Automatic detection and classification system of domestic waste via multi-model cascaded convolutional neural network

Domestic waste classification was incorporated into legal provisions recently in China. The workforce for domestic waste detection and classification is inefficient. We proposed a Multi-model Cascaded Convolutional Neural Network (MCCNN) for domestic waste image detection and classification. MCCNN combined three subnetworks (DSSD, YOLOv4, and Faster-RCNN) to obtain the detections. Moreover, to suppress the false-positive predicts, we utilized a classification model cascaded with the detection part to judge whether the detection results are correct. To train and evaluate MCCNN, we designed a large-scale waste image dataset (LSWID), containing 30,000 domestic waste multi-labeled images with 52 categories. To the best of our knowledge, the LSWID is the largest dataset on domestic waste images. Furthermore, a smart trash can (STC) is designed and applied to a Shanghai community, which helped save time and make waste recycling more efficient. Experimental results showed a state-of-the-art performance, with an average improvement of 10% in detection precision.