{"id":19751,"date":"2025-01-27T11:47:38","date_gmt":"2025-01-27T10:47:38","guid":{"rendered":"https:\/\/fondation-grenoble-inp.fr\/?post_type=projet&#038;p=19751"},"modified":"2025-01-31T11:56:10","modified_gmt":"2025-01-31T10:56:10","slug":"detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route","status":"publish","type":"projet","link":"https:\/\/fondation-grenoble-inp.fr\/en\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/","title":{"rendered":"Thesis: Multispectral detection (RGB-IR) for driving assistance and protection of vulnerable road users"},"content":{"rendered":"<p><strong>Project leaders :<\/strong> Lo\u00efc ARBEZ, Jocelyn CHANUSSOT, Ronald PHLYPO, Jessy MATIAS<\/p>\n\n\n\n<p><strong>Project research areas : <\/strong>Deep learning, Computer vision, Data fusion<\/p>\n\n\n\n<p><strong>Organisations associated with the project : <\/strong><br><a href=\"https:\/\/fondation-grenoble-inp.fr\/en\/nos-actions\/chaire-deep-red\/\" target=\"_blank\" rel=\"noreferrer noopener\">Deep Red Chair<\/a> (Supported by the<a href=\"https:\/\/fondation-grenoble-inp.fr\/en\/\" target=\"_blank\" rel=\"noreferrer noopener\"> Grenoble INP Foundation<\/a>)<br><a href=\"https:\/\/www.lynred.com\/fr\" target=\"_blank\" rel=\"noreferrer noopener\">Lynred<\/a><br><a href=\"https:\/\/www.gipsa-lab.grenoble-inp.fr\/\" target=\"_blank\" rel=\"noreferrer noopener\">Gipsa-lab<\/a><br><a href=\"https:\/\/www.inria.fr\/fr\/centre-inria-universite-grenoble-alpes\" target=\"_blank\" rel=\"noreferrer noopener\">INRIA Centre, Grenoble Alpes University<\/a><\/p>\n\n\n\n<p><strong>The project:<\/strong><\/p>\n\n\n\n<p>The importance of infrared and multispectral image processing lies in its ability to reveal a wealth of information beyond the visible spectrum, enhancing our understanding of the world and enabling advanced applications in a variety of fields. A notable feature of infrared sensors is their ability to capture the thermal radiation emitted by any material above 0 K (-273.15\u00b0C), compared with standard data from the visible light spectrum, which depends on the reflective properties of the object or scene being observed. This allows an infrared sensor to perform better in adverse lighting conditions such as low light, foggy weather or exposure to direct light. This quality makes it a valuable complement to visible light information in a variety of applications, including security, autonomous driving, remote sensing and medicine [1]. <\/p>\n\n\n\n<p>Analysing these images using artificial intelligence and deep learning techniques unlocks the potential for more accurate, efficient and adaptive systems in areas such as autonomous vehicles, healthcare and environmental conservation. Although multimodal RGB-IR images have traditionally been used for pedestrian detection, particularly with datasets such as FLIR ADAS [2] or KAIST [3], their use was initially limited due to the high cost of infrared sensors [1]. However, \u2018recent advances in sensor technology have made them increasingly accessible and widespread\u2019, as Wilson et al [1] suggest. Object detection, on the other hand, has always been a major challenge in computer vision and has become increasingly important with the widespread adoption of neural network architectures. Initially focused on object identification in classical RGB environments, object detection has also proved useful for multispectral or infrared systems, with slight adaptations of the models developed for RGB images [4][5][6]. However, due to the lack of a good basis for comparison, consisting of a single public dataset for the detection and classification of multi-class objects, the FLIR ADAS. The subject does not seem to have aroused much interest in the community. <\/p>\n\n\n\n<p><strong>Project objectives :<\/strong><\/p>\n\n\n\n<p>The aim of this thesis is to focus on the development of methods for processing and analysing infrared and multispectral sequences. The focus will be on the detection of sensitive road users such as pedestrians, cyclists, motorbikes and scooters in the context of a power-assisted vehicle. This work will be based on an in-house dataset similar to version 2.0 of the FLIR ADAS dataset supplied by the French infrared sensor company <a href=\"https:\/\/www.lynred.com\/fr\" target=\"_blank\" rel=\"noreferrer noopener\">LYNRED<\/a>. The temporal aspect of the image sequences studied could be taken into account, as well as the strategy for mixing the visible and infrared components of the image, as demonstrated by Bao et al [6]. Furthermore, as in any image classification task, the size of the dataset used is closely linked to the performance of the model created. Exploring methods for generating infrared or multispectral data, whether by augmenting multispectral data or generating infrared data from RGB images, is also an essential aspect of this research. [1] <\/p>\n\n\n\n<p><strong>Publications associated with the project :<\/strong><\/p>\n\n\n\n<p>Wilson, A., et al. &lsquo;Recent advances in thermal imaging