Improving a Real-Time Object Detector with Compact Temporal Information

Martin Ahrnbom, Morten Borno Jensen, Kalle Astrom, Mikael Nilsson, Hakan Ardo, Thomas Moeslund
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
Neural networks designed for real-time object detection have recently improved significantly, but in practice, looking at only a single RGB image at the time may not be ideal. For example, when detecting objects in videos, a foreground detection algorithm can be used to obtain compact temporal data, which can be fed into a neural network alongside RGB images. We propose an approach for doing this, based on an existing object detector, that re-uses pretrained weights for the processing of RGB
more » ... rocessing of RGB images. The neural network was tested on the VIRAT dataset with annotations for object detection, a problem this approach is well suited for. The accuracy was found to improve significantly (up to 66%), with a roughly 40% increase in computational time.
doi:10.1109/iccvw.2017.31 dblp:conf/iccvw/AhrnbomJANAM17 fatcat:zxmeotb43na47dwje7jp4dydtm