Comparative Analysis of Driving Maneuvers Using 3D Body Posture Data

Research has shown that driver inattention is the m ost prevalent cause of traffic collisions accountin g for an estimated 25 to 56% of crashes in the US. Driver i nattention may result from drivers engagement in se condary activities (such as texting or cellphone use), or l ack of awareness of the surrounding environment. The main objective of this research is to investigate the re lationship between potentially unsafe driving event s and the actual driver body posture and movements when performing a driving maneuver under different traffic configura tions. The paper presents results from a pilot study that capt ured the 3-D posture and activity of three drivers while performing both mandatory (merging) and discretionary (lane ch anging) maneuvers on freeway and arterial segments in Gainesville, Florida. The body posture of the driv ers was captured through the use of a low-cost infr ared depth sensor. A 7-point human skeletal model was fit to t he captured depth frame sequences using our proposed framework. The comparative analysis of the particip ants’ body movements while performing the maneuvers revealed differences between the participants’ body activity when performing the same maneuvers. The findings of this research provide significant insights regardin g which body movements may hide unsafe situations while performing a driving maneuver that requires the att ention of the surrounding environment.