Integrating LIDAR Range Scans and Photographs with Temporal Changes

Morago, Brittany; Bui, Giang; Duan, Ye

doi:10.1109/cvprw.2014.113

Cited by 7 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This might easily require more time and skill than annotating 3 or more tie points. Morago et al (2014) have chosen to automate the alignment of new photos with LIDAR scans by 2D feature point matching with photos that were taken together with the LIDAR scans, making use of their available 3D registration. However, this approach does not solve the problem of how to align photos with 3D scans for which no photos have been registered yet.…”

Section: Previous Workmentioning

confidence: 99%

A Semi-Automatic Procedure for Texturing of Laser Scanning Point Clouds With Google Streetview Images

Lichtenauer¹,

Sırmaçek

2015

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:We introduce a method to texture 3D urban models with photographs that even works for Google Streetview images and can be done with currently available free software. This allows realistic texturing, even when it is not possible or cost-effective to (re)visit a scanned site to take textured scans or photographs. Mapping a photograph onto a 3D model requires knowledge of the intrinsic and extrinsic camera parameters. The common way to obtain intrinsic parameters of a camera is by taking several photographs of a calibration object with a priori known structure. The extra challenge of using images from a database such as Google Streetview, rather than your own photographs, is that it does not allow for any controlled calibration. To overcome this limitation, we propose to calibrate the panoramic viewer of Google Streetview using Structure from Motion (SfM) on any structure of which Google Streetview offers views from multiple angles. After this, the extrinsic parameters for any other view can be calculated from 3 or more tie points between the image from Google Streetview and a 3D model of the scene. These point correspondences can either be obtained automatically or selected by manual annotation. We demonstrate how this procedure provides realistic 3D urban models in an easy and effective way, by using it to texture a publicly available point cloud from a terrestrial laser scan made in Bremen, Germany, with a screenshot from Google Streetview, after estimating the focal length from views from Paris, France.

show abstract

Section: Previous Workmentioning

confidence: 99%

A Semi-Automatic Procedure for Texturing of Laser Scanning Point Clouds With Google Streetview Images

Lichtenauer¹,

Sırmaçek

2015

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Allowing a model of a 3D scene to be viewed from remote locations by sending it over available networks to officials can aid in response organization. Large scale models can be created using 3D LIDAR (Light Detection and Ranging) scans that use a laser to determine distance to surfaces and reconstruct a scene [2]. This type This work was supported by the National Science Foundation under awards ACI-1245795 and CNS-1205658 and Cisco Systems.…”

Section: Introductionmentioning

confidence: 99%

“…Mutual information can also be used for direct 2D-3D registration in which various properties of a scan such as laser reflectivity or point cloud height are visualized in 2D [11], [12]. If the scanner has a build in camera, keypoint features can be matched in 2D to obtain an camera pose estimate that can be refined with 3D normal or edge information [2], [13].…”

Section: Introductionmentioning

confidence: 99%

LIDAR-based virtual environment study for disaster response scenarios

Bui

Calyam

Morago

et al. 2015

2015 IFIP/IEEE International Symposium on Integrated Network Management (IM)

Self Cite

View full text Add to dashboard Cite

In the event of natural or man-made disasters, many videos may be collected by civilians and surveillance cameras that can be extremely useful for first responders trying to ascertain the extent of the damage. However, watching and analyzing numerous videos on separate screens can be a cumbersome task. Registering a set of 2D videos with a 3D model can provide an intuitive venue for viewing multiple videos simultaneously. In such a setup, it is likely that the user will want to work with the dynamic 3D environment from a remote location, requiring that videos be transferred over a network to be registered with a 3D model. In this paper, we propose combining the fields of computer vision, cloud computing, and high-speed networking to create a system that takes in HD videos, streams the data to a server where a dynamic 3D model is constructed, and provides a virtual scene navigation program for viewing the videos in a 3D scene from a mobile device. We test transferring the data of interest over different types of networks and processing the videos on various server configurations to determine the capabilities of such a system and the necessary requirements for it to provide a high-quality user experience.

show abstract

“…In our second case study application, function-centric computing registers 2D videos with 3D LIDAR scans collected at the theater-scale. As a result, first responders can view sets of videos in an intuitive (3D) virtual environment [19]. This simplifies the cumbersome task of analyzing several disparate 2D videos on a grid display.…”

Section: Scene Reconstruction From Lidar Scansmentioning

confidence: 99%

Reliable service chain orchestration for scalable data-intensive computing at infrastructure edges

Chemodanov¹

View full text Add to dashboard Cite

In the event of natural or man-made disasters, geospatial video analytics is valuable to provide situational awareness that can be extremely helpful for first responders. However, geospatial video analytics demands massive imagery/video data 'collection' from Internet-of-Things (IoT) and their seamless 'computation/consumption' within a geo-distributed (edge/core) cloud infrastructure in order to cater to user Quality of Experience (QoE) expectations. Thus, the edge computing needs to be designed with a reliable performance while interfacing with the core cloud to run computer vision algorithms. This is because infrastructure edges near locations generating imagery/video content are rarely equipped with high-performance computation capabilities. This thesis addresses challenges of interfacing edge and core cloud computing within the geo-distributed infrastructure as a novel 'function-centric computing' paradigm that brings new insights to computer vision, edge routing and network virtualization areas. Specifically, we detail the state-of-the-art techniques and illustrate our new/improved solution approaches based on function-centric computing for the two problems of: (i) high-throughput data collection from IoT devices at the wireless edge, and (ii) seamless data computation/consumption within the geo-distributed (edge/core) cloud infrastructure. To address (i), we present a novel deep learning-augmented geographic edge routing that relies on physical area knowledge obtained from satellite imagery. To address (ii), we describe a novel reliable service chain orchestration framework that builds upon microservices and utilizes a novel 'metapath composite variable' approach supported by a constrained-shortest path finder. Finally, we show both analytically and empirically, how our geographic routing, constrained shortest path finder and reliable service chain orchestration approaches that compose our function-centric computing framework are superior than many traditional and state-of-the-art techniques. As a result, we can significantly speedup (up to 4 times) data-intensive computing at infrastructure edges fostering effective disaster relief coordination to save lives.

show abstract

Integrating LIDAR Range Scans and Photographs with Temporal Changes

Cited by 7 publications

References 31 publications

A Semi-Automatic Procedure for Texturing of Laser Scanning Point Clouds With Google Streetview Images

A Semi-Automatic Procedure for Texturing of Laser Scanning Point Clouds With Google Streetview Images

LIDAR-based virtual environment study for disaster response scenarios

Reliable service chain orchestration for scalable data-intensive computing at infrastructure edges

Contact Info

Product

Resources

About