We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Real-time detection and monitoring of public littering behavior using deep learning for a sustainable environment
Summary
Researchers developed an AI-powered surveillance system called SAWN that uses video cameras and deep learning models to detect public littering by vehicles and pedestrians in real time, achieving up to 99.5% accuracy — offering a scalable tool to reduce plastic pollution at its source.
With the global population surpassing 8 billion, waste production has skyrocketed, leading to increased pollution that adversely affects both terrestrial and marine ecosystems. Public littering, a significant contributor to this pollution, poses severe threats to marine life due to plastic debris, which can inflict substantial ecological harm. Additionally, this pollution jeopardizes human health through contaminated food and water sources. Given the annual global plastic consumption of approximately 475 million tons and the pervasive issue of public littering, addressing this challenge has become critically urgent. The Surveillance and Waste Notification (SAWN) system presents an innovative solution to combat public littering. Leveraging surveillance cameras and advanced computer vision technology, SAWN aims to identify and reduce instances of littering. Our study explores the use of the MoViNet video classification model to detect littering activities by vehicles and pedestrians, alongside the YOLOv8 object detection model to identify individuals responsible through facial recognition and license plate detection. Collecting appropriate data for littering detection presented significant challenges due to its unavailability. Consequently, project members simulated real-life littering scenarios to gather the required data. This dataset was then used to train different models, including LRCN, CNN-RNN, and MoViNets. After extensive testing, MoViNets demonstrated the most promising results. Through a series of experiments, we progressively improved the model's performance, achieving accuracy rates of 93.42% in the first experiment, 95.53% in the second, and ultimately reaching 99.5% in the third experiment. To detect violators' identities, we employed YOLOv8, trained on the KSA vehicle plate dataset, achieving 99.5% accuracy. For face detection, we utilized the Haar Cascade from the OpenCV library, known for its real-time performance. Our findings will be used to further enhance littering behavior detection in future developments.
Sign in to start a discussion.
More Papers Like This
An Automatic Garbage Classification System Based on Deep Learning
Researchers developed an automated garbage classification system using a deep learning algorithm based on ResNet-34, achieving 99% classification accuracy with a processing time of under one second per item. Automated waste sorting technology like this could improve the efficiency of plastic waste recovery and reduce mismanaged plastic that eventually becomes environmental pollution.
Development of Drifting Debris Detection System using Deep Learning on Coastal Cleanup
Researchers developed a deep learning-based system to detect litter on beaches using images and automated object recognition. Efficient litter detection tools could help coastal cleanup programs identify and remove plastic debris before it breaks down into microplastics.
Automated Plastic Waste Detection Using Advanced Deep Learning Frameworks
Researchers developed a deep learning system using advanced neural network frameworks for automated detection and classification of plastic waste from images, achieving high accuracy in identifying multiple plastic types to support environmental monitoring and waste sorting.
A Smart Garbage Classification based on Deep Learning
Researchers developed an AI-powered garbage classification system using deep learning to automatically sort waste categories. Accurate automated waste sorting could improve plastic recycling rates, reducing the amount of plastic that eventually breaks down into environmental microplastics.
Advancing Plastic Pollution Monitoring Through Enhanced Protocols and Deep Learning: applicability and effectiveness in real-world scenarios (Le Stang, France)
Researchers developed and tested a deep learning image analysis tool to enhance monitoring of beach plastic pollution, specifically targeting meso- and large microplastics at the wrack line in Brittany, France. The AI model achieved high detection accuracy under real-world conditions and integrated with established French national monitoring protocols, demonstrating feasibility for scalable automated beach litter surveillance.