A Lightweight Neural Network Based on AlexNet-SSD Model for Garbage Detection

As the theory of deep learning develops, object detection technology has been widely used in all fields. How to find objects accurately and quickly is one of the key technologies. A usage scenario to be solved is proposed here, that is how to facilitate object detection technology in waste sorting. Hence, in this paper, a lightweight deep learning model is proposed. The basic network architecture of SSD(Single Shot MultiBox Detector) is changed to AlexNet. In this way, the capacity on object detection of SSD is remained, and the model parameters are greatly reduced. The experimental results show that the modified model can recognize the categories of waste accurately.