Real-time camera pose estimation via line tracking

Li, Yanli; Chen, Xianghui; Gu, Tianlun; Zhang, Yanci; Xing, Guanyu

doi:10.1007/s00371-018-1523-9

Cited by 10 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work [ 45 ], we proposed and validated a camera pose calibration algorithm based on VPs. In this study, we continue to utilize VPs to estimate camera rotation R cw :

where v x , v y , and v z are the VPs in camera coordinate O c .…”

Section: Structural-line-based Slam Initializationmentioning

confidence: 99%

“…The z-direction can be obtained by taking the cross product of the x and y directions. Based on stable structural line tracking, we could easily calculate the translation of the initialization frame [ 45 ], as shown in Figure 5 . A ′ P ′ is projected from AP , P ″ the intersection of the line ( O c P ) with the line L passing through A ′ and whose direction is A → P .…”

Section: Structural-line-based Slam Initializationmentioning

confidence: 99%

See 1 more Smart Citation

Accurate Monocular SLAM Initialization via Structural Line Tracking

Gu,

Zhang,

Liu

2023

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, we present a novel monocular simultaneous localization and mapping (SLAM) initialization algorithm that relies on structural features by tracking structural lines. This approach addresses the limitations of the traditional method, which can fail to account for a lack of features or their uneven distribution. Our proposed method utilizes a sliding window approach to guarantee the quality and stability of the initial pose estimation. We incorporate multiple geometric constraints, orthogonal dominant directions, and coplanar structural lines to construct an efficient pose optimization strategy. Experimental evaluations conducted on both the collected chessboard datasets and real scene datasets show that our approach provides superior results in terms of accuracy and real-time performance compared to the well-tuned baseline methods. Notably, our algorithm achieves these improvements while being computationally lightweight, without the need for matrix decomposition.

show abstract

“…In our previous work [ 45 ], we proposed and validated a camera pose calibration algorithm based on VPs. In this study, we continue to utilize VPs to estimate camera rotation R cw :

where v x , v y , and v z are the VPs in camera coordinate O c .…”

Section: Structural-line-based Slam Initializationmentioning

confidence: 99%

Section: Structural-line-based Slam Initializationmentioning

confidence: 99%

Accurate Monocular SLAM Initialization via Structural Line Tracking

Gu,

Zhang,

Liu

2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…To establish mentioned matching, it is mandatory to know the user orientation and position in the real world. In this way, previous work is proposed related to indoor navigation and positioning [9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

“…However, the methodology based only on RGB-D sensors may be affected by inconsistencies between depth data and color images. Therefore, some approaches take advantage of the fact that most indoor environments follow the Manhattan World assumption, in which the spatial layout constraints facilitate the camera tracking [12,26,27]. Even so, some authors ensure that accuracy during free navigation must be checked and adjusted, for instance, by planar surface matching [28] or by means of video frames [12,26].…”

Section: Introductionmentioning

confidence: 99%

GEUINF: Real-Time Visualization of Indoor Facilities Using Mixed Reality

Jurado

Ortega

et al. 2021

Sensors

View full text Add to dashboard Cite

Mixed reality (MR) enables a novel way to visualize virtual objects on real scenarios considering physical constraints. This technology arises with other significant advances in the field of sensors fusion for human-centric 3D capturing. Recent advances for scanning the user environment, real-time visualization and 3D vision using ubiquitous systems like smartphones allow us to capture 3D data from the real world. In this paper, a disruptive application for assessing the status of indoor infrastructures is proposed. The installation and maintenance of hidden facilities such as water pipes, electrical lines and air conditioning tubes, which are usually occluded behind the wall, supposes tedious and inefficient tasks. Most of these infrastructures are digitized but they cannot be visualized onsite. In this research, we focused on the development of a new application (GEUINF) to be launched on smartphones that are capable of capturing 3D data of the real world by depth sensing. This information is relevant to determine the user position and orientation. Although previous approaches used fixed markers for this purpose, our application enables the estimation of both parameters with a centimeter accuracy without them. This novelty is possible since our method is based on a matching process between reconstructed walls of the real world and 3D planes of the replicated world in a virtual environment. Our markerless approach is based on scanning planar surfaces of the user environment and then, these are geometrically aligned with their corresponding virtual 3D entities. In a preprocessing phase, the 2D CAD geometry available from an architectural project is used to generate 3D models of an indoor building structure. In real time, these virtual elements are tracked with the real ones modeled by using ARCore library. Once the alignment between virtual and real worlds is done, the application enables the visualization, navigation and interaction with the virtual facility networks in real-time. Thus, our method may be used by private companies and public institutions responsible of the indoor facilities management and also may be integrated with other applications focused on indoor navigation.

show abstract