Constructing an automatic object-recognition algorithm using labeling information for efficient recycling of WEEE

Hayashi, Naohito; Koyanaka, Shigeki; Oki, Tatsuya

doi:10.1016/j.wasman.2019.03.065

Cited by 20 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These changes would result in efficient management of the reuse, repair, and recycle phase of products and components. Hayashi et al (2019) used scanning of product labels to identify manufacturer and model names on discarded digital cameras. They used both the manufacturer's logo and optical character recognition processing and were able to identify manufacturers and models even when the equipment was moving on a conveyor belt, a typical situation in a recycle plant.…”

Section: Discussionmentioning

confidence: 99%

A comparative study of national variations of the European WEEE directive: manufacturer’s view

Andersen

2021

Environ Sci Pollut Res

View full text Add to dashboard Cite

We are facing the challenge of rapid growth in waste from electrical products (e-waste). In Europe, handling e-waste is regulated by the European Waste Electrical and Electronic Equipment (WEEE) directive, which is based on the extended producer responsibility (EPR) model as a regulatory tool forcing manufacturers and importers to take responsibility for their products throughout their lifecycles. However, the directive allows for great variations in implementations in each country, causing e-manufacturers and e-waste handling operators to face challenges in their transition to more sustainable operations. To identify the challenges involved, this study investigates the effect of the WEEE directive from a manufacturer’s perspective. A case study of an e-manufacturer operating subsidiaries in several European countries and the associated producer responsibility organizations (PROs) is presented. The case study includes interviews from 17 stakeholders in 12 organizations in eight European countries. Key findings are as follows. First, the WEEE data reported are not harmonized. Second, the calculations of the environmental fee differ across countries. Third, following up on different national WEEE obligations sometimes leads to over-reporting to avoid negative effects on environmental corporate social responsibility, brand reputation, and profitability. Fourth, outsourcing end-of-life (EoL) treatment responsibility to PROs is seen as positive by the manufacturer but results in a decoupling of the EPR and the operational EoL treatment, which may reduce efforts to transfer to a higher circularity level of its EEE products. Fifth, WEEE is considered a way for e-manufacturers to handle waste not to adopt a circular focus. This paper contributes to both practitioners and researchers within reverse logistics and sustainability by adding knowledge from real-life context of how EPR is implemented in WEEE.

show abstract

Section: Discussionmentioning

confidence: 99%

A comparative study of national variations of the European WEEE directive: manufacturer’s view

Andersen

2021

Environ Sci Pollut Res

View full text Add to dashboard Cite

show abstract

“…The core idea of the algorithm is to construct the global energy function by using the minimum cut and maximum flow methods, so as to optimize the parallax solution [9]. At the same time, in order to eliminate flicker effect and noise, spatio-temporal consistency processing is also required to realize spatial smoothing [10]. See formula (1) for the energy function of parallax calculation.…”

Section: Parallax Calculation and Depth Map Extractionmentioning

confidence: 99%

“…The resolution is m by sliding window overlap M×N depth map expansion detection, and the image needs to be divided into w windows. See formula (10) for the calculation function.…”

Section: ( )mentioning

confidence: 99%

“…In formula (10), the number of image horizontal windows is expressed in ψ and the number of image vertical windows is expressed in ϕ . According to the w feature windows formed by sliding detection, w feature sequences can be obtained, and each feature sequence is composed of p-dimensional feature vector, and then w can be obtained W×p, and then PCA is selected to reduce the dimension.…”

Section: ( )mentioning

confidence: 99%

See 1 more Smart Citation

Obstacle Avoidance and Environmental Adaptability Analysis of Snake-like Robot Based on Deep Learning

Zou¹

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Aiming at the problems of high complexity and low accuracy of visual depth map feature recognition, a graph recognition algorithm based on principal component direction depth gradient histogram (pca-hodg) is designed in this study. In order to obtain high-quality depth map, it is necessary to calculate the parallax of the visual image. At the same time, in order to obtain the quantized regional shape histogram, it is necessary to carry out edge detection and gradient calculation on the depth map, then reduce the dimension of the depth map combined with the principal component, and use the sliding window detection method to reduce the dimension again to realize the feature extraction of the depth map. The results show that compared with other algorithms, the pca-hodg algorithm designed in this study improves the average classification accuracy and significantly reduces the average running time. This shows that the algorithm can reduce the running time by reducing the dimension, extract the depth map features more accurately, and has good robustness.

