Wearable omnidirectional vision system for personal localization and guidance

Murillo, Ana C.; Gutiérrez-Gómez, Daniel; Rituerto, Alejandro; Puig, Luis; Guerrero, J. J.

doi:10.1109/cvprw.2012.6239189

Cited by 24 publications

(11 citation statements)

References 29 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas, in [1], the common scene observed by the wearer and a surveillance camera has been used Poster Session F1: Deep Learning for Multimedia MM '20, October 12-16, 2020, Seattle, WA, USA to identify the wearer. Other works compute the location of the wearer directly [7,15] or indirectly (using gaze, social interactions, etc.) [16,17], which is then used to identify the wearer.…”

Section: Related Workmentioning

confidence: 99%

Recognizing Camera Wearer from Hand Gestures in Egocentric Videos

Thapar

Nigam

Arora

2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Figure 1: The above figure shows cutting (first two rows) and washing (last two rows) activities performed by two different subjects, as seen from the head-mounted egocentric cameras. The thesis of this paper is that egocentric cameras are able to capture wearer identifying hand gesture signatures, merely by looking at various activities being performed by the wearers. While it may be difficult for the reader to visually, our deep neural network-based model correctly identifies that activities in rows 1 and 3 have been performed by the same wearer, whereas the other subject has performed activities in rows 2, 4.

show abstract

Section: Related Workmentioning

confidence: 99%

Recognizing Camera Wearer from Hand Gestures in Egocentric Videos

Thapar

Nigam

Arora

2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Their method is based on linearisation of a catadioptric camera model and they perform tracking with omnidirectional patch descriptors that are rotation and scale invariant. Murillo et al [27] apply the same approach to data that is similar to that in our stabilisation application, namely first person video captured by a wearable omnidirectional camera. Torii et al [36] build 3D city models from Google Street View imagery.…”

Section: Related Workmentioning

confidence: 99%

Structure-From-Motion in Spherical Video Using the von Mises-Fisher Distribution

Guan

Smith

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we present a complete pipeline for computing structure-from-motion from the sequences of spherical images. We revisit problems from multiview geometry in the context of spherical images. In particular, we propose methods suited to spherical camera geometry for the spherical-n-point problem (estimating camera pose for a spherical image) and calibrated spherical reconstruction (estimating the position of a 3-D point from multiple spherical images). We introduce a new probabilistic interpretation of spherical structure-from-motion which uses the von Mises-Fisher distribution to model noise in spherical feature point positions. This model provides an alternate objective function that we use in bundle adjustment. We evaluate our methods quantitatively and qualitatively on both synthetic and real world data and show that our methods developed for spherical images outperform straightforward adaptations of methods developed for perspective images. As an application of our method, we use the structure-from-motion output to stabilise the viewing direction in fully spherical video.

show abstract

“…6) corrects the scale drift of the raw visual odometry. In the last experiment we test our approach in an indoor environment, with normal gait not set by a metronome [16]. Fig.…”

Section: Framementioning

confidence: 99%

Full scaled 3D visual odometry from a single wearable omnidirectional camera

Gutiérrez-Gómez

Puig

Guerrero

2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-In the last years monocular SLAM has been widely used to obtain highly accurate maps and trajectory estimations of a moving camera. However, one of the issues of this approach is that, due to the impossibility of the depth being measured in a single image, global scale is not observable and scene and camera motion can only be recovered up to scale. This problem gets aggravated as we deal with larger scenes since it is more likely that scale drift arises between different map portions and their corresponding motion estimates. To compute the absolute scale we need to know some kind of dimension of the scene (e.g., actual size of an element of the scene, velocity of the camera or baseline between two frames) and somehow integrate it in the SLAM estimation. In this paper, we present a method to recover the scale of the scene using an omnidirectional camera mounted on a helmet. The high precision of visual SLAM allows the head vertical oscillation during walking to be perceived in the trajectory estimation. By performing a spectral analysis on the camera vertical displacement, we can measure the step frequency. We relate the step frequency to the speed of the camera by an empirical formula based on biomedical experiments on human walking. This speed measurement is integrated in a particle filter to estimate the current scale factor and the 3D motion estimation with its true scale. We evaluated our approach using image sequences acquired while a person walks. Our experiments show that the proposed approach is able to cope with scale drift.

show abstract

Wearable omnidirectional vision system for personal localization and guidance

Cited by 24 publications

References 29 publications

Recognizing Camera Wearer from Hand Gestures in Egocentric Videos

Recognizing Camera Wearer from Hand Gestures in Egocentric Videos

Structure-From-Motion in Spherical Video Using the von Mises-Fisher Distribution

Full scaled 3D visual odometry from a single wearable omnidirectional camera

Contact Info

Product

Resources

About