The authors have unveiled a novel dataset comprising discarded face masks, named MaskNet, alongside the introduction of a cutting-edge deep neural network architecture known as LitterNet. This innovative architecture is designed for rapid identification of abandoned face masks across diverse environments. Additionally, they have introduced a location-based intelligence model aimed at predicting areas with a heightened risk of hazardous litter in smart cities. This comprehensive framework offers valuable support to authorities in preemptively planning emergency responses to the dispersal of dangerous materials within residential settings.

Authors’ research has several novel contributions:

• The novel multi-location littered face mask dataset, called MaskNet, gathered for training machine learning models for autonomous detection and classifcation of discarded face masks in various urban and natural environments. This dataset is collected in Steyr, Austria, and Tehran, Iran, and to the best of our knowledge, is the frst dataset of littered medical face masks in diferent environments. Although currently there are several face mask datasets available online, the experimental results in this research prove that the detection of littered face mask using these datasets leads to low accuracy. In order to have an accurate deep neural network model for littered mask detection, face masks with various degrees of degradation and deformation, covered in various levels of dirt and in various natural backgrounds under diferent light conditions should be presents in the dataset. The proposed MaskNet dataset addresses these requirements.
• The second contribution of the paper is a new deep neural network architecture, called LitterNet, which is able to automatically detect and classify environments with discarded face masks with the accuracy of 96%. The speed of proposed model is 10 times faster than comparable architectures, which is an important factor in processing the required footage on the SoC processing units of edge surveillance nodes in the smart city with limited computational resources.
• The third contribution of this research is a location intelligence model which combines the output of LitterNet with various models interpolated from smart city geo-location datasets in order to provide a series of proposals for hazardous litter management intelligence in smart cities for emergency response management.

The architecture of LitterNet and the process of mask and trash detection.

The MaskNet dataset was collected in Austria and Iran in July 2020. The dataset was collected daily for seven days in Steyr, Austria, and Tehran, Iran, during diferent times of day from 6 A.M. up to 6 P.M. from diferent environments such as streets, parks, riverbanks, inside buildings and ofces. It consists of 1061 surgical masks images that are littered on the streets and other urban areas. In addition, images of streets without discarded masks were also collected. The original size of the dataset is 6.9 GB, and the photos have an image resolution of 3024 × 4032 pixels. The images are captured by three smartphones: An Apple iPhone 11, a Samsung Galaxy S8, and a Samsung Galaxy S10.

For sampling, the images were acquired with the default zoom of the aforementioned smartphones with the mask at the centre, top, bottom, corners of the image, and discarded masks were left in diferent states of deformation, various levels of dirt and near diferent objects, such as bins and bushes. In order to efciently train the model used in the proposed system and normalize the dataset, the size of the images is reduced to the image size of 540 × 720 pixels, which reduces the size of the dataset to 220 MB. In order to train the models, 70% of images are used for training the LitterNet deep neural network, 13% for cross-validation, and 17% for testing.