We are working on the problem of outdoor activity recognition, for this purpose, we need to test our approaches using a dataset that contains users' mobility traces, we need both the continuous GPS recordings and the visited places.
Hi Mehdi. I was the chair of the ECML 2015 Discovery Challenge. We published the dataset of the competition in the UCI repository. It has gps traces of the taxi busy services for a period of one year. It has no labelled visited places...but you can easily label some of them (such as downtown, train station or airport) with a simple haversine distance function. The granulairty of the dataset is 15 seconds.
https://archive.ics.uci.edu/ml/datasets/Taxi+Service+Trajectory+-+Prediction+Challenge,+ECML+PKDD+2015
I hope that this helps.
Best,
Luis
Dear Luis,
Thank you for your answer the dataset is very intersting, however, our activity recognition approach is made principally for pedestrians since we track the changes in users' orientation . I fear the dataset aren't going to make it.
Best,
Mehdi
Yeah...thats would be difficult then. I cannot help you that much.
Best,
Luis
Maybe this link helps
https://privamov.github.io/accio/docs/datasets.html