Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published October 2017 | Submitted
Book Section - Chapter Open

Benchmarking and Error Diagnosis in Multi-instance Pose Estimation

Abstract

We propose a new method to analyze the impact of errors in algorithms for multi-instance pose estimation and a principled benchmark that can be used to compare them. We define and characterize three classes of errors - localization, scoring, and background - study how they are influenced by instance attributes and their impact on an algorithm's performance. Our technique is applied to compare the two leading methods for human pose estimation on the COCO Dataset, measure the sensitivity of pose estimation with respect to instance size, type and number of visible keypoints, clutter due to multiple instances, and the relative score of instances. The performance of algorithms, and the types of error they make, are highly dependent on all these variables, but mostly on the number of keypoints and the clutter. The analysis and software tools we propose offer a novel and insightful approach for understanding the behavior of pose estimation algorithms and an effective method for measuring their strengths and weaknesses.

Additional Information

© 2017 IEEE.

Attached Files

Submitted - 1707.05388.pdf

Files

1707.05388.pdf
Files (6.2 MB)
Name Size Download all
md5:631cddf4520bdf635def6f19a9a67597
6.2 MB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 18, 2023