3D Scene Reconstruction through a Fusion of Passive Video and Lidar Imagery

Gurram, Prudhvi; Rhody, Harvey; Kerekes, John P.; Lach, S.R.; Saber, Eli

doi:10.1109/aipr.2007.17

Cited by 18 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the use of higherorder geometry primitives and dense appearance allows small but crucial scene details to be detected and visualized. Third, as presented, the model allows scene reasoning to extend beyond reconstruction, e.g., the model allows [19][20][21][22][23][24][25][26][27] effortless detection of moving objects and reasoning about scene dimensions in absolute scale and orientation.…”

Section: Resultsmentioning

confidence: 99%

“…LiDAR has been exploited extensively in aerial reconstructions [10,15,19,22,23,24,25,38,39,40]. However, in sharp contrast to the proposed method, these methods assume that LiDAR provides a noise-free and accurate geometry, relegating images solely as a source of texture information and neglecting image-based geometric information.…”

Section: Background and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Aerial Reconstructions via Probabilistic Data Fusion

Cabezas

Freifeld

Rosman

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We propose an integrated probabilistic model for multimodal fusion of aerial imagery, LiDAR data, and (optional) GPS measurements. The model allows for analysis and dense reconstruction (in terms of both geometry and appearance) of large 3D scenes. An advantage of the approach is that it explicitly models uncertainty and allows for missing data. As compared with image-based methods, dense reconstructions of complex urban scenes are feasible with fewer observations. Moreover, the proposed model allows one to estimate absolute scale and orientation, and reason about other aspects of the scene, e.g., detection of moving objects. As formulated, the model lends itself to massively-parallel computing. We exploit this in an efficient inference scheme that utilizes both general purpose and domain-specific hardware components. We demonstrate results on large-scale reconstruction of urban terrain from Li-DAR and aerial photography data.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Background and Related Workmentioning

confidence: 99%

Aerial Reconstructions via Probabilistic Data Fusion

Cabezas

Freifeld

Rosman

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Zhou and Neumann (2009) only work with horizontal planes, which they gain from a distance-based region growing process. Following Ma (2004) and Gurram et al (2007) apply the mean shift procedure (Fukunaga and Hostetler, 1975) for segmentation, using the normal vectors and point locations as the defining features. An in-depth description on how this nonparametric segmentation can be applied to 3D point clouds is e.g.…”

Section: Segmentationmentioning

confidence: 99%

An update on automatic 3D building reconstruction

Haala

Kada

2010

ISPRS Journal of Photogrammetry and Remote Sensing

391

246

View full text Add to dashboard Cite

“…A posteriori fusion aims at integrating the outputs (i.e., disparity maps) of both sensors to enhance the final output of the system [3], [4], [5], [6]. This is usually accomplished by using evidence grids [6] or at the object level [4], [3], [2]. A priori integration, on the other hand, fuses the ranges obtained from the TOF camera into the stereo computation algorithm in order to improve the resulting disparity map.…”

Section: A Related Researchmentioning

confidence: 99%

“…There are mainly two types of stereo/TOF integration, a posteriori and a priori integration. A posteriori fusion aims at integrating the outputs (i.e., disparity maps) of both sensors to enhance the final output of the system [3], [4], [5], [6]. This is usually accomplished by using evidence grids [6] or at the object level [4], [3], [2].…”

Section: A Related Researchmentioning

confidence: 99%

Integrating LIDAR into Stereo for Fast and Improved Disparity Computation

Badino

Huber

Kanade

2011

2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission

View full text Add to dashboard Cite

The fusion of stereo and laser range finders (LIDARs) has been proposed as a method to compensate for each individual sensor's deficiencies − stereo output is dense, but noisy for large distances, while LIDAR is more accurate, but sparse. However, stereo usually performs poorly on textureless areas and on scenes containing repetitive structures, and the subsequent fusion with LIDAR leads to a degraded estimation of the 3D structure. In this paper, we propose to integrate LIDAR data directly into the stereo algorithm to reduce false positives while increasing the density of the resulting disparity image on textureless regions. We demonstrate with extensive experimental results with real data that the disparity estimation is substantially improved while speeding up the stereo computation by as much as a factor of five.

show abstract

3D Scene Reconstruction through a Fusion of Passive Video and Lidar Imagery

Cited by 18 publications

References 12 publications

Aerial Reconstructions via Probabilistic Data Fusion

Aerial Reconstructions via Probabilistic Data Fusion

An update on automatic 3D building reconstruction

Integrating LIDAR into Stereo for Fast and Improved Disparity Computation

Contact Info

Product

Resources

About