Manoeuvre segmentation using smartphone sensors

Christopher Woo, Dana Kulic

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

10 Citations (Scopus)


In this paper, we propose a classifier-based approach for driving manoeuvre recognition from mobile phone data. We introduce a driving manoeuvre classifier using Support Vector Machines (SVM). We investigate the performance of a sliding window of velocity and angular velocity signals obtained using a smartphone as features for our classifier. Principal Component Analysis (PCA) is used for dimensionality reduction. The classifiers use a vehicle simulation for training data and experimental data for validation. A novel technique to extract the rotation matrix using PCA is presented to calibrate the smartphone's orientation. A classifier performance of 0.8158 average precision and 0.8279 average recall was achieved resulting in an average F1 score of 0.8194. Balanced accuracy was calculated to be 0.8874.

Original languageEnglish
Title of host publication2016 IEEE Intelligent Vehicles Symposium (IV 2016)
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781509018215
ISBN (Print)9781509018222
Publication statusPublished - 2016
Externally publishedYes
EventIntelligent Vehicles Symposium 2016 - Gotenburg, Sweden
Duration: 19 Jun 201622 Jun 2016 (Proceedings)


ConferenceIntelligent Vehicles Symposium 2016
Abbreviated titleIEEE IV 2016
Internet address


  • Global Positioning System
  • Gyroscopes
  • Intelligent vehicles
  • Principal component analysis
  • Support vector machines

Cite this