File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.jenvman.2021.112233
- Scopus: eid_2-s2.0-85101970009
- PMID: 33684803
- WOS: WOS:000634969400003
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: “Looking beneath the surface”: A visual-physical feature hybrid approach for unattended gauging of construction waste composition
Title | “Looking beneath the surface”: A visual-physical feature hybrid approach for unattended gauging of construction waste composition |
---|---|
Authors | |
Keywords | Construction and demolition waste Construction waste management Waste composition Computer vision Deep convolutional neural network |
Issue Date | 2021 |
Publisher | Academic Press. The Journal's web site is located at http://www.elsevier.com/locate/jenvman |
Citation | Journal of Environmental Management, 2021, v. 286, article no. 112233 How to Cite? |
Abstract | There are various scenarios challenging human experts to judge the interior of something based on limited surface information. Likewise, at waste disposal facilities around the world, human inspectors are often challenged to gauge the composition of waste bulks to determine admissibility and chargeable levy. Manual approaches are laborious, hazardous, and prone to carelessness and fatigue, making unattended gauging of construction waste composition using simple surface information highly desired. This research attempts to contribute to automated waste composition gauging by harnessing a valuable dataset from Hong Kong. Firstly, visual features, called visual inert probability (VIP), characterizing inert and non-inert materials are extracted from 1127 photos of waste bulks using a fine-tuned convolutional neural network (CNN). Then, these visual features together with easy-to-obtain physical features (e.g., weight and depth) are fed to a tailor-made support vector machine (SVM) model to determine waste composition as measured by the proportions of inert and non-inert materials. The visual-physical feature hybrid model achieved a waste composition gauging accuracy of 94% in the experiments. This high performance implies that the model, with proper adaption and integration, could replace human inspectors to smooth the operation of the waste disposal facilities. |
Persistent Identifier | http://hdl.handle.net/10722/297689 |
ISSN | 2023 Impact Factor: 8.0 2023 SCImago Journal Rankings: 1.771 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, J | - |
dc.contributor.author | Lu, W | - |
dc.contributor.author | Xue, F | - |
dc.date.accessioned | 2021-03-23T04:20:18Z | - |
dc.date.available | 2021-03-23T04:20:18Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Journal of Environmental Management, 2021, v. 286, article no. 112233 | - |
dc.identifier.issn | 0301-4797 | - |
dc.identifier.uri | http://hdl.handle.net/10722/297689 | - |
dc.description.abstract | There are various scenarios challenging human experts to judge the interior of something based on limited surface information. Likewise, at waste disposal facilities around the world, human inspectors are often challenged to gauge the composition of waste bulks to determine admissibility and chargeable levy. Manual approaches are laborious, hazardous, and prone to carelessness and fatigue, making unattended gauging of construction waste composition using simple surface information highly desired. This research attempts to contribute to automated waste composition gauging by harnessing a valuable dataset from Hong Kong. Firstly, visual features, called visual inert probability (VIP), characterizing inert and non-inert materials are extracted from 1127 photos of waste bulks using a fine-tuned convolutional neural network (CNN). Then, these visual features together with easy-to-obtain physical features (e.g., weight and depth) are fed to a tailor-made support vector machine (SVM) model to determine waste composition as measured by the proportions of inert and non-inert materials. The visual-physical feature hybrid model achieved a waste composition gauging accuracy of 94% in the experiments. This high performance implies that the model, with proper adaption and integration, could replace human inspectors to smooth the operation of the waste disposal facilities. | - |
dc.language | eng | - |
dc.publisher | Academic Press. The Journal's web site is located at http://www.elsevier.com/locate/jenvman | - |
dc.relation.ispartof | Journal of Environmental Management | - |
dc.subject | Construction and demolition waste | - |
dc.subject | Construction waste management | - |
dc.subject | Waste composition | - |
dc.subject | Computer vision | - |
dc.subject | Deep convolutional neural network | - |
dc.title | “Looking beneath the surface”: A visual-physical feature hybrid approach for unattended gauging of construction waste composition | - |
dc.type | Article | - |
dc.identifier.email | Chen, J: chenjj10@hku.hk | - |
dc.identifier.email | Lu, W: wilsonlu@hku.hk | - |
dc.identifier.email | Xue, F: xuef@hku.hk | - |
dc.identifier.authority | Lu, W=rp01362 | - |
dc.identifier.authority | Xue, F=rp02189 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.jenvman.2021.112233 | - |
dc.identifier.pmid | 33684803 | - |
dc.identifier.scopus | eid_2-s2.0-85101970009 | - |
dc.identifier.hkuros | 321752 | - |
dc.identifier.volume | 286 | - |
dc.identifier.spage | article no. 112233 | - |
dc.identifier.epage | article no. 112233 | - |
dc.identifier.isi | WOS:000634969400003 | - |
dc.publisher.place | United Kingdom | - |