Abstract
This paper presents an extensive research carried out for enhancing the performances of convolutional neural network (CNN) object detectors applied to municipal waste identification. In order to obtain an accurate and fast CNN architecture, several types of Single Shot Detectors (SSD) and Regional Proposal Networks (RPN) have been fine-tuned on the TrashNet database. The network with the best performances is executed on one autonomous robot system, which is able to collect detected waste from the ground based on the CNN feedback. For this type of application, a precise identification of municipal waste objects is very important. In order to develop a straightforward pipeline for waste detection, the paper focuses on boosting the performance of pre-trained CNN Object Detectors, in terms of precision, generalization, and detection speed, using different loss optimization methods, database augmentation, and asynchronous threading at inference time. The pipeline consists of data augmentation at the training time followed by CNN feature extraction and box predictor modules for localization and classification at different feature map sizes. The trained model is generated for inference afterwards. The experiments revealed better performances than all other Object Detectors trained on TrashNet or other garbage datasets with a precision of 97.63% accuracy for SSD and 95.76% accuracy for Faster R-CNN, respectively. In order to find the optimal higher and lower bounds of our learning rate where the network is actually learning, we trained our model for several epochs, updating the learning rate after each epoch, starting from 1 × 10−10 and decreasing it until reaching 1 × 10−1.
Highlights
Municipal waste sorting is becoming an important matter in cities across the European Union (EU)and beyond
This paper focuses on object identification based on municipal waste images, more precisely the AI techniques used for localization and classification
Since there are a limited number of images in the dataset, data augmentation has been applied in order to achieve better generalization and regularization in the fully connected layers using a dropout of 0.5, which has been added to randomly switch the neurons that are trained at each iteration
Summary
Municipal waste sorting is becoming an important matter in cities across the European Union (EU)and beyond. The most recent data showed that in the EU, 786 million tones of waste, excluding major mineral waste, were generated in 2016, equivalent to 35 % of the total waste generated. This means that in relation to population size, the EU generated, on average, 1.8 tones per inhabitant of waste, excluding major mineral waste, in 2016 [1]. Half of the waste (52.6 %) went through different recovery operations: recycling (36.7 % of the total recovered waste), backfilling (10.1 %), or energy recovery (5.8 %). The latest EU report, from 2016, shows that the average amount of municipal waste that has been recycled was 45%
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.