scholarly journals A 3D Reconstruction Pipeline of Urban Drainage Pipes Based on MultiviewImage Matching Using Low-Cost Panoramic Video Cameras

Water ◽  
2019 ◽  
Vol 11 (10) ◽  
pp. 2101 ◽  
Author(s):  
Zhang ◽  
Zhao ◽  
Hu ◽  
Wang ◽  
Ai ◽  
...  
Keyword(s):  
3D Reconstruction ◽  
High Precision ◽  
Image Matching ◽  
Low Cost ◽  
Geometric Distortion ◽  
Urban Drainage ◽  
Affine Invariant ◽  
Pipe Inspection ◽  
Video Cameras ◽  
Panoramic Video

Urban drainage pipe networks have complex spatial contributions, andthey are now facing problems such as damage, defects, and aging. A rapid and high-precision pipe inspection strategy is thekey to ensuring thesustainable development of urban water supply and drainage system. In this paper, a three-dimensional (3D) reconstruction pipeline of urban drainage pipes based on multiview image matching using low-cost panoramic video cameras is proposed, which provides an innovative technical approach for pipe inspection. Firstly, we extracted frames from the panoramic video of the pipes andcorrected the geometric distortion using a spherical reprojection to obtain multiview pipe images. Second, the robust feature matching method using support lines and affine-invariant ratios isintroduced to conduct pipe image matching. Finally, the photogrammetric processing, using structure from motion (SfM) and dense reconstruction, wasintroduced to achieve the 3D modeling of drainage pipes. Several typical drainage pipes and shafts of the real scenes were taken for the 3D reconstruction experiments. Theresults show that our strategy can realize high-precision 3D reconstruction of different types of pipes, which can provide effective technical support for rapid and efficient inspection of urban pipes with broad application prospects in the daily management of sustainable urban drainage systems (SUDSs).

scholarly journals Underwater High-Precision 3D Reconstruction System Based on Rotating Scanning

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1402
Author(s):  
Qingsheng Xue ◽  
Qian Sun ◽  
Fupeng Wang ◽  
Haoxuan Bai ◽  
Bai Yang ◽  
...  
Keyword(s):  
3D Reconstruction ◽  
High Precision ◽  
Laser Scanning ◽  
Low Cost ◽  
Three Dimensional ◽  
Reconstruction Error ◽  
Scanning System ◽  
Standard Sphere ◽  
Underwater Camera ◽  
The Impact

This paper presents an underwater high-precision line laser three-dimensional (3D) scanning (LLS) system with rotary scanning mode, which is composed of a low illumination underwater camera and a green line laser projector. The underwater 3D data acquisition can be realized in the range of field of view of 50° (vertical) × 360° (horizontal). We compensate the refraction of the 3D reconstruction system to reduce the angle error caused by the refraction of light on different media surfaces and reduce the impact of refraction on the image quality. In order to verify the reconstruction effect of the 3D reconstruction system and the effectiveness of the refraction compensation algorithm, we conducted error experiments on a standard sphere. The results show that the system’s underwater reconstruction error is less than 0.6 mm within the working distance of 140 mm~2500 mm, which meets the design requirements. It can provide reference for the development of low-cost underwater 3D laser scanning system.

Method on 3D Dense Point Cloud Recovery of Geographical Scene

2013 ◽  
Vol 748 ◽  
pp. 619-623 ◽  
Author(s):  
Yan Liang ◽  
Ye Hua Sheng ◽  
Ka Zhang
Keyword(s):  
Computer Vision ◽  
Virtual Reality ◽  
High Precision ◽  
Point Cloud ◽  
Low Cost ◽  
Experimental Results ◽  
Affine Invariant ◽  
Invariant Features ◽  
Dense Point

The object of this research is to reconstruct 3D dense point cloud of geographical scene. With the technology and method of computer vision , first affine invariant features are extracted and matched, then cameras parameters and 3D dense point cloud are recovered and united under geographical reference. The experimental results show that this method with low cost and high precision of centimeters can satisfy the requirements of measurement, modeling and virtual reality.

scholarly journals Towards a Fully Automated 3D Reconstruction System Based on LiDAR and GNSS in Challenging Scenarios

2021 ◽  
Vol 13 (10) ◽  
pp. 1981
Author(s):  
Ruike Ren ◽  
Hao Fu ◽  
Hanzhang Xue ◽  
Zhenping Sun ◽  
Kai Ding ◽  
...  
Keyword(s):  
3D Reconstruction ◽  
High Precision ◽  
Moving Objects ◽  
Autonomous Driving ◽  
Satellite System ◽  
Factor Graph ◽  
Mapping System ◽  
Global Navigation ◽  
Real World Datasets ◽  
Global Navigation Satellite