show abstract

“…It would require substantial enhancements to identify and sort a highly complex variety of products. Technology is emerging to support such advanced identification, for example through watermarks (e.g., the Holy Grail Project [101]) or object recognition technology [102]. Nevertheless, the implementation of this technology requires systemic and collaborative change.…”

Section: Reusable Fmcgs Become "Slow-moving Consumer Goods" and Require System-wide Changementioning

confidence: 99%

Characterisation and Environmental Value Proposition of Reuse Models for Fast-Moving Consumer Goods: Reusable Packaging and Products

et al. 2021

View full text Add to dashboard Cite

Fast-Moving Consumer Goods (FMCGs) are products that are purchased and consumed frequently to satisfy continuous consumer demand. In a linear economy, FMCGs are typically offered as single-use and disposable products. Limitations in product design, insufficient collection systems, and inefficient recovery processes prevent high recycling rates. As a result, FMCGs often end up in landfill or the environment, contributing to waste accumulation, and pollution. Whilst recycling is the most common waste prevention strategy practiced by the industry, the process is limited to addressing only the final stage of the product life cycle, omitting the overproduction and consumption of materials typical of FMCGs. Instead, reuse is a strategy that is capable of extending the value of resources by slowing material flows. Novel reuse models that require the consumer to interact with durable primary packaging and products are emerging in the FMCG industry. However, the constituent elements and operation principles of such reuse models are not fully understood. The aim of this research is to develop a comprehensive characterisation of reuse models and to evaluate their potential to deliver environmental value. Method: Ninety-two reuse offerings were selected and analysed to identify their reuse system elements. The analysis led to the identification of a framework including five reuse models, which were also evaluated to establish their capability to deliver environmental value when compared to conventional single-use and disposable FMCGs. Results: Currently in the FMCG sector, reusable products are mostly durable packaging, such as bottles and containers for beverages, foods, personal and home care goods, and are infrequently durable products, such as personal and baby care goods, including razors and nappies. Three reuse models involve exclusive reuse, a behaviour by which a reusable product is used and kept by a single user throughout the product lifetime. In exclusive reuse models, users are provided with either a reusable product (model 1), a reusable product with preparation for reuse infrastructure (model 2), or access to preparation for reuse infrastructure (model 3). Two reuse models involve sequential reuse, a behaviour by which a reusable product is used by multiple users throughout the product lifetime and returned after each use to a provider. In sequential reuse models, users are provided with either a reusable product with preparation for reuse infrastructure and provider-operated recovery services (model 4), or a reusable product and provider-operated services for recovery and preparation for reuse (model 5). Whilst the five reuse models can operate standalone, some offerings were found to embed a multi-model approach. Both exclusive and sequential reuse models are capable of delivering environmental value by reducing the use of natural resources and retaining their value in the economy. In particular, sequential reuse models were found to have a greater capability to increase the share of recyclable resources by offering access to infrastructure for the closure of material loops. Conclusions: Consumers can currently access five reuse models and choose between exclusive and sequential reuse behaviours. When adopted in conjunction with recycling, reuse models can enable a more efficient consumption of FMCGs. Providing the infrastructure necessary to enable reuse and recycling is key to the successful and sustainable deployment of the reuse models.

show abstract

Constructing an automatic object-recognition algorithm using labeling information for efficient recycling of WEEE

Cited by 20 publications

References 7 publications

A comparative study of national variations of the European WEEE directive: manufacturer’s view

A comparative study of national variations of the European WEEE directive: manufacturer’s view

Obstacle Avoidance and Environmental Adaptability Analysis of Snake-like Robot Based on Deep Learning

Characterisation and Environmental Value Proposition of Reuse Models for Fast-Moving Consumer Goods: Reusable Packaging and Products

Contact Info

Product

Resources

About