Applying Active Vision and SLAM to Wearables

Mayol, W.W.; Davison, Andrew J.; Tordoff, B.J.; Murray, David

doi:10.1007/11008941_35

Cited by 16 publications

(22 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was demonstrated operating within the Extended Kalman Filter (EKF) monoSLAM algorithm of Davison et al [3,4], a method which has already proved a useful vehicle for AR using wearable vision [16,2].…”

Section: Introductionmentioning

confidence: 99%

Video-rate localization in multiple maps for wearable augmented reality

Castle

Klein

Murray

2008

2008 12th IEEE International Symposium on Wearable Computers

Self Cite

202

117

View full text Add to dashboard Cite

We show how a system for video-rate parallel camera tracking and 3D map-building can be readily extended to allow one or more cameras to work in several maps, separately or simultaneously. The ability to handle several thousand features per map at video-rate, and for the cameras to switch automatically between maps, allows spatially localized AR workcells to be constructed and used with very little intervention from the user of a wearable vision system. The user can explore an environment in a natural way, acquiring local maps in real-time. When revisiting those areas the camera will select the correct local map from store and continue tracking and structural acquisition, while the user views relevant AR constructs registered to that map.

show abstract

Section: Introductionmentioning

confidence: 99%

Video-rate localization in multiple maps for wearable augmented reality

Castle

Klein

Murray

2008

2008 12th IEEE International Symposium on Wearable Computers

Self Cite

202

117

View full text Add to dashboard Cite

show abstract

“…When an active wearable camera supplies the imagery, the system has some autonomy to explore the world itself. As mentioned in the introduction, in [18] 3D point positions in the map were hand-labelled to allow a remote operator to command an active wearable to fixate on objects of interest while continuing to map. This method can now be automated to command the system to locate and fixate upon particular objects, without intervention of the wearer.…”

Section: Discussionmentioning

confidence: 99%

“…Key to providing a wearable camera system with a greater degree of autonomy are the abilities both to locate the camera in the environment and to determine what is where around it [18]. In [18] it was demonstrated that once a partial 3D map of the camera's environment is established, locations can be selected for the camera to fixate upon, counteracting movements of the wearer, while continuing both to accumulate scene structure and to determine the camera pose.…”

Section: Introductionmentioning

confidence: 99%

“…In [18] it was demonstrated that once a partial 3D map of the camera's environment is established, locations can be selected for the camera to fixate upon, counteracting movements of the wearer, while continuing both to accumulate scene structure and to determine the camera pose. Whilst that process demonstrated the ability of a wearable system to direct attention independently of the wearer's movements, the 3D structure had no intrinsic significance to the wearable system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Video-rate recognition and localization for wearable cameras

Castle¹,

Gawley²,

Klein³

et al. 2007

Procedings of the British Machine Vision Conference 2007

View full text Add to dashboard Cite

Using simultaneous localization and mapping to determine the 3D surroundings and pose of a wearable or hand-held camera provides the geometrical foundation for several capabilities of value to an autonomous wearable vision system. The one explored here is the ability to incorporate recognized objects into the map of the surroundings and refer to them. Established methods for feature cluster recognition are used to identify and localize known planar objects, and their geometry is incorporated into the map of the surrounds using a minimalist representation. Continued measurement of these mapped objects improves both the accuracy of estimated maps and the robustness of the tracking system. In the context of wearable (or hand-held) vision, the system's ability to enhance generated maps with known objects increases the map's value to human operators, and also enables meaningful automatic annotation of the user's surroundings.

show abstract

“…Although the fusion of cameras and inertial sensors has previously been considered for motion tracking [29][23], augmented reality [12], and SLAM (simultaneous localization and mapping) [20], the work presented in this paper bears more similarity to the multiple-target tracking literature. The reason is that the main problems that we tackle are data association and motion correspondence, rather than exact position estimation.…”

Section: Related Workmentioning

confidence: 99%

Tasking networked CCTV cameras and mobile phones to identify and localize multiple people

Teixeira

Jung

Savvides

2010

Proceedings of the 12th ACM International Conference on Ubiquitous Computing

View full text Add to dashboard Cite

We present a method to identify and localize people by leveraging existing CCTV camera infrastructure along with inertial sensors (accelerometer and magnetometer) within each person's mobile phones. Since a person's motion path, as observed by the camera, must match the local motion measurements from their phone, we are able to uniquely identify people with the phones' IDs by detecting the statistical dependence between the phone and camera measurements. For this, we express the problem as consisting of a twomeasurement HMM for each person, with one camera measurement and one phone measurement. Then we use a maximum a posteriori formulation to find the most likely ID assignments. Through sensor fusion, our method largely bypasses the motion correspondence problem from computer vision and is able to track people across large spatial or temporal gaps in sensing. We evaluate the system through simulations and experiments in a real camera network testbed.

show abstract

Applying Active Vision and SLAM to Wearables

Cited by 16 publications

References 20 publications

Video-rate localization in multiple maps for wearable augmented reality

Video-rate localization in multiple maps for wearable augmented reality

Video-rate recognition and localization for wearable cameras

Tasking networked CCTV cameras and mobile phones to identify and localize multiple people

Contact Info

Product

Resources

About