High-precision 3D maps play an important role in autonomous driving. The current mapping system performs well in most circumstances. However, it still encounters difficulties in the case of the Global Navigation Satellite System (GNSS) signal blockage, when surrounded by too many moving objects, or when mapping a featureless environment. In these challenging scenarios, either the global navigation approach or the local navigation approach will degenerate. With the aim of developing a degeneracy-aware robust mapping system, this paper analyzes the possible degeneration states for different navigation sources and proposes a new degeneration indicator for the point cloud registration algorithm. The proposed degeneracy indicator could then be seamlessly integrated into the factor graph-based mapping framework. Extensive experiments on real-world datasets demonstrate that the proposed 3D reconstruction system based on GNSS and Light Detection and Ranging (LiDAR) sensors can map challenging scenarios with high precision.

scholarly journals A Low-Cost Water Depth and Electrical Conductivity Sensor for Detecting Inputs into Urban Stormwater Networks

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3056
Author(s):  
Baiqian Shi ◽  
Stephen Catsamas ◽  
Peter Kolotelo ◽  
Miao Wang ◽  
Anna Lintern ◽  
...  
Keyword(s):  
Electrical Conductivity ◽  
Water Depth ◽  
Asset Management ◽  
Low Cost ◽  
Rate Of Change ◽  
Urban Drainage ◽  
Urban Stormwater ◽  
High Resolution Data ◽  
Conductivity Sensor ◽  
Level Sensor

High-resolution data collection of the urban stormwater network is crucial for future asset management and illicit discharge detection, but often too expensive as sensors and ongoing frequent maintenance works are not affordable. We developed an integrated water depth, electrical conductivity (EC), and temperature sensor that is inexpensive (USD 25), low power, and easily implemented in urban drainage networks. Our low-cost sensor reliably measures the rate-of-change of water level without any re-calibration by comparing with industry-standard instruments such as HACH and HORIBA’s probes. To overcome the observed drift of level sensors, we developed an automated re-calibration approach, which significantly improved its accuracy. For applications like monitoring stormwater drains, such an approach will make higher-resolution sensing feasible from the budget control considerations, since the regular sensor re-calibration will no longer be required. For other applications like monitoring wetlands or wastewater networks, a manual re-calibration every two weeks is required to limit the sensor’s inaccuracies to ±10 mm. Apart from only being used as a calibrator for the level sensor, the conductivity sensor in this study adequately monitored EC between 0 and 10 mS/cm with a 17% relative uncertainty, which is sufficient for stormwater monitoring, especially for real-time detection of poor stormwater quality inputs. Overall, our proposed sensor can be rapidly and densely deployed in the urban drainage network for revolutionised high-density monitoring that cannot be achieved before with high-end loggers and sensors.

scholarly journals An affine invariant approach for dense wide baseline image matching

2016 ◽  
Vol 12 (12) ◽  
pp. 155014771668082
Author(s):  
Fanhuai Shi ◽  
Jian Gao ◽  
Xixia Huang
Keyword(s):  
Image Matching ◽  
Intelligent Systems ◽  
Region Growing ◽  
Low Rank ◽  
Affine Invariant ◽  
Affine Transformations ◽  
Visual Sensor ◽  
Dense Matching ◽  
Rank Matrix ◽  
Distributed Intelligent Systems

Visual sensor networks have emerged as an important class of sensor-based distributed intelligent systems, where image matching is one of the key technologies. This article presents an affine invariant method to produce dense correspondences between uncalibrated wide baseline images. Under affine transformations, both point location and its neighborhood texture are changed between views, so dense matching becomes a tough task. The proposed approach tends to solve this problem within a sparse-to-dense framework. The contribution of this article is in threefolds. First, a strategy of reliable sparse matching is proposed, which starts from affine invariant features extraction and matching and then these initial matches are utilized as spatial prior to produce more sparse matches. Second, match propagation from sparse feature points to its neighboring pixels is conducted in the way of region growing in an affine invariant framework. Third, the unmatched points are handled by low-rank matrix recovery technique. Comparison experiments of the proposed method versus existing ones show a significant improvement in the presence of large affine deformations.

Sign in / Sign up

Export Citation Format

Share Document