Image based estimation of pedestrian orientation for improving path prediction

Gandhi, T.; Trivedi, Mohan M.

doi:10.1109/ivs.2008.4621257

Cited by 88 publications

(52 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many applications to the estimation of the orientation of the person in front of the camera: estimating the visual focus of attention for marketing strategies and effective advertisement methods [11], clothes-shopping [17], intelligent vehicles [5,6], perceptual interfaces, facilitating pose recovery [8], etc.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Human Orientation in Images Captured with a Range Camera

Pierard

Leroy

Hansen

et al. 2011

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

Estimating the orientation of the observed person is a crucial task for some application fields like home entertainment, man-machine interaction, or intelligent vehicles. In this paper, we discuss the usefulness of conventional cameras for estimating the orientation, present some limitations, and show that 3D information improves the estimation performance. Technically, the orientation estimation is solved in the terms of a regression problem and supervised learning. This approach, combined to a slicing method of the 3D volume, provides mean errors as low as 9.2°o r 4.3°depending on the set of considered poses. These results are consistent with those reported in the literature. However, our technique is faster and easier to implement than existing ones.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimation of Human Orientation in Images Captured with a Range Camera

Pierard

Leroy

Hansen

et al. 2011

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

show abstract

“…Using the equations for the summation of geometric series on (8) and inserting in (9) gives an equation for determining α. For instance, if the smoother is to follow a step function to 80% (q = 0.8) within the next k = 180 measuring time steps, α should be about 0.009.…”

Section: Exponential Smoothingmentioning

confidence: 99%

“…While many publications (e.g. [8]) predict pedestrians' movements from an exocentric point of view, this paper approaches the problem from egocentric perspective.…”

mentioning

confidence: 99%

Using Head Tracking Data for Robust Short Term Path Prediction of Human Locomotion

Nescher

Künz

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Modern interactive environments like virtual reality simulators or augmented reality systems often require reliable information about a user's future intention in order to increase their immersion and usefulness. For many of such systems, where human locomotion is an essential way of interaction, knowing a user's future walking direction provides relevant information.This paper explains how head tracking data can be used to retrieve a person's intended direction of walking. The goal is to provide a reliable and stable path prediction of human locomotion that holds for a few seconds. Using 6 degrees of freedom head tracking data, the head orientation and the head's movement direction can be derived. Within a user study it is shown that such raw tracking data provides poor prediction results mainly due to noise from gait oscillations. Hence, smoothing filters have to be applied to the data to increase the reliability and robustness of a predictor.Results of the user study show that double exponential smoothing of a person's walking direction data in combination with an initialization using the head orientation provides a reliable short term path predictor with high robustness.

show abstract

“…As explained in Section 3.1, it is preferable to use a side view. In this case, methods based on the image instead of the segmentation mask have been proposed (Enzweiler and Gavrila, 2010;Gandhi and Trivedi, 2008;Nakajima et al, 2003;Shimizu and Poggio, 2004).…”

Section: Related Workmentioning

confidence: 99%

Estimation of Human Orientation Based on Silhouettes and Machine Learning Principles

Pierard

Droogenbroeck

2012

Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

Abstract:Estimating the orientation of the observed person is a crucial task for home entertainment, man-machine interaction, intelligent vehicles, etc. This is possible but complex with a single camera because it only provides one side view. To decrease the sensitivity to color and texture, we use the silhouette to infer the orientation.Under these conditions, we show that the only intrinsic limitation is to confuse the orientation θ with the supplementary angle (that is 180°− θ), and that the shape descriptor must distinguish between mirrored images. In this paper, the orientation estimation is expressed and solved in the terms of a regression problem and supervised learning. In our experiments, we have tested and compared 18 shape descriptors; the best one achieves a mean error of 5.24°. However, because of the intrinsic limitation mentioned above, the range of orientations is limited to 180°. Our method is easy to implement and outperforms existing techniques.

show abstract

Image based estimation of pedestrian orientation for improving path prediction

Cited by 88 publications

References 14 publications

Estimation of Human Orientation in Images Captured with a Range Camera

Estimation of Human Orientation in Images Captured with a Range Camera

Using Head Tracking Data for Robust Short Term Path Prediction of Human Locomotion

Estimation of Human Orientation Based on Silhouettes and Machine Learning Principles

Contact Info

Product

Resources

About