[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-649642-105":59,"doc-detail-649642-en":129},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":122,"head_meta":124,"extra_data":126,"updated_unix":128},105,"en","ifpnet-integrated-feature-pyramid-network-with-fusion-factor-lane-detection-paper","IFPNet - Integrated Feature Pyramid Network with Fusion Factor - Lane detection paper","","Lane detection is a basic yet demanding task for autonomous driving, where complex and diverse road scenes challenge existing models. The paper proposes IFPNet, an Integrated Feature Pyramid Network with Fusion Factor, designed to learn and