TY - GEN
T1 - A unifed model for activity recognition from video sequences
AU - Resendiz, Esther
AU - Ahuja, Narendra
PY - 2008
Y1 - 2008
N2 - We propose an activity recognition algorithm that utilizes a unified spatial-frequency model of motion to recognize large-scale differences in action using global statistics, and subsequently distinguishes between motions with similar global statistics by spatially localizing the moving objects. We model the Fourier transforms of translating rigid objects in a video, since the Fourier domain inherently groups regions of the video with similar motion in high energy concentrations within its domain to make global motion detectable. Frequency-domain statistics can be used to isolate the frames that both adhere to our model and contain similar global motion, thus we can separate activities into broader classes based on their global motion. A leastsquares solution is then solved to isolate the spatially discriminative object configurations that produce similar global motion statistics. This model provides a unified framework to form concise globally-optimal spatial and motion descriptors necessary for discriminating activities. Experimental results are demonstrated on a human activity dataset.
AB - We propose an activity recognition algorithm that utilizes a unified spatial-frequency model of motion to recognize large-scale differences in action using global statistics, and subsequently distinguishes between motions with similar global statistics by spatially localizing the moving objects. We model the Fourier transforms of translating rigid objects in a video, since the Fourier domain inherently groups regions of the video with similar motion in high energy concentrations within its domain to make global motion detectable. Frequency-domain statistics can be used to isolate the frames that both adhere to our model and contain similar global motion, thus we can separate activities into broader classes based on their global motion. A leastsquares solution is then solved to isolate the spatially discriminative object configurations that produce similar global motion statistics. This model provides a unified framework to form concise globally-optimal spatial and motion descriptors necessary for discriminating activities. Experimental results are demonstrated on a human activity dataset.
UR - http://www.scopus.com/inward/record.url?scp=77957946587&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77957946587&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:77957946587
SN - 9781424421756
T3 - Proceedings - International Conference on Pattern Recognition
BT - 2008 19th International Conference on Pattern Recognition, ICPR 2008
T2 - 2008 19th International Conference on Pattern Recognition, ICPR 2008
Y2 - 8 December 2008 through 11 December 2008
ER -