Traffic Regulator Detection and Identification from Crowdsourced Data—A Systematic Literature Review

Abstract

Mapping with surveying equipment is a time-consuming and cost-intensive procedure thatmakes the frequent map updating unaffordable. In the last few years, much research has focused oneliminating such problems by counting on crowdsourced data, such as GPS traces. An importantsource of information in maps, especially under the consideration of forthcoming self-driving vehicles,is the traffic regulators. This information is largely lacking in maps like OpenstreetMap (OSM) andthis article is motivated by this fact. The topic of this systematic literature review (SLR) is the detectionand recognition of traffic regulators such as traffic lights (signals), stop-, yield-, priority-signs, right ofway priority rules and turning restrictions at intersections, by leveraging non imagery crowdsourceddata. More particularly, the aim of this study is (1) to identify the range of detected and recognisedregulatory types bycrowdsensingmeans, (2) to indicate the different classification techniques thatcan be used for these two tasks, (3) to assess the performance of different methods, as well as (4)to identify important aspects of the applicability of these methods. The two largest databases ofpeer-reviewed literature were used to locate relevant research studies and after different screeningsteps eleven articles were selected for review. Two major findings were concluded—(a) most regulatortypes can be identified with over 80% accuracy, even using heuristic-driven approaches and (b) underthe current progress on the field, no study can be reproduced for comparative purposes nor can solelyrely on open data sources due to lack of publicly available datasets and ground truth maps. Futureresearch directions are highlighted as possible extensions of the reviewed studies.