Deep Learning Based Garbage Detection for Autonomous Garbage Collection Vehicles

With the rapid technological advances and increasing human population, need for more production has emerged consumption increased accordingly. As a result of this consumption, garbage been generated. Environmental pollution caused by these garbages emerges as problem that people have to overcome both in Turkey world. Many studies conducted problem. Especially today, with development autonomous vehicles artificial intelligence, solutions using technologies increased. In study, new data set was created collection model proposed which can be used. The prepared images paper cups, is one most polluting garbage, taken different places, consisting without cups. Paper cups were detected from pre-trained Squenzenet, VGG-19 GoogLeNet convolutional neural networks. performance rate SquenzeNet, Vgg-19 networks used study found 97.77%, 96.44% 94.66%, respectively.