Three-dimensional CityGML building models in mobile augmented reality: a smartphone-based pose tracking system

Blut, Christoph; Blankenbach, Jörg

doi:10.1080/17538947.2020.1733680

Cited by 21 publications

(12 citation statements)

References 42 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consecutive images are successively registered in the local model coordinate system utilizing 2D- to 3D-point correspondences as described in [ 40 ]. Therefore, with the correspondences of 2D feature points of a considered image and 3D world points triangulated by previous image pairs, we solve the perspective-n-point (PnP) problem [ 41 ].…”

Section: Methodsmentioning

confidence: 99%

A Novel Camera-Based Measurement System for Roughness Determination of Concrete Surfaces

2020

Self Cite

View full text Add to dashboard Cite

Determining the roughness of technical surfaces is an important task in many engineering disciplines. In civil engineering, for instance, the repair and reinforcement of building component parts (such as concrete structures) requires a certain surface roughness in order to ensure the bond between a coating material and base concrete. The sand patch method is so far the state-of-the-art for the roughness measurement of concrete structures. Although the method is easy to perform, it suffers from considerable drawbacks. Consequently, more sophisticated measurement systems are required. In a research project, we developed a novel camera-based alternative, which comes with several advantages. The measurement system consists of a mechanical cross slide that guides an industrial camera over a surface to be measured. Images taken by the camera are used for 3D reconstruction. Finally, the reconstructed point clouds are used to estimate roughness. In this article, we present our measurement system (including the hardware and the self-developed software for 3D reconstruction). We further provide experiments to camera calibration and evaluation of our system on concrete specimens. The resulting roughness estimates for the concrete specimens show a strong linear correlation to reference values obtained by the sand patch method.

show abstract

Section: Methodsmentioning

confidence: 99%

A Novel Camera-Based Measurement System for Roughness Determination of Concrete Surfaces

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The visualization of the CIM data can not only help people better understand the city but also assist in decision-making at all stages of the city life cycle [12,[40][41][42][43]. Therefore, the CIM visualizations integrating VR and augmented reality (AR) have drawn the main research concerns (see Table 3).…”

Section: Data Visualizationmentioning

confidence: 99%

City Information Modeling: State of the Art

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

The concept of city information modeling (CIM) has become increasingly popular in recent years. A literature review of previous CIM studies is presented in this paper. First, a bibliometric analysis of the current global CIM research is described, revealing that CIM has become a significant research hotspot. Next, three main research areas of the current CIM technique, namely data collection, integration, and visualization, are summarized to describe the characteristics of CIM research. Furthermore, some widely used CIM platforms are compared, and typical application cases of the CIM technique at different stages of the city life cycle are summarized. Finally, the current issues in CIM research are discussed, and future development directions are proposed. The findings of this study are expected to help researchers understand the current state of CIM and identify future development directions, thereby promoting CIM research development.

show abstract

“…In recent years, Computer Vision has been involved in several, heterogeneous tasks which include rehabilitation [1][2][3][4][5], virtual/augmented reality [6][7][8][9][10], deception detection [11][12][13][14], robotics [15][16][17][18][19], and much more. Focusing on the latter, one of the most prominent applications involves the usage of drones (hereinafter, UAVs).…”

Section: Introductionmentioning

confidence: 99%

MS-Faster R-CNN: Multi-Stream Backbone for Improved Faster R-CNN Object Detection and Aerial Tracking from UAV Images

et al. 2021

View full text Add to dashboard Cite

Tracking objects across multiple video frames is a challenging task due to several difficult issues such as occlusions, background clutter, lighting as well as object and camera view-point variations, which directly affect the object detection. These aspects are even more emphasized when analyzing unmanned aerial vehicles (UAV) based images, where the vehicle movement can also impact the image quality. A common strategy employed to address these issues is to analyze the input images at different scales to obtain as much information as possible to correctly detect and track the objects across video sequences. Following this rationale, in this paper, we introduce a simple yet effective novel multi-stream (MS) architecture, where different kernel sizes are applied to each stream to simulate a multi-scale image analysis. The proposed architecture is then used as backbone for the well-known Faster-R-CNN pipeline, defining a MS-Faster R-CNN object detector that consistently detects objects in video sequences. Subsequently, this detector is jointly used with the Simple Online and Real-time Tracking with a Deep Association Metric (Deep SORT) algorithm to achieve real-time tracking capabilities on UAV images. To assess the presented architecture, extensive experiments were performed on the UMCD, UAVDT, UAV20L, and UAV123 datasets. The presented pipeline achieved state-of-the-art performance, confirming that the proposed multi-stream method can correctly emulate the robust multi-scale image analysis paradigm.

show abstract

Three-dimensional CityGML building models in mobile augmented reality: a smartphone-based pose tracking system

Cited by 21 publications

References 42 publications

A Novel Camera-Based Measurement System for Roughness Determination of Concrete Surfaces

A Novel Camera-Based Measurement System for Roughness Determination of Concrete Surfaces

City Information Modeling: State of the Art

MS-Faster R-CNN: Multi-Stream Backbone for Improved Faster R-CNN Object Detection and Aerial Tracking from UAV Images

Contact Info

Product

Resources

About