Maneuver identification using elastic template matching: multi-case study ?

摘要

Advanced driver assistance systems (ADAS), which can either help to prevent accidents or reduce their negative consequences by intervening in a wide variety of ways, are the solution of choice for considerably greater safety in traffic and comfortable driving. Further, they can be used to perform various improvements such as optimizing fuel consumption or emissions. In conjunction with the driver, they form human machine systems (HMS) with varying degrees of complexity and automation. In order to pass the numerous checks and meet certain standards, ADAS must recognize the surrounding traffic as quickly and accurately as possible in order to act upon it. As a result, rapid and accurate identification methods are required to ensure this. Available approaches still have a lot of potential for optimization in terms of speed and accuracy and in the present work we are aiming to improve the elastic template matching algorithm developed by the authors in a previous study. We extend the approach with a training-free continuous and simultaneous detection of several maneuvers by means of the so-called Nearest Neighbour Algorithm, which in our case transforms into Nearest Centroid Classifier. Moreover, the approach can be easily used for multi-vehicle scenarios; though by treating each vehicle as a separate object without taking into account their interactions.