Real Time Detection Of Waste Type Using Single Shot Multibox Detector

Abdiansah Abdiansah (Artificial Intelligence Laboratory, Universitas Sriwijaya, South-Sumatera, Indonesia)
M. Qurhanul Rizqie (Artificial Intelligence Laboratory, Universitas Sriwijaya, South-Sumatera, Indonesia)
M. Hatta Aldino Ramadhan (Artificial Intelligence Laboratory, Universitas Sriwijaya, South-Sumatera, Indonesia)

Sriwijaya Journal of Informatics and Applications
Vol 3, No 1 (2022)

The lack of human initiative to manage their own wastes is one of many reasons why waste management in residential area is not optimal. A system to detect waste type in real time is a necessity to support the waste management process to be faster and optimal. This research propose the waste type detection systems using 2 types of Single Shot Multibox Detector models, SSD300 and SSD512. Both models were compared based on the accuracy and speed of detection on TACO dataset dan Waste Classification Data. SSD512 achieves a better accuracy of 0.63 mAP compared to the accuracy of SSD300, which is 0.57 mAP. Both models can also be said to be real time, with the SSD300's detection speed being faster at 51 fps compared to the SSD512's detection speed at 28 fps.