TY - GEN
T1 - Multiple hypothesis object tracking for unsupervised self-learning
T2 - 27th AAAI Conference on Artificial Intelligence, AAAI 2013
AU - Faghmous, James H
AU - Uluyol, Muhammed
AU - Styles, Luke
AU - Le, Matthew
AU - Mithal, Varun
AU - Boriah, Shyam
AU - Kumar, Vipin
PY - 2013
Y1 - 2013
N2 - Mesoscale ocean eddies transport heat, salt, energy, and nutrients across oceans. As a result, accurately identifying and tracking such phenomena are crucial for understanding ocean dynamics and marine ecosystem sustainability. Traditionally, ocean eddies are monitored through two phases: identification and tracking. A major challenge for such an approach is that the tracking phase is dependent on the performance of the identification scheme, which can be susceptible to noise and sampling errors. In this paper, we focus on tracking, and introduce the concept of multiple hypothesis assignment (MHA), which extends traditional multiple hypothesis tracking for cases where the features tracked are noisy or uncertain. Under this scheme, features are assigned to multiple potential tracks, and the final assignment is deferred until more data are available to make a relatively unambiguous decision. Unlike the most widely used methods in the eddy tracking literature, MHA uses contextual spatio-temporal information to take corrective measures autonomously on the detection step a posteriori and performs significantly better in the presence of noise. This study is also the first to empirically analyze the relative robustness of eddy tracking algorithms.
AB - Mesoscale ocean eddies transport heat, salt, energy, and nutrients across oceans. As a result, accurately identifying and tracking such phenomena are crucial for understanding ocean dynamics and marine ecosystem sustainability. Traditionally, ocean eddies are monitored through two phases: identification and tracking. A major challenge for such an approach is that the tracking phase is dependent on the performance of the identification scheme, which can be susceptible to noise and sampling errors. In this paper, we focus on tracking, and introduce the concept of multiple hypothesis assignment (MHA), which extends traditional multiple hypothesis tracking for cases where the features tracked are noisy or uncertain. Under this scheme, features are assigned to multiple potential tracks, and the final assignment is deferred until more data are available to make a relatively unambiguous decision. Unlike the most widely used methods in the eddy tracking literature, MHA uses contextual spatio-temporal information to take corrective measures autonomously on the detection step a posteriori and performs significantly better in the presence of noise. This study is also the first to empirically analyze the relative robustness of eddy tracking algorithms.
UR - http://www.scopus.com/inward/record.url?scp=84893383492&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84893383492&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84893383492
SN - 9781577356158
T3 - Proceedings of the 27th AAAI Conference on Artificial Intelligence, AAAI 2013
SP - 1277
EP - 1283
BT - Proceedings of the 27th AAAI Conference on Artificial Intelligence, AAAI 2013
Y2 - 14 July 2013 through 18 July 2013
ER -