Countor: count without bells and whistles

The effectiveness of an Intelligent transportation system (ITS) relies on the understanding of the vehicles behaviour. Different approaches are proposed to extract the attributes of the vehicles as Re-Identification (ReID) or multi-target single camera tracking (MTSC). The analysis of those attributes leads to the behavioural tasks as multi-target multicamera tracking (MTMC) and Turn-counts (Count vehicles that go through a predefined path). In this work, we propose a novel approach to Turn-counts which uses a MTSC and a proposed path classifier. The proposed method is evaluated on CVPR AI City Challenge 2020. Our algorithm achieves the second place in Turn-counts with a score of 0.9346.