Computer vision for solid waste sorting: A critical review of academic research

Qualitative classification of waste garments for textile recycling based on machine vision and attention mechanisms

The increasing volume of garment waste underscores the need for advanced sorting and recycling strategies. As a critical procedure in the secondary usage of waste clothes, qualitative classification of garments categorizes post-consumer clothes based on types and styles. However, this process currently relies on manual labor, which is inefficient, labor-intensive, and poses risks to workers. Despite efforts to implement automatic clothes classification systems, challenges persist due to visual complexities such as similar colors, deformations, and occlusions. In response to these challenges, this study introduces an enhanced intelligent machine vision system with attention mechanisms designed to automate the laborious and skill-demanding task of garment classification. Initially, a waste garment dataset comprising approximately 27,000 garments was curated using a self-developed automatic classification platform. Subsequently, the proposed attention method parameters were selected, and a series of benchmarks were conducted against state-of-the-art methods. Finally, the proposed system underwent a two-week online deployment to evaluate its running stability and sensitivity to similar colors, deformation, and occlusion in industrial production settings. The benchmarks indicate that the proposed method significantly improves classification accuracy across various models. The visualization interpretation of Grad-CAM reveals that the proposed method effectively handles complex environments by directing its focus toward garment-related pixels. Notably, the proposed system elevates classification accuracy from 68.28 % to human-level performance (>90 %) while ensuring greater running stability. This advancement holds promise for automating the classification process and potentially alleviating workers from labor-intensive and hazardous tasks associated with clothes recycling.

Low-Cost Recognition of Plastic Waste Using Deep Learning and a Multi-Spectral Near-Infrared Sensor

This work presents an approach for the recognition of plastics using a low-cost spectroscopy sensor module together with a set of machine learning methods. The sensor is a multi-spectral module capable of measuring 18 wavelengths from the visible to the near-infrared. Data processing and analysis are performed using a set of ten machine learning methods (Random Forest, Support Vector Machines, Multi-Layer Perceptron, Convolutional Neural Networks, Decision Trees, Logistic Regression, Naive Bayes, k-Nearest Neighbour, AdaBoost, Linear Discriminant Analysis). An experimental setup is designed for systematic data collection from six plastic types including PET, HDPE, PVC, LDPE, PP and PS household waste. The set of computational methods is implemented in a generalised pipeline for the validation of the proposed approach for the recognition of plastics. The results show that Convolutional Neural Networks and Multi-Layer Perceptron can recognise plastics with a mean accuracy of 72.50% and 70.25%, respectively, with the largest accuracy of 83.5% for PS plastic and the smallest accuracy of 66% for PET plastic. The results demonstrate that this low-cost near-infrared sensor with machine learning methods can recognise plastics effectively, making it an affordable and portable approach that contributes to the development of sustainable systems with potential for applications in other fields such as agriculture, e-waste recycling, healthcare and manufacturing.

A construction waste landfill dataset of two districts in Beijing, China from high resolution satellite images

Construction waste is unavoidable in the process of urban development, causing serious environmental pollution. Accurate assessment of municipal construction waste generation requires building construction waste identification models using deep learning technology. However, this process requires high-quality public datasets for model training and validation. This study utilizes Google Earth and GF-2 images as the data source to construct a specific dataset of construction waste landfills in the Changping and Daxing districts of Beijing, China. This dataset contains 3,653 samples of the original image areas and provides mask-labeled images in the semantic segmentation domains. Each pixel within a construction waste landfill is classified into 4 categories of the image areas, including background area, vacant landfillable area, engineering facility area, and waste dumping area. The dataset contains 237,115,531 pixels of construction waste and 49,724,513 pixels of engineering facilities. The pixel-level semantic segmentation labels are provided to quantify the construction waste yield, which can serve as the basic data for construction waste extraction and yield estimation both for academic and industrial research.

Data Science Applications in Circular Economy: Trends, Status, and Future

The circular economy (CE) aims to decouple the growth of the economy from the consumption of finite resources through strategies, such as eliminating waste, circulating materials in use, and regenerating natural systems. Due to the rapid development of data science (DS), promising progress has been made in the transition toward CE in the past decade. DS offers various methods to achieve accurate predictions, accelerate product sustainable design, prolong asset life, optimize the infrastructure needed to circulate materials, and provide evidence-based insights. Despite the exciting scientific advances in this field, there still lacks a comprehensive review on this topic to summarize past achievements, synthesize knowledge gained, and navigate future research directions. In this paper, we try to summarize how DS accelerated the transition to CE. We conducted a critical review of where and how DS has helped the CE transition with a focus on four areas including (1) characterizing socioeconomic metabolism, (2) reducing unnecessary waste generation by enhancing material efficiency and optimizing product design, (3) extending product lifetime through repair, and (4) facilitating waste reuse and recycling. We also introduced the limitations and challenges in the current applications and discussed opportunities to provide a clear roadmap for future research in this field.

