Statistical body height estimation from a single image

BenAbdelkader, Chiraz; Yacoob, Yaser

doi:10.1109/afgr.2008.4813453

Cited by 47 publications

(48 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, height inference in images acquired with calibrated cameras and in which the location of the ground plane is given [14,18,21,47] or where objects of known height are visible [18,23] have been demonstrated. The method of [4] is the only one we know of that can operate on single uncalibrated RGB images and without prior knowledge. However, it relies on manually supplied keypoints and its reported results on real images lack precision.…”

Section: Introductionmentioning

confidence: 99%

What Face and Body Shapes Can Tell Us About Height

Günel

Rhodin

Fua

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Recovering a person's height from a single image is important for virtual garment fitting, autonomous driving and surveillance, however, it is also very challenging due to the absence of absolute scale information. We tackle the rarely addressed case, where camera parameters and scene geometry is unknown. To nevertheless resolve the inherent scale ambiguity, we infer height from statistics that are intrinsic to human anatomy and can be estimated from images directly, such as articulated pose, bone-length proportions, and facial features. Our contribution is twofold. First, we experiment with different machine learning models to capture the relation between image content and human height. Second, we show that performance is predominantly limited by dataset size and create a new dataset that is three magnitudes larger, by mining explicit height labels and propagating them to additional images through face recognition and assignment consistency. Our evaluation shows that monocular height estimation is possible with a MAE of 5.56cm.

show abstract

Section: Introductionmentioning

confidence: 99%

What Face and Body Shapes Can Tell Us About Height

Günel

Rhodin

Fua

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

show abstract

“…Although this is an under-constrained problem, there are several work trying to resolve this via introducing priors, e.g. [24,25]. An insight is to explore similar body images by searching from internet (might directly use methods or borrow ideas from image retrieval, e.g.…”

Section: Discussionmentioning

confidence: 99%

Estimation of human body shape and cloth field in front of a kinect

et al. 2015

View full text Add to dashboard Cite

“…Related to our idea is study by [1], in this research authors tried to estimate the height of human body from single uncalibrated image, however no reference towards camera viewpoint and estimation of camera parameters were provided. Localization of body landmarks was done in semi-automatic way and estimation was in this case carried out only for height.…”

Section: Anthropometric Features Estimationmentioning

confidence: 99%

Anthropometric Proportions Estimation Using recCAL in Multi-camera Environment

Kainz¹,

Cymbalák²,

Jakab³

2015

IJMO

View full text Add to dashboard Cite

Abstract-In this paper, a new technique for anthropometric proportions estimation using multi-camera environment is presented. We refer to this system as a recCAL. System is represented in a form of a 3D model and as well real-world physical model, both used as a reference model/object in the size estimation process. Further anthropometric proportions of human body and face are utilized to provide an estimate of real size from series of images as captured by multi-camera system. recCAL has potential applications in variety of areas where anthropometric proportions or size of other objects may be useful.

show abstract

Statistical body height estimation from a single image

Abstract: We address the problem of estimating a person '

Cited by 47 publications

References 10 publications

What Face and Body Shapes Can Tell Us About Height

What Face and Body Shapes Can Tell Us About Height

Estimation of human body shape and cloth field in front of a kinect

Anthropometric Proportions Estimation Using recCAL in Multi-camera Environment

Contact Info

Product

Resources

About