Improving a real-time object detector with compact temporal information

Neural networks designed for real-time object detection have recently improved significantly, but in practice, look- ing 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 images. The neural network was tested on the VIRAT dataset with annotations for object de- tection, a problem this approach is well suited for. The ac- curacy was found to improve significantly (up to 66%), with a roughly 40% increase in computational time.