Paper Info
Title
Evaluation of manually created ground truth for multi-view people localization
Abstract
In the field of multi-view people localization, only a few works consider a non-planar ground surface. In this article we introduce a framework for collecting ground truth data in such case, we show characterization of specific errors and introduce a method to automatically merge multiple ground truth data generated by different users to form a more reliable reference ground truth. We use this reference ground truth to evaluate the error rate, the accuracy and the recall of subjects (6 laymen and 3 with domain knowledge). We show that even laymen can work accurately, but even subjects with domain knowledge miss a number of people in a crowded scene. Our findings show that creating ground truth data requires special attention in this field.
Year
DOI
Venue
2013
10.1145/2501105.2501106
VIGTA@ICVS
Keywords
Field
DocType
reference ground truth,reliable reference ground truth,multiple ground truth data,ground truth data,error rate,different user,multi-view people localization,non-planar ground surface,domain knowledge,crowded scene,image segmentation
Computer vision,Domain knowledge,Computer science,Word error rate,Image segmentation,Ground truth,Artificial intelligence,Merge (version control),Recall
Conference
Citations 
PageRank 
References 
2
0.36
8
Authors
2
Name
Order
Citations
PageRank
Ákos Kiss1223.33
Tamás Szirányi215226.92