Edge-Computing Video Analytics Solution for Automated Plastic-Bag Contamination Detection: A Case from Remondis

Abstract

The increased global waste generation rates over the last few decades have made the waste management task a significant problem. One of the potential approaches adopted globally is to recycle a significant portion of generated waste. However, the contamination of recyclable waste has been a major problem in this context and causes almost 75% of recyclable waste to be unusable. For sustainable development, efficient management and recycling of waste are of huge importance. To reduce the waste contamination rates, conventionally, a manual bin-tagging approach is adopted; however, this is inefficient and requires huge labor effort. Within household waste contamination, plastic bags have been found to be one of the main contaminants. Towards automating the process of plastic-bag contamination detection, this paper proposes an edge-computing video analytics solution using the latest Artificial Intelligence (AI), Artificial Intelligence of Things (AIoT) and computer vision technologies. The proposed system is based on the idea of capturing video of waste from the truck hopper, processing it using edge-computing hardware to detect plastic-bag contamination and storing the contamination-related information for further analysis. Faster R-CNN and You Only Look Once version 4 (YOLOv4) deep learning model variants are trained using the Remondis Contamination Dataset (RCD) developed from Remondis manual tagging historical records. The overall system was evaluated in terms of software and hardware performance using standard evaluation measures (i.e., training performance, testing performance, Frames Per Second (FPS), system usage, power consumption). From the detailed analysis, YOLOv4 with CSPDarkNet_tiny was identified as a suitable candidate with a Mean Average Precision (mAP) of 63% and FPS of 24.8 with NVIDIA Jetson TX2 hardware. The data collected from the deployment of edge-computing hardware on waste collection trucks was used to retrain the models and improved performance in terms of mAP, False Positives (FPs), False Negatives (FNs) and True Positives (TPs) was achieved for the retrained YOLOv4 with CSPDarkNet_tiny backbone model. A detailed cost analysis of the proposed system is also provided for stakeholders and policy makers.

Dhad—A Children’s Handwritten Arabic Characters Dataset for Automated Recognition

“…Fine-tuning of Existing Models: An important insight from the performed experiments is the unparalleled efficacy of fine-tuning existing deep learning architectures. This approach resonates with the existing literature [29][30][31], highlighting the potential of harnessing pre-trained models fine-tuned for application-specific tasks. The flexibility of fine-tuning, which combines using general features with adjusting to specific dataset details, highlights its essential importance.…”

Advanced IoT Pressure Monitoring System for Real-Time Landfill Gas Management

“…In line with waste collection, our research group has also explored the realm of edge computing to address waste collection compliance. We have leveraged edge devices such as NVIDIA Jetson modules to enable automatic waste identification on collection trucks using video analytics [50]. The integration of standalone sensors, as discussed in our previous discussion, could complement visual data and contribute to an enhanced real-time compliance model.…”

An Efficient Edge Computing-Enabled Network for Used Cooking Oil Collection

“…In [30], the authors proposed an edge-computing solution for automated detection of plastic-bag contamination in waste. The system enhances waste collection efficiency by reducing manual labor and increasing the contamination detection speed.…”

“…Leveraging the benefits brought about by each of the computing models, a collaborative cloud-fog-edge architecture has the potential to provide efficient disposal and collection tasks. [31] Marginal Excellent Good Iqbal et al [30] Marginal Good Good…”