TY - JOUR
T1 - Spatial and temporal downsampling in event-based visual classification
AU - Cohen, Gregory
AU - Afshar, Saeed
AU - Orchard, Garrick
AU - Tapson, Jonathan
AU - Benosman, Ryad
AU - Schaik, André van
PY - 2018
Y1 - 2018
N2 - As the interest in event-based vision sensors for mobile and aerial applications grows, there is an increasing need for high-speed and highly robust algorithms for performing visual tasks using event-based data. As event rate and network structure have a direct impact on the power consumed by such systems, it is important to explore the efficiency of the event-based encoding used by these sensors. The work presented in this paper represents the first study solely focused on the effects of both spatial and temporal downsampling on event-based vision data and makes use of a variety of data sets chosen to fully explore and characterize the nature of downsampling operations. The results show that both spatial downsampling and temporal downsampling produce improved classification accuracy and, additionally, a lower overall data rate. A finding is particularly relevant for bandwidth and power constrained systems. For a given network containing 1000 hidden layer neurons, the spatially downsampled systems achieved a best case accuracy of 89.38% on N-MNIST as opposed to 81.03% with no downsampling at the same hidden layer size. On the N-Caltech101 data set, the downsampled system achieved a best case accuracy of 18.25%, compared with 7.43% achieved with no downsampling. The results show that downsampling is an important preprocessing technique in eventbased visual processing, especially for applications sensitive to power consumption and transmission bandwidth.
AB - As the interest in event-based vision sensors for mobile and aerial applications grows, there is an increasing need for high-speed and highly robust algorithms for performing visual tasks using event-based data. As event rate and network structure have a direct impact on the power consumed by such systems, it is important to explore the efficiency of the event-based encoding used by these sensors. The work presented in this paper represents the first study solely focused on the effects of both spatial and temporal downsampling on event-based vision data and makes use of a variety of data sets chosen to fully explore and characterize the nature of downsampling operations. The results show that both spatial downsampling and temporal downsampling produce improved classification accuracy and, additionally, a lower overall data rate. A finding is particularly relevant for bandwidth and power constrained systems. For a given network containing 1000 hidden layer neurons, the spatially downsampled systems achieved a best case accuracy of 89.38% on N-MNIST as opposed to 81.03% with no downsampling at the same hidden layer size. On the N-Caltech101 data set, the downsampled system achieved a best case accuracy of 18.25%, compared with 7.43% achieved with no downsampling. The results show that downsampling is an important preprocessing technique in eventbased visual processing, especially for applications sensitive to power consumption and transmission bandwidth.
KW - classification
KW - detectors
UR - http://handle.westernsydney.edu.au:8081/1959.7/uws:45185
U2 - 10.1109/TNNLS.2017.2785272
DO - 10.1109/TNNLS.2017.2785272
M3 - Article
SN - 2162-237X
VL - 29
SP - 5030
EP - 5044
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 10
ER -