3D terrain reconstruction of construction sites using a stereo camera

Sung, Chang Kyung; Kim, Pan Young

doi:10.1016/j.autcon.2015.12.022

Cited by 44 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chung and Kim (2015) presented a 3D reconstruction algorithm for stereo cameras and tested it on a construction site. They have reported that stereo camera integrated with their MSD based 3D reconstruction algorithms provides good performance with low computational time for autonomous control applications [7]. There have been studies which compared structure from motion (similar to stereo cameras technology) with laser scanning [8].It is reported that the structure from motion algorithms is less accurate than point clouds generated from laser scans.…”

Section: Past Workmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Handheld Devices for 3D Reconstruction in Construction

Senthilvel¹,

Soman²,

Varghese³

2017

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

-Generation and quality of as built models influence the subsequent applications such as progress monitoring, quality control, and deviation detection. The quality of any 3D reconstructed model heavily depends on the raw inputs and the post processing involved. While laser and LiDAR-based scanning are widely prevalent, lower cost equipment and sensors are increasingly becoming adaptable for 3D reconstruction. This study tests the feasibility of using IR-based scanning tablets and passive stereo vision cameras to acquire data from a construction environment based on the type of applications (such as progress monitoring, deviation detection) on a construction site. Two different off the shelf technologies: Tango tablet and ZED camera are tested during this research for developing as-built models using 3D reconstruction. The devices are compared on the basis of metrics such as preparation time for each scan, calibration of the scanner and total scanning time for determining the ease of scanning process, accuracy of generated point clouds. Also, the influence of external factors such as scanning parameters, ambient lighting, and characteristics of the object being scanned, and angle/orientation of scanner with respect to the object are studied.

show abstract

Section: Past Workmentioning

confidence: 99%

“…The methodology by Sung and Kim on a similar work is adopted for this test [7] [16]. The lengths of the major dimensions in each scan are measured in the scan data using MeshLab.…”

Section: Accuracy Of Scanmentioning

confidence: 99%

Comparison of Handheld Devices for 3D Reconstruction in Construction

Senthilvel¹,

Soman²,

Varghese³

2017

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

show abstract

“…However, there is a limit to their practical applications because of their computational complexity. In order to overcome this problem, MSD has been proposed for real practical vision application in challenging outdoor conditions [3,13]. Therefore, in order to find correspondence points, each extracted corner point is described by MSD in the proposed method.…”

Section: Matchingmentioning

confidence: 99%

“…This descriptor already has demonstrated its performance in outdoor applications such as motion estimation and dense 3D reconstruction [3,13]. Therefore, we also used the MSD to describe extracted corner points because of its distinctiveness and computational efficiency.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, the development of automated construction systems on construction sites for safety and convenience has attracted interest [1,2,3]. In order to operate an automated construction system, it is essential to understand the environment in which construction equipment operates, and the first step of environment recognition is terrain reconstruction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast and Robust 3D Terrain Surface Reconstruction of Construction site Using Stereo camera

Sung¹,

Lee²,

Kwon³

et al. 2016

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

Self Cite

View full text Add to dashboard Cite

-This paper presents a fast and robust threedimensional (3D) terrain surface reconstruction system using a stereo camera. The local featurebased 3D terrain surface reconstruction algorithm consists of two major steps: matching and terrain surface reconstruction. In this paper, extracted corners are described by multi-scale descriptors (MSDs), and the matching precision is increased by a quadratic interpolation method. In the terrain surface reconstruction step, the construction terrain surface is modeled using a 3D regular grid plane for its computational efficiency and robustness. The precision of the 3D regular grid plane is improved by inferring the 3D grid vertices from a robustly matched nearest point cloud. The computational complexity of the proposed terrain surface is simplified using 2D and 3D triangle mesh structures.In order to evaluate the proposed method, different types of 3D reconstruction methods were compared under the conditions of a practical construction site. The results of the experiment show that the MSD-based 3D terrain surface algorithm performed well in terms of robustness and computational efficiency.

show abstract