and its applications using machine learning: A review,&rsquo; in IEEE Sensors Journal, 2023. [2] \u201c<a href=\"https:\/\/www.flir.in\/oem\/adas\/adas-dataset-form\/\" target=\"_blank\" rel=\"noreferrer noopener\">Free teledyne FLIR thermal dataset for algorithm training<\/a>\u00ab\u00a0. Accessed: 2023-12-13. [3] S. Hwang, J. Park, N. Kim, Y. Choi, and I. S. Kweon, \u201cMultispectral pedestrian detection: Benchmark dataset and baselines,\u201d inProceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [4] K. Takumi, K. Watanabe, Q. Ha, A. Tejero-De-Pablos, Y. Ushiku, and T. Harada, \u201cMultispectral object detection for autonomous vehicles,\u201d in Proceedings of the on Thematic Workshops of ACM Multimedia 2017,pp. 35\u201343, 2017. [5] S. Li, Y. Li, Y. Li, M. Li, and X. Xu, \u201cYolo-firi: Improved yolov5 for infrared image object detection,\u201dIEEEaccess, vol. 9, pp. 141861\u2013141875, 2021. [6] C. Bao, J. Cao, Q. Hao, Y. Cheng, Y. Ning, and T. Zhao, \u201cDual-yolo architecture from infrared and visible images for object detection,\u201dSensors, vol. 23, no. 6, p. 2934, 2023.<\/p>\n\n\n\n<p><br><strong>Planification : <\/strong>from 01\/12\/2024 to 01\/12\/2026<\/p>\n\n\n\n<p><\/p>","protected":false},"excerpt":{"rendered":"<p>L&rsquo;importance du traitement des images infrarouges et multispectrales r\u00e9side dans sa capacit\u00e9 \u00e0 r\u00e9v\u00e9ler une multitude d&rsquo;informations au-del\u00e0 du spectre visible, am\u00e9liorant ainsi notre compr\u00e9hension du monde et permettant des applications avanc\u00e9es dans divers domaines<\/p>","protected":false},"featured_media":19752,"template":"","acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v18.0 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Th\u00e8se : D\u00e9tection multispectrale (RGB-IR) pour l\u2019aide \u00e0 la conduite et la protection des usagers vuln\u00e9rables de la route - Fondation Grenoble INP<\/title>\n<meta name=\"description\" content=\"L&#039;importance du traitement des images infrarouges et multispectrales r\u00e9side dans sa capacit\u00e9 \u00e0 r\u00e9v\u00e9ler une multitude d&#039;informations au-del\u00e0 du spectre visible.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/fondation-grenoble-inp.fr\/en\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Th\u00e8se : D\u00e9tection multispectrale (RGB-IR) pour l\u2019aide \u00e0 la conduite et la protection des usagers vuln\u00e9rables de la route - Fondation Grenoble INP\" \/>\n<meta property=\"og:description\" content=\"L&#039;importance du traitement des images infrarouges et multispectrales r\u00e9side dans sa capacit\u00e9 \u00e0 r\u00e9v\u00e9ler une multitude d&#039;informations au-del\u00e0 du spectre visible.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/fondation-grenoble-inp.fr\/en\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/\" \/>\n<meta property=\"og:site_name\" content=\"Fondation Grenoble INP\" \/>\n<meta property=\"article:modified_time\" content=\"2025-01-31T10:56:10+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2025\/01\/exampleIR.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1451\" \/>\n\t<meta property=\"og:image:height\" content=\"464\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/#organization\",\"name\":\"Fondation INP Grenoble\",\"url\":\"https:\/\/fondation-grenoble-inp.fr\/\",\"sameAs\":[],\"logo\":{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/#logo\",\"inLanguage\":\"en-US\",\"url\":\"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2021\/03\/cropped-favicon-fondation-inp-grenoble.png\",\"contentUrl\":\"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2021\/03\/cropped-favicon-fondation-inp-grenoble.png\",\"width\":512,\"height\":512,\"caption\":\"Fondation INP Grenoble\"},\"image\":{\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/#logo\"}},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/#website\",\"url\":\"https:\/\/fondation-grenoble-inp.fr\/\",\"name\":\"Fondation Grenoble INP\",\"description\":\"#OsezlAvenir\",\"publisher\":{\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/fondation-grenoble-inp.fr\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#primaryimage\",\"inLanguage\":\"en-US\",\"url\":\"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2025\/01\/exampleIR.jpg\",\"contentUrl\":\"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2025\/01\/exampleIR.jpg\",\"width\":\"1451\",\"height\":\"464\",\"caption\":\"D\u00e9tection multispectrale (RGB-IR)\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#webpage\",\"url\":\"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/\",\"name\":\"Th\u00e8se : D\u00e9tection multispectrale (RGB-IR) pour l\u2019aide \u00e0 la conduite et la protection des usagers vuln\u00e9rables de la route - Fondation Grenoble INP\",\"isPartOf\":{\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#primaryimage\"},\"datePublished\":\"2025-01-27T10:47:38+00:00\",\"dateModified\":\"2025-01-31T10:56:10+00:00\",\"description\":\"L'importance du traitement des images infrarouges et multispectrales r\u00e9side dans sa capacit\u00e9 \u00e0 r\u00e9v\u00e9ler une multitude d'informations au-del\u00e0 du spectre visible.