A deep transfer learning based approach to detect<scp>COVID</scp>‐19 waste

COVID-19 or Novel Coronavirus disease is not only creating a pandemic but also created another kind of problem, initiating group wastes, which called as waste. waste includes the mask, hand gloves, sanitizer bottles, Personal Protective Equipment (PPE) kits, syringes used to vaccinate people, etc. These wastes are now polluting every continent and ocean. Improper disposal such may increase rate spread contamination. In this regard, we decided build up detection model, will be able detect some wastes. We considered masks, initial get detected. collected dataset manually, annotated images with these three classes, then trained different CNN models compare accuracies for our dataset. got best model EfficientDet D0, gives mean average precision 0.82. Further, have developed UI deploy where general users can upload controlling threshold.