Take the 2-minute tour ×
Geographic Information Systems Stack Exchange is a question and answer site for cartographers, geographers and GIS professionals. It's 100% free, no registration required.

I need a detailed description of a GPS trajectories. I don't need to know what a GPS trajectory is, I already know it. Exactly I need a paper (better if scientific cut) that talk about different type of trajectories. e.g.: Difference in pedestrian, marine and car and highlight what difference presents from each other, can anyone help?

Best regards

share|improve this question
1  
Are you looking for an existing "mode detection" algorithm? Or do you want to create one? –  underdark Feb 18 '12 at 10:41
    
No, I just need to know the features that characterize different types of trajectories. e.g.: Pedestrian path are different from vehicle path because the first show low velocity and frequent change in heading. Marine traffic have no altitude feature. And so on... –  Mariano Feb 18 '12 at 12:01

2 Answers 2

You may be interested in the GeoLife stream of reasearch (PDF here) in which transportation mode is inferred from raw GPS tracks. Yan et al. also work on semantic enrichment of GPS tracks.

share|improve this answer
    
I already know these papers. Usefull but they are focus on how to do inference on trajectories and understand the type. It seems quite poor about description, and I need a description about it. –  Mariano Feb 19 '12 at 9:32

Two pointers that might be of some interest:


An approach that defines an algorithm to cluster trajectories including information about the direction of movement. There is pseudocode inside the paper demonstrating this approach, however I haven't seen an implementation of that.

Rocha, J. A. M. R.; Times, V. C.; Oliveira, G.; Alvares, L. O. & Bogorny, V. (2010), DB-SMoT: A direction-based spatio-temporal clustering method., in 'IEEE Conf. of Intelligent Systems' , IEEE, , pp. 114-119 .


Weka-STPM - Semantic Trajectory Preprocessing Module (alternative source). A module that extends Weka data mining toolset. It aims at mining trajectories in a higher abstraction level. Papers of interest detailing this solution:

Weka-STPM: from trajectory samples to semantic trajectories

Weka-STPM: a Software Architecture and Prototype for Semantic Trajectory Data Mining and Visualization


share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.