TY - JOUR
T1 - Real-time human action recognition on an embedded, reconfigurable video processing architecture
AU - Meng, Hongying
AU - Pears, Nick
AU - Bailey, Chris
AU - Freeman, Mike
PY - 2008/9
Y1 - 2008/9
N2 - In recent years, automatic human action recognition has been widely researched within the computer vision and image processing communities. Here we propose a real-time, embedded vision solution for human action recognition, implemented on an FPGA-based ubiquitous device. There are three main contributions in this paper. Firstly, we have developed a fast human action recognition system with simple motion features and a linear support vector machine classifier. The method has been tested on a large, public human action dataset and achieved competitive performance for the temporal template class of approaches, which include "Motion History Image" based techniques. Secondly, we have developed a reconfigurable, FPGA based video processing architecture. One advantage of this architecture is that the system processing performance can be reconfigured for a particular application, with the addition of new or replicated processing cores. Finally, we have successfully implemented a human action recognition system on this reconfigurable architecture. With a small number of human actions (hand gestures), this stand-alone system is operating reliably at 12 frames/s, with an 80% average recognition rate using limited training data. This type of system has applications in security systems, man-machine communications and intelligent environments.
AB - In recent years, automatic human action recognition has been widely researched within the computer vision and image processing communities. Here we propose a real-time, embedded vision solution for human action recognition, implemented on an FPGA-based ubiquitous device. There are three main contributions in this paper. Firstly, we have developed a fast human action recognition system with simple motion features and a linear support vector machine classifier. The method has been tested on a large, public human action dataset and achieved competitive performance for the temporal template class of approaches, which include "Motion History Image" based techniques. Secondly, we have developed a reconfigurable, FPGA based video processing architecture. One advantage of this architecture is that the system processing performance can be reconfigured for a particular application, with the addition of new or replicated processing cores. Finally, we have successfully implemented a human action recognition system on this reconfigurable architecture. With a small number of human actions (hand gestures), this stand-alone system is operating reliably at 12 frames/s, with an 80% average recognition rate using limited training data. This type of system has applications in security systems, man-machine communications and intelligent environments.
KW - Human motion recognition
KW - Reconfigurable architectures
KW - Embedded computer vision
KW - FPGA
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=47849117149&partnerID=8YFLogxK
U2 - 10.1007/s11554-008-0073-1
DO - 10.1007/s11554-008-0073-1
M3 - Article
SN - 1861-8200
VL - 3
SP - 163
EP - 176
JO - JOURNAL OF REAL-TIME IMAGE PROCESSING
JF - JOURNAL OF REAL-TIME IMAGE PROCESSING
IS - 3
ER -