{"id":{"repo_id":"sdstate","oai_identifier":"oai:openprairie.sdstate.edu:etd-5140"},"canonical_url":"https://search.ndltd.org/etd/sdstate/oai:openprairie.sdstate.edu:etd-5140","repository":{"repo_id":"sdstate","name":"South Dakota State University","base_url":"https://openprairie.sdstate.edu/do/oai/"},"display":{"title":"Past to Present (P2P): Road Thermal Image Colorization","abstract":"Thermal image colorization into realistic RGB image is a challenging task. Thermal cameras are easily to detect objects in particular situation (e.g. darkness and fog) that the human eyes cannot detect. However, it is difficult to interpret the thermal image with human eyes. Enhancing thermal image colorization is an important task to improve these areas. The results of the existing colorization method still have color ambiguities, distortion, and blurriness problems. This paper focused on thermal image colorization using pix2pix network architecture based on Generative Adversarial Net (GAN). Pix2pix is a model that transforms thermal image into RGB image, but our proposed model used three input types of images which are present as frame thermal image, present frame RGB image, and previous frame RGB image. By extracting the color information (i.e. luminance and chrominance) of the previous frame RGB image, the result obtained a more realistic RGB image. Experiments use two kinds of evaluation method, which are quantitative measure and qualitative measure. First, quantitative measure is the calculation of specific numerical scores, the method names are PSNR and SSIM. Second, qualitative measure is human subjective evaluation. Evaluation method compared and evaluated pix2pix and our proposed method with the two types of measuring method.","abstract_html":"Thermal image colorization into realistic RGB image is a challenging task. Thermal cameras are easily to detect objects in particular situation (e.g. darkness and fog) that the human eyes cannot detect. However, it is difficult to interpret the thermal image with human eyes. Enhancing thermal image colorization is an important task to improve these areas. The results of the existing colorization method still have color ambiguities, distortion, and blurriness problems. This paper focused on thermal image colorization using pix2pix network architecture based on Generative Adversarial Net (GAN). Pix2pix is a model that transforms thermal image into RGB image, but our proposed model used three input types of images which are present as frame thermal image, present frame RGB image, and previous frame RGB image. By extracting the color information (i.e. luminance and chrominance) of the previous frame RGB image, the result obtained a more realistic RGB image. Experiments use two kinds of evaluation method, which are quantitative measure and qualitative measure. First, quantitative measure is the calculation of specific numerical scores, the method names are PSNR and SSIM. Second, qualitative measure is human subjective evaluation. Evaluation method compared and evaluated pix2pix and our proposed method with the two types of measuring method.","abstract_has_math":false,"creators":["Park, Yuseong"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis - Open Access","degree_discipline":"Electrical Engineering and Computer Science","degree_department":null,"school":null,"contributors":["Sung Shin"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:00:51Z","subjects":["Colorization","Computer vision","Generative Adversarial Nets","Computer Engineering","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://openprairie.sdstate.edu/etd/4074","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://openprairie.sdstate.edu/etd/4074","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://openprairie.sdstate.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopenprairie.sdstate.edu%3Aetd-5140","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sung Shin"]},{"key":"dc:creator","label":"Author","values":["Park, Yuseong"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2020-08-20T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2020-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering and Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Colorization","Computer vision","Generative Adversarial Nets","Computer Engineering","Electrical and Computer Engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://openprairie.sdstate.edu/etd/4074"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Thermal image colorization into realistic RGB image is a challenging task. Thermal cameras are easily to detect objects in particular situation (e.g. darkness and fog) that the human eyes cannot detect. However, it is difficult to interpret the thermal image with human eyes. Enhancing thermal image colorization is an important task to improve these areas. The results of the existing colorization method still have color ambiguities, distortion, and blurriness problems. This paper focused on thermal image colorization using pix2pix network architecture based on Generative Adversarial Net (GAN). Pix2pix is a model that transforms thermal image into RGB image, but our proposed model used three input types of images which are present as frame thermal image, present frame RGB image, and previous frame RGB image. By extracting the color information (i.e. luminance and chrominance) of the previous frame RGB image, the result obtained a more realistic RGB image. Experiments use two kinds of evaluation method, which are quantitative measure and qualitative measure. First, quantitative measure is the calculation of specific numerical scores, the method names are PSNR and SSIM. Second, qualitative measure is human subjective evaluation. Evaluation method compared and evaluated pix2pix and our proposed method with the two types of measuring method."]},{"key":"dc:title","label":"Title","values":["Past to Present (P2P): Road Thermal Image Colorization"]}]}],"canonical_facts":{"dc:contributor":["Sung Shin"],"dc:creator":["Park, Yuseong"],"dc:date.available":["2020-08-20T07:00:00Z"],"dc:date.created":["2020-01-01T08:00:00Z"],"dc:description.abstract":["Thermal image colorization into realistic RGB image is a challenging task. Thermal cameras are easily to detect objects in particular situation (e.g. darkness and fog) that the human eyes cannot detect. However, it is difficult to interpret the thermal image with human eyes. Enhancing thermal image colorization is an important task to improve these areas. The results of the existing colorization method still have color ambiguities, distortion, and blurriness problems. This paper focused on thermal image colorization using pix2pix network architecture based on Generative Adversarial Net (GAN). Pix2pix is a model that transforms thermal image into RGB image, but our proposed model used three input types of images which are present as frame thermal image, present frame RGB image, and previous frame RGB image. By extracting the color information (i.e. luminance and chrominance) of the previous frame RGB image, the result obtained a more realistic RGB image. Experiments use two kinds of evaluation method, which are quantitative measure and qualitative measure. First, quantitative measure is the calculation of specific numerical scores, the method names are PSNR and SSIM. Second, qualitative measure is human subjective evaluation. Evaluation method compared and evaluated pix2pix and our proposed method with the two types of measuring method."],"dc:identifier":["https://openprairie.sdstate.edu/etd/4074"],"dc:rights":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Colorization","Computer vision","Generative Adversarial Nets","Computer Engineering","Electrical and Computer Engineering"],"dc:title":["Past to Present (P2P): Road Thermal Image Colorization"],"thesis:degree_discipline":["Electrical Engineering and Computer Science"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T09:00:51Z"}