[Poster] Augmented reality binoculars on the move

Oskiper, Taragay; Sizintsev, Mikhail; Branzoi, Vlad; Samarasekera, Supun; Kumar, Rakesh

doi:10.1109/ismar.2014.6948454

Cited by 1 publication

(12 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We validate our approach against our own implementation of a state-of-the-art outdoor augmented reality system [5,18,19], which has been used for military vehicle training and observer training. Although this system incorporates the same set of sensors as our system, its filter architecture and IMU mechanism formulation are different from our system (Section 4.1).…”

Section: Methodsmentioning

confidence: 99%

“…The first environment is a training field, including unpaved roads and country roads, which is similar to [5,18,19] for military training. There are 4 sequences: each sequence is around 5.5 minutes and 3.1 kilometers.…”

Section: Methodsmentioning

confidence: 99%

“…There are recent methods that fuse feature tracks [5,10,18,19] perceived from low-cost monocular cameras with low-cost IMUs to filter corrupted GPS readings and to improve motion estimation over time for outdoor augmented reality applications. The closest work to our system is [5], which leverages the navigation algorithm from [18,19] to provide precise and stable real-time 6-DOF pose estimation for military vehicle training.…”

Section: Navigation For Augmented Reality Drivingmentioning

confidence: 99%

“…where m l denotes the function integrating the accelerations and rotation rates. We use the pre-integration theory [13] to perform IMU integration in the local frame at time i − 1 rather than in the global frame as used in traditional IMU mechanization [5,18,19]. The subscript "l" in m l denotes the fact that the integration computes quantities in the local frame.…”

Section: Imu Motion Modelmentioning

confidence: 99%

“…In Section 7, we evaluate our system against a state-of-the-art outdoor augmented reality system, which has been used for military vehicle training [5] and observer training [18,19]. We show our approach improves both navigation accuracy and depth map quality for driving within vehicle training environments and urban areas (including dense and crowded places, such as downtown streets with buildings and traffic).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Augmented Reality Driving Using Semantic Geo-Registration

Chiu

Murali

Villamil

et al. 2018

2018 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)

Self Cite

View full text Add to dashboard Cite

We propose a new approach that utilizes semantic information to register 2D monocular video frames to the world using 3D georeferenced data, for augmented reality driving applications. The geo-registration process uses our predicted vehicle pose to generate a rendered depth map for each frame, allowing 3D graphics to be convincingly blended with the real world view. We also estimate absolute depth values for dynamic objects, up to 120 meters, based on the rendered depth map and update the rendered depth map to reflect scene changes over time. This process also creates opportunistic global heading measurements, which are fused with other sensors, to improve estimates of the 6 degrees-of-freedom global pose of the vehicle over state-of-the-art outdoor augmented reality systems [5, 18, 19]. We evaluate the navigation accuracy and depth map quality of our system on a driving vehicle within various large-scale environments for producing realistic augmentations.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%