{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-thermal-imaging-proximate-material-type","title":"Deep Thermal Imaging: Proximate Material Type Recognition in the Wild through Deep Learning of Spatial Surface Temperature Patterns","arxiv_id":"1803.02310","date":"2018-03-06","proceeding":null,"authors":["Youngjun Cho","Nadia Bianchi-Berthouze","Nicolai Marquardt","Simon J. Julier"],"abstract":"We introduce Deep Thermal Imaging, a new approach for close-range automatic\nrecognition of materials to enhance the understanding of people and ubiquitous\ntechnologies of their proximal environment. Our approach uses a low-cost mobile\nthermal camera integrated into a smartphone to capture thermal textures. A deep\nneural network classifies these textures into material types. This approach\nworks effectively without the need for ambient light sources or direct contact\nwith materials. Furthermore, the use of a deep learning network removes the\nneed to handcraft the set of features for different materials. We evaluated the\nperformance of the system by training it to recognise 32 material types in both\nindoor and outdoor environments. Our approach produced recognition accuracies\nabove 98% in 14,860 images of 15 indoor materials and above 89% in 26,584\nimages of 17 outdoor materials. We conclude by discussing its potentials for\nreal-time use in HCI applications and future directions.","url_abs":"http://arxiv.org/abs/1803.02310v1","url_pdf":"http://arxiv.org/pdf/1803.02310v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-thermal-imaging-proximate-material-type","repo_url":"https://github.com/deepneuroscience/DeepThermalImaging","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"material-classification","task_name":"Material Classification"},{"task_slug":"material-recognition","task_name":"Material Recognition"},{"task_slug":"thermal-infrared-object-tracking","task_name":"Thermal Infrared Object Tracking"}],"methods":[],"datasets_introduced":[{"slug":"deep-thermal-imaging-dataset","name":"Deep Thermal Imaging Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.02310","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}