Paper Info
Title
Pedestrian's avoidance behavior recognition for road anomaly detection in the city
Abstract
In this paper, we show an opportunistic sensing-based system for road anomaly detection. To detect road anomalies such as cracks, pits, and puddles, we focus on pedestrian's avoidance behavior that is characterized by the azimuth changing patterns. Three typical avoidance behaviors are defined. RandomForest is chosen as a classifier, in which 29 features are defined. Ten-fold cross-validation showed an average classification performance with an F-measure of 0.87 for 7 activities.
Year
DOI
Venue
2015
10.1145/2800835.2800918
UbiComp/ISWC Adjunct
Field
DocType
Citations 
Anomaly detection,Computer vision,Pedestrian,Computer science,Azimuth,Artificial intelligence,Behavior recognition,Classifier (linguistics)
Conference
0
PageRank 
References 
Authors
0.34
1
2
Name
Order
Citations
PageRank
Tsuyoshi Ishikawa101.01
Kaori Fujinami231641.25