TY - GEN
T1 - Activity recognition and localization on a truck parking lot
AU - Andersson, Maria
AU - Patino, Luis
AU - Burghouts, Gertjan J.
AU - Flizikowski, Adam
AU - Evans, Murray
AU - Gustafsson, David
AU - Petersson, Henrik
AU - Schutte, Klamer
AU - Ferryman, James
PY - 2013/8/30
Y1 - 2013/8/30
N2 - In this paper we present a set of activity recognition and localization algorithms that together assemble a large amount of information about activities on a parking lot. The aim is to detect and recognize events that may pose a threat to truck drivers and trucks. The algorithms perform zone-based activity learning, individual action recognition and group detection. Visual sensor data, from one camera, have been recorded for 23 realistic scenarios of different complexities. The scene is complicated and causes uncertain and false position estimates. We also present a situational assessment ontology which serves the algorithms with relevant knowledge about the observed scene (e.g. information about objects, vulnerabilities and historical data). The algorithms are tested with real tracking data and the evaluations show promising results. The accuracies are 90 % for zone-based activity learning, 71 % for individual action recognition and 66 % for group detection (i.e. merging of people).
AB - In this paper we present a set of activity recognition and localization algorithms that together assemble a large amount of information about activities on a parking lot. The aim is to detect and recognize events that may pose a threat to truck drivers and trucks. The algorithms perform zone-based activity learning, individual action recognition and group detection. Visual sensor data, from one camera, have been recorded for 23 realistic scenarios of different complexities. The scene is complicated and causes uncertain and false position estimates. We also present a situational assessment ontology which serves the algorithms with relevant knowledge about the observed scene (e.g. information about objects, vulnerabilities and historical data). The algorithms are tested with real tracking data and the evaluations show promising results. The accuracies are 90 % for zone-based activity learning, 71 % for individual action recognition and 66 % for group detection (i.e. merging of people).
UR - http://www.scopus.com/inward/record.url?scp=84890878491&partnerID=8YFLogxK
U2 - 10.1109/AVSS.2013.6636650
DO - 10.1109/AVSS.2013.6636650
M3 - Chapter in a published conference proceeding
AN - SCOPUS:84890878491
SN - 9781479907038
T3 - 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013
SP - 263
EP - 269
BT - 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013
PB - IEEE
CY - U. S. A.
T2 - 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013
Y2 - 27 August 2013 through 30 August 2013
ER -