In your paper, "Traffic analysis without motion features", you have used the Dataset from the following sites:
In our research we are using a different object-centric CNN algorithm to perform traffic analysis. Do you happen to have all the images from the aforementioned dataset compiled in a public repository, which we could use for our research?
Training our algorithm with the same dataset would give us the opportunity to compare our work with the existing state-of-the-art methodologies such as yours.