Empowering vehicle tracking in a cluttered environment with adaptive cellular automata suitable to intelligent transportation systems

摘要

Detecting and tracking moving vehicles in actual traffic scenes is an embryonic investigation field for smart transportation systems. This study presents the computational paradigm of fuzzy cellular automata (FCA) to manage the sensitive to environmental fluctuations limitation associated with the background subtraction methods for dynamic vehicle tracking. The suggested model extends FCA that is formed with rules supporting least sensitive fuzzy ‘exclusive or’ operation as next case logic to control levels of ambiguity in rule similarly functions. At each step, the refresh of background in frame difference proposals is established according to the number of active cells and fuzzy mapping function; so moving vehicles that their grey level is totally similar to the background grey level are easily identified. Furthermore, an occlusion handling routine based on visual measurement is engaged in discovering the classes of the vehicle occlusions and fragmenting the vehicle from each occlusive class. The empirical outcomes confirm that the suggested method is more accurate and powerful than conventional techniques for real-time vehicle tracking.