\",\"breadcrumb\":{\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\/\/fondation-grenoble-inp.fr\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Th\u00e8se : D\u00e9tection multispectrale (RGB-IR) pour l\u2019aide \u00e0 la conduite et la protection des usagers vuln\u00e9rables de la route\"}]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Th\u00e8se : D\u00e9tection multispectrale (RGB-IR) pour l\u2019aide \u00e0 la conduite et la protection des usagers vuln\u00e9rables de la route - Fondation Grenoble INP","description":"L'importance du traitement des images infrarouges et multispectrales r\u00e9side dans sa capacit\u00e9 \u00e0 r\u00e9v\u00e9ler une multitude d'informations au-del\u00e0 du spectre visible.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/fondation-grenoble-inp.fr\/en\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/","og_locale":"en_US","og_type":"article","og_title":"Th\u00e8se : D\u00e9tection multispectrale (RGB-IR) pour l\u2019aide \u00e0 la conduite et la protection des usagers vuln\u00e9rables de la route - Fondation Grenoble INP","og_description":"L'importance du traitement des images infrarouges et multispectrales r\u00e9side dans sa capacit\u00e9 \u00e0 r\u00e9v\u00e9ler une multitude d'informations au-del\u00e0 du spectre visible.","og_url":"https:\/\/fondation-grenoble-inp.fr\/en\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/","og_site_name":"Fondation Grenoble INP","article_modified_time":"2025-01-31T10:56:10+00:00","og_image":[{"width":"1451","height":"464","url":"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2025\/01\/exampleIR.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Organization","@id":"https:\/\/fondation-grenoble-inp.fr\/#organization","name":"Fondation INP Grenoble","url":"https:\/\/fondation-grenoble-inp.fr\/","sameAs":[],"logo":{"@type":"ImageObject","@id":"https:\/\/fondation-grenoble-inp.fr\/#logo","inLanguage":"en-US","url":"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2021\/03\/cropped-favicon-fondation-inp-grenoble.png","contentUrl":"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2021\/03\/cropped-favicon-fondation-inp-grenoble.png","width":512,"height":512,"caption":"Fondation INP Grenoble"},"image":{"@id":"https:\/\/fondation-grenoble-inp.fr\/#logo"}},{"@type":"WebSite","@id":"https:\/\/fondation-grenoble-inp.fr\/#website","url":"https:\/\/fondation-grenoble-inp.fr\/","name":"Fondation Grenoble INP","description":"#OsezlAvenir","publisher":{"@id":"https:\/\/fondation-grenoble-inp.fr\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/fondation-grenoble-inp.fr\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"ImageObject","@id":"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#primaryimage","inLanguage":"en-US","url":"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2025\/01\/exampleIR.jpg","contentUrl":"https:\/\/fondation-grenoble-inp.fr\/wp-content\/uploads\/2025\/01\/exampleIR.jpg","width":"1451","height":"464","caption":"D\u00e9tection multispectrale (RGB-IR)"},{"@type":"WebPage","@id":"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#webpage","url":"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/","name":"Th\u00e8se : D\u00e9tection multispectrale (RGB-IR) pour l\u2019aide \u00e0 la conduite et la protection des usagers vuln\u00e9rables de la route - Fondation Grenoble INP","isPartOf":{"@id":"https:\/\/fondation-grenoble-inp.fr\/#website"},"primaryImageOfPage":{"@id":"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#primaryimage"},"datePublished":"2025-01-27T10:47:38+00:00","dateModified":"2025-01-31T10:56:10+00:00","description":"L'importance du traitement des images infrarouges et multispectrales r\u00e9side dans sa capacit\u00e9 \u00e0 r\u00e9v\u00e9ler une multitude d'informations au-del\u00e0 du spectre visible.","breadcrumb":{"@id":"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/fondation-grenoble-inp.fr\/projet\/detection-multispectrale-rgb-ir-pour-laide-a-la-conduite-et-la-protection-des-usagers-vulnerables-de-la-route\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/fondation-grenoble-inp.fr\/"},{"@type":"ListItem","position":2,"name":"Th\u00e8se : D\u00e9tection multispectrale (RGB-IR) pour l\u2019aide \u00e0 la conduite et la protection des usagers vuln\u00e9rables de la route"}]}]}},"_links":{"self":[{"href":"https:\/\/fondation-grenoble-inp.fr\/en\/wp-json\/wp\/v2\/projet\/19751"}],"collection":[{"href":"https:\/\/fondation-grenoble-inp.fr\/en\/wp-json\/wp\/v2\/projet"}],"about":[{"href":"https:\/\/fondation-grenoble-inp.fr\/en\/wp-json\/wp\/v2\/types\/projet"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/fondation-grenoble-inp.fr\/en\/wp-json\/wp\/v2\/media\/19752"}],"wp:attachment":[{"href":"https:\/\/fondation-grenoble-inp.fr\/en\/wp-json\/wp\/v2\/media?parent=19751"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}