matlab. This task carried out by morphological operations, band ratio and thresholding methods. In this study, high resolution aerial images with 8 cm ground sampling distance (GSD) were used. Three separate test zones were selected with varying building level of detail on these images. Finally, it was assessed the accuracy of segmented buildings using Correctness, Completeness and Quality metrics by comparing the results images and manually digitized reference image.The proposed approach for building extraction from images was shown to be 98% accurate on buildings with simple geometry and homogeneous roof textures. However accuracy of extracted buildings with heterogeneous roof textures and lighting, and complex geometry is 89%. The results clearly show that automatically calculated initial contour positions work in accordance with the active contour algorithm and easily extraction of the buildings boundaries.

show abstract

Section: Resultsmentioning

confidence: 99%

Automatic Extraction of Building Boundaries From High Resolution Images With Active Contour Segmentation

Akbulut¹,

Özdemir²,

Acar³

et al. 2018

International Journal of Engineering and Geosciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…LIDAR generates point clouds for digital surface models, digital elevation models and light intensity models. LIDAR has been used in the specially designed algorithms instead of optical sensor images to solve automatic building extraction problems (Canaz et al, 2015, Karsli et al, 2016 LIDAR provides more accurate height information but less accurate boundary lines.…”

Section: Building Detection Using Machine Learning Techniquementioning

confidence: 99%

“…LIDAR alone however can give better accuracy in vertical component in comparison to Airborne SAR which is imperative to produce 3D position of the ground. Point cloud produced by LIDAR also has been used in the specially designed algorithms instead of optical sensor images to solve automatic building extraction problems (Karsli et al, 2016;Michaelsen et al, 2005;Michaelsen, 2010) The LIDAR data can be used to characterize the elevation and object height information of the scene. (Karsli et al, 2016) proved that multi-features derived from combination of optical and LIDAR data can be successfully applied to solve the problem of automatic detection of buildings by using the proposed approach.…”

Section: Building Detection Using Machine Learning Techniquementioning

confidence: 99%

“…Point cloud produced by LIDAR also has been used in the specially designed algorithms instead of optical sensor images to solve automatic building extraction problems (Karsli et al, 2016;Michaelsen et al, 2005;Michaelsen, 2010) The LIDAR data can be used to characterize the elevation and object height information of the scene. (Karsli et al, 2016) proved that multi-features derived from combination of optical and LIDAR data can be successfully applied to solve the problem of automatic detection of buildings by using the proposed approach. LIDAR data provide a source of complementary information that can greatly assist in the classification of hyperspectral data, in particular when it is difficult to separate complex classes.…”

Section: Building Detection Using Machine Learning Techniquementioning

confidence: 99%

See 1 more Smart Citation

The Potential of Building Detection From Sar and Lidar Using Deep Learning

Nordin

Shafri

Abdullah

et al. 2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The introduction of airborne Synthetic Aperture Radar (SAR) approach has successfully addressed several challenges for mapping and surveying applications Unlike other conventional sensors, airborne SAR mapping approach offers practicality and significant cost savings for the nation minimizing the need for ground control points on the ground in addition to providing high-resolution, day-and-night, cloud coverage and weather independent images, which in turn provides faster turnaround times for creation of large area geospatial data. Up-to-date building map is necessary to guide the decision making in many fields to understand the urban dynamics such as in disaster management, population estimation, planning and many other applications. Whilst mapping and surveying work using airborne SAR have started to capture many interest among surveyors, professionals and practitioners abroad, Malaysia however is still lacking behind in term of the knowledge and the usage of this technology together with Deep Learning, Machine Learning approach especially in building extraction for topographic mapping and urban planning and development. Deep learning is a subset of the machine learning algorithm. Recently, Deep Learning has been proposed to solve traditional artificial intelligent problems. In order to develop a sustainable national geospatial infrastructure for years to come, the integration between airborne SAR and other sensors as such LIDAR is therefore essential in Malaysia and in high demand for urban planning and management. Thus, this paper reviews current techniques and future trends of multi-sources Remote Sensing for building extraction.

show abstract

“…Automatic extraction of building information while using unmanned aerial vehicles (UAVs), aerospace, and remote sensing satellite imagery is an important component in many fields, including illegal land use monitoring, land-use change, image interpretation, and cartography [1,2]. Dividing pixels into semantic objects is one of the most challenging and important issues in urban aviation and satellite imagery.…”

Section: Introductionmentioning

confidence: 99%

Accurate Building Extraction from Fused DSM and UAV Images Using a Chain Fully Convolutional Neural Network

et al. 2019

View full text Add to dashboard Cite

Accurate extraction of buildings using high spatial resolution imagery is essential to a wide range of urban applications. However, it is difficult to extract semantic features from a variety of complex scenes (e.g., suburban, urban and urban village areas) because various complex man-made objects usually appear heterogeneous with large intra-class and low inter-class variations. The automatic extraction of buildings is thus extremely challenging. The fully convolutional neural networks (FCNs) developed in recent years have performed well in the extraction of urban man-made objects due to their ability to learn state-of-the-art features and to label pixels end-to-end. One of the most successful FCNs used in building extraction is U-net. However, the commonly used skip connection and feature fusion refinement modules in U-net often ignore the problem of feature selection, and the ability to extract smaller buildings and refine building boundaries needs to be improved. In this paper, we propose a trainable chain fully convolutional neural network (CFCN), which fuses high spatial resolution unmanned aerial vehicle (UAV) images and the digital surface model (DSM) for building extraction. Multilevel features are obtained from the fusion data, and an improved U-net is used for the coarse extraction of the building. To solve the problem of incomplete extraction of building boundaries, a U-net network is introduced by chain, which is used for the introduction of a coarse building boundary constraint, hole filling, and "speckle" removal. Typical areas such as suburban, urban, and urban villages were selected for building extraction experiments. The results show that the CFCN achieved recall of 98.67%, 98.62%, and 99.52% and intersection over union (IoU) of 96.23%, 96.43%, and 95.76% in suburban, urban, and urban village areas, respectively. Considering the IoU in conjunction with the CFCN and U-net resulted in improvements of 6.61%, 5.31%, and 6.45% in suburban, urban, and urban village areas, respectively. The proposed method can extract buildings with higher accuracy and with clearer and more complete boundaries.

show abstract

Automatic building extraction from very high-resolution image and LiDAR data with SVM algorithm

Cited by 25 publications

References 40 publications

Automatic Extraction of Building Boundaries From High Resolution Images With Active Contour Segmentation

Automatic Extraction of Building Boundaries From High Resolution Images With Active Contour Segmentation

The Potential of Building Detection From Sar and Lidar Using Deep Learning

Accurate Building Extraction from Fused DSM and UAV Images Using a Chain Fully Convolutional Neural Network

Contact Info

Product

Resources

About