Smart-sight: Video-based waste characterization for RDF-3 production

A material recovery facility (MRF) can transform municipal solid waste (MSW) into a valued commodity called refuse-derived fuel (RDF) as a promising solution to waste-to-energy conversion. The quality of the produced RDF significantly relies on the composition of in-feed waste and waste characterization method applied for auditing purposes, a process that is both time-consuming and fraught with potential hazards. This study focuses to enhance the workflow of the waste characterization process at an MRF. A solution named Smart Sight is proposed to detect and classify waste based on videos recorded after processing MSW through a mechanical sorting line consisting of bag breakers and trommel screens. A comprehensive dataset is created encompassing thirteen mixed waste classes from single and multi-family streams. The dataset is preprocessed with motion compensation techniques and frame differencing methods to extract and refine valuable frames. A one-stage YOLO detector model is then trained over the dataset. The experimental results show that the proposed method works efficiently at detecting and classifying waste objects in indoor MRF environments. Accuracy, precision, recall, and F1 score related to the proposed solution are found to be 0.70, 0.762, 0.69 and 0.72, respectively, with a mAP@0.5 of 0.716. The proposed approach is validated using data collected from local MRF by comparing the estimated waste composition values of the proposed solution with laboratory results obtained through current standardized industrial practices. Comparison reveals that waste characterization estimation obtained is consistent with the laboratory results, inferring that Smart-Sight is a viable tool for estimating waste composition.

DSYOLO-trash: An attention mechanism-integrated and object tracking algorithm for solid waste detection

In a global context, the production of urban solid waste significantly varies with changes in living standards. This trend exhibits diversity across different countries and regions, reflecting shifts in lifestyles as well as varying needs and challenges in waste management strategies. However, current standards of waste recycling are too complex for the general public to follow. In this study, we propose a model called DSYOLO-Trash to identify solid waste by integrating the dual attention mechanisms convolutional block attention module (CBAM) and Contextual Transformer Networks(CotNet), which significantly enhance its ability to mine channel-related and spatial attention features while optimizing the learning process. We apply the deep simple online and realtime tracking (DeepSORT) object tracking algorithm to solid waste detection for the first time in the literature to enable the real-time identification and tracking of waste. We also develop a multi-label dataset of mixed solid waste, called MMTrash, to realistically simulate actual scenarios of waste classification. Our proposed DSYOLO-Trash delivered superior performance to classical detection algorithms on both the MMTrash and the TrashNet datasets. Our system combines the improved you only look once(YOLO) algorithm with DeepSORT technology by using industrial cameras and PLC-controlled robotic arms to intelligently sort waste. The work here constitutes an important contribution to intelligent waste management and the sustainable development of cities.

Volume Determination Challenges in Waste Sorting Facilities: Observations and Strategies

In this case study on volume determination in waste sorting facilities, we evaluate the effectiveness of ultrasonic sensors and address waste-material-specific challenges. Although ultrasonic sensors offer a cost-effective automation solution, their accuracy is affected by irregular waste shapes, varied compositions, and environmental factors. Notable inconsistencies in volume measurements between storage bunkers and conveyor belts underscore the need for a comprehensive approach to standardize bale production. With prediction reliability being constrained by limited datasets, undocumented modifications to machine settings, and sensor failures, this task renders a challenging application area for machine learning. We explore related research and present dataset analyses from three distinct waste sorting facilities in Europe, addressing issues such as sensor usability, data quality, and material specifics. Our analysis suggests promising strategies and future directions for enhancing waste volume measurement accuracy, ultimately aiming to advance sustainable waste management.

GCDN-Net: Garbage classifier deep neural network for recyclable urban waste management

The escalating waste volume due to urbanization and population growth has underscored the need for advanced waste sorting and recycling methods to ensure sustainable waste management. Deep learning models, adept at image recognition tasks, offer potential solutions for waste sorting applications. These models, trained on extensive waste image datasets, possess the ability to discern unique features of diverse waste types. Automating waste sorting hinges on robust deep learning models capable of accurately categorizing a wide range of waste types. In this study, a multi-stage machine learning approach is proposed to classify different waste categories using the "Garbage In, Garbage Out" (GIGO) dataset of 25,000 images. The novel Garbage Classifier Deep Neural Network (GCDN-Net) is introduced as a comprehensive solution, adept in both single-label and multi-label classification tasks. Single-label classification distinguishes between garbage and non-garbage images, while multi-label classification identifies distinct garbage categories within single or multiple images. The performance of GCDN-Net is rigorously evaluated and compared against state-of-the-art waste classification methods. Results demonstrate GCDN-Net's excellence, achieving 95.77% accuracy, 95.78% precision, 95.77% recall, 95.77% F1-score, and 95.54% specificity when classifying waste images, outperforming existing models in single-label classification. In multi-label classification, GCDN-Net attains an overall Mean Average Precision (mAP) of 0.69 and an F1-score of 75.01%. The reliability of network performance is affirmed through saliency map-based visualization generated by Score-CAM (class activation mapping). In conclusion, deep learning-based models exhibit efficacy in categorizing diverse waste types, paving the way for automated waste sorting and recycling systems that can mitigate costs and processing times.

A computer vision-based system for real-time component identification from waste printed circuit boards

With an exponential increase in consumers' need for electronic products, the world is facing an ever-increasing economic and environmental threat of electronic waste (e-waste). To minimize their adverse effects, e-waste recycling is one of the pivotal factors that can help in minimizing the environmental pollution andto increase recovery of valuable materials. For instance, Printed Circuit Boards (PCBs), while they have several valuable elements, they are hazardous too; and therefore, they form a large chunk of e-waste being generated today. Thus, in recycling PCBs, Electronic Components (ECs) are segregated at first, and separately processed for recovering key elements that could be re-used. However, in the current recycling process, especially in developing nations, humans manually screen ECs, which goes on to affect their health. It also causes losses of valuable materials. Therefore, automated solutions need to be adopted for both to classify and to segregate ECs from waste PCBs. The study proposes a robust EC identification system based on computer vision and deep learning algorithms (YOLOv3) to automate sorting process which would help in further processing. The study uses a publicly available dataset, and a PCB dataset which reflect challenging recycling environments like lighting conditions, cast shadows, orientations, viewpoints, and different cameras/resolutions. The outcome of YOLOv3 detection model based on training of both datasets presents satisfactory classification accuracy and capability of real-time competent identification, which in turn, could help in automatically segregating ECs, while leading towards effective e-waste recycling.

Deep learning-based models for environmental management: Recognizing construction, renovation, and demolition waste in-the-wild

The construction industry generates a substantial volume of solid waste, often destinated for landfills, causing significant environmental pollution. Waste recycling is decisive in managing waste yet challenging due to labor-intensive sorting processes and the diverse forms of waste. Deep learning (DL) models have made remarkable strides in automating domestic waste recognition and sorting. However, the application of DL models to recognize the waste derived from construction, renovation, and demolition (CRD) activities remains limited due to the context-specific studies conducted in previous research. This paper aims to realistically capture the complexity of waste streams in the CRD context. The study encompasses collecting and annotating CRD waste images in real-world, uncontrolled environments. It then evaluates the performance of state-of-the-art DL models for automatically recognizing CRD waste in-the-wild. Several pre-trained networks are utilized to perform effectual feature extraction and transfer learning during DL model training. The results demonstrated that DL models, whether integrated with larger or lightweight backbone networks can recognize the composition of CRD waste streams in-the-wild which is useful for automated waste sorting. The outcome of the study emphasized the applicability of DL models in recognizing and sorting solid waste across various industrial domains, thereby contributing to resource recovery and encouraging environmental management efforts.

Augmented reality-enabled human-robot collaboration to balance construction waste sorting efficiency and occupational safety and health

Construction waste sorting (CWS) is highly recommended as a key step for construction waste management. However, current CWS involves humans' manual hand-picking, which poses significant threats to their occupational safety and health (OSH). Robotic sorting promises to change the situation by adopting modern artificial intelligence and automation technologies. However, in practice, it is usually challenging for robots to do an efficient job (e.g., measured by quickness and accuracy) owing to the difficulties in precisely recognizing compositions of the mixed and heterogeneous waste stream. Leveraging augmented reality (AR) as a communication interface, this research aims to develop a human-robot collaboration (HRC) approach to address the dilemmatic balance between CWS efficiency and OSH. Firstly, a model for human-robot collaborative sorting using AR is established. Then, a prototype for the AR-enable collaborative sorting system is developed and evaluated. The experimental results demonstrate that the proposed AR-enabled HRC method can improve the accuracy rate of CWS by 10% and 15% for sorting isolated waste and obscured waste, respectively, when compared to the method without human involvement. Interview results indicate a significant improvement in OSH, especially the reduction of contamination risks and machinery risks. The research lays out a human-robot collaborative paradigm for productive and safe CWS via an immersive and interactive interface like AR.

AerialWaste dataset for landfill discovery in aerial and satellite images

Illegal landfills are sites where garbage is dumped violating waste management laws. Aerial images enable the use of photo interpretation for territory scanning and landfill detection but this practice is hindered by the manual nature of this task which also requires expert knowledge. Deep Learning methods can help capture the analysts' expertise and build automated landfill discovery tools. However, this goal requires public high-quality datasets for model training and testing. At present no such datasets exist and this gap penalizes the research toward scalable and accurate landfill discovery methods. We present a dataset for landfill detection featuring airborne, WorldView-3, and GoogleEarth images annotated by professional photo interpreters. It comprises 3,478 positive and 6,956 negative examples. Most positive instances are characterized by metadata: the type of waste, its storage mode, the type of the site, and the evidence and severity of the illicit. The dataset has been technically validated by building an accurate landfill detector and is accompanied by a visualization and annotation tool.

Recent advances in applications of artificial intelligence in solid waste management: A review

Efficient management of solid waste is essential to lessen its potential health and environmental impacts. However, the current solid waste management practices encounter several challenges. The development of effective waste management systems using advanced technologies is vital to overcome the challenges faced by the current approaches. Artificial Intelligence (AI) has emerged as a powerful tool for applications in various fields. Several studies also reported the applications of AI techniques in the management of solid waste. This article critically reviews the recent advancements in the applications of AI techniques for the management of solid waste. Various AI and hybrid techniques have been successfully employed to predict the performance of various methods used for the generation, segregation, storage, and treatment of solid waste. The key challenges that limit the applications of AI in solid waste are highlighted. These include the availability and selection of applicable data, poor reproducibility, and less evidence of applications in real solid waste. Based on identified gaps and challenges, recommendations for future work are provided. This review is beneficial for all stakeholders in the field of solid waste management, including policy-makers, governments, waste management organizations, municipalities, and researchers.

Spatially varying associations between the built environment and older adults' propensity to walk

Population aging has become a severe issue facing most nations and areas worldwide-with Hong Kong being no exception. For older adults, walking is among the most well-liked travel modes, boosting their overall health and wellbeing. Some studies have confirmed that the built environment has a significant (spatially fixed) influence on older adults' walking behavior. However, little consideration has been given to the potential spatial heterogeneity in such influences. Hence, this study extracted data on older adults' (outdoor) walking behavior from the 2011 Hong Kong Travel Characteristics Survey and measured a series of built environment attributes based on geo-data (e.g., Google Street View imagery). Logistic regression and geographically weighted logistic regression models were developed to unveil the complicated (including spatially fixed and heterogeneous) association between the built environment and older adults' propensity to walk. We show that population density, land-use mix, street greenery, and access to bus stops are positively connected with the propensity to walk of older adults. Intersection density seems to impact walking propensity insignificantly. All built environment attributes have spatially heterogeneous effects on older adults' walking behavior. The percentage of deviance explained is heterogeneously distributed across space.

Multi-View Learning for Material Classification

Material classification is similar to texture classification and consists in predicting the material class of a surface in a color image, such as wood, metal, water, wool, or ceramic. It is very challenging because of the intra-class variability. Indeed, the visual appearance of a material is very sensitive to the acquisition conditions such as viewpoint or lighting conditions. Recent studies show that deep convolutional neural networks (CNNs) clearly outperform hand-crafted features in this context but suffer from a lack of data for training the models. In this paper, we propose two contributions to cope with this problem. First, we provide a new material dataset with a large range of acquisition conditions so that CNNs trained on these data can provide features that can adapt to the diverse appearances of the material samples encountered in real-world. Second, we leverage recent advances in multi-view learning methods to propose an original architecture designed to extract and combine features from several views of a single sample. We show that such multi-view CNNs significantly improve the performance of the classical alternatives for material classification.