Traffic light detection and recognition (TLR) research has grown every year. In addition,\nMachine Learning (ML) has been largely used not only in traffic light research but in every field\nwhere it is useful and possible to generalize data and automatize human behavior. ML algorithms\nrequire a large amount of data to work properly and, thus, a lot of computational power is required to\nanalyze the data. We argue that expert knowledge should be used to decrease the burden of collecting\na huge amount of data for ML tasks. In this paper, we show how such kind of knowledge was used\nto reduce the amount of data and improve the accuracy rate for traffic light detection and recognition.\nResults show an improvement in the accuracy rate around 15%. The paper also proposes a TLR\ndevice prototype using both camera and processing unit of a smartphone which can be used as a\ndriver assistance. To validate such layout prototype, a dataset was built and used to test an ML model\nbased on adaptive background suppression filter (AdaBSF) and Support Vector Machines (SVMs).\nResults show 100% precision rate and recall of 65%.
Loading....