Accurate Human Navigation Using Wearable Monocular Visual and Inertial Sensors

Tian, Yuan; Hamel, W.R.; Tan, Jindong

doi:10.1109/tim.2013.2277514

Cited by 54 publications

(31 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By plugging in (18), (19), (20) and dropping the term P (η 1 , η 2 , · · · η n ) (as it does not depend on θ ), we then obtain the optimal solution on θ :…”

Section: Maximum Posteriori Estimationmentioning

confidence: 99%

“…The inertial based arm motion tracking [5] takes advantage of IMU measurements and employs the AGOF filter to estimate the body joint orientations. In [18], the system combines both IMU and monocular camera to conduct the orientation estimation based upon Kalman filter. However, it over-depends upon inertial measurements, which turns out to be less accurate than our method.…”

Section: Visual-inertial Motion Trackingmentioning

confidence: 99%

“…In inertial-based orientation estimate, some researchers (for instance: Madgwick et al [26], Tian et al [18]) have come up with effective methods to conduct the MARG sensor orientation estimation. Their methods are encouraging.…”

Section: Inertial-based Orientation Estimatementioning

confidence: 99%

“…Visual-inertial orientation system employs IMU [17,18] to assist camera in achieving pose estimation. Hardegger et al [1] fused the foot-mounted inertial measurements with visual local landmark map in the particle filter framework for 3D Action SLAM in the indoor scenarios.…”

Section: Visual-inertial-based Orientation Estimatementioning

confidence: 99%

“…However, subject self-occlusion and limited effective areas greatly restrict the overall performance. By comparison, the wearable monocular camera (MC) rather than multiple cameras can be adopted and combined with IMU [18,20] to capture first-view scenes. This compact MC-IMU system facilitates wearability near human body joints.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Robust orientation estimate via inertial guided visual sample consensus

Zhang

Liang

et al. 2017

Pers Ubiquit Comput

Self Cite

View full text Add to dashboard Cite

This paper presents a novel orientation estimate approach named inertial guided visual sample consensus (IGVSAC). This method is intentionally designed for capturing the orientation of human body joints in freeliving environments. Unlike the traditional visual-based orientation estimation methods, where outliers among putative image-pair correspondences are removed based on hypothesize-and-verify models such as the computationally costly RANSAC, our approach novelly exploits prior motion information (i.e., rotation and translation) deduced from the quick-response inertial measurement unit (IMU) as the initial body pose to assist camera in removing hidden outliers. In addition, our IGVSAC algorithm is able to ensure estimation accuracy even in the presence of a large quantity of outliers, thanks to its capability of rejecting apparent mismatches. The estimated orientation from the visual sensor is, in turn, able to correct long-term IMU drifts. We conducted extensive experiments to verify the effectiveness and robustness of our IGVSAC algorithm. Comparisons with highly accurate VICON and OptiTrack Motion Tracking Systems prove that our orientation estimate system is quite suitable for capturing human body joints.

show abstract

“…By plugging in (18), (19), (20) and dropping the term P (η 1 , η 2 , · · · η n ) (as it does not depend on θ ), we then obtain the optimal solution on θ :…”

Section: Maximum Posteriori Estimationmentioning

confidence: 99%

Section: Visual-inertial Motion Trackingmentioning

confidence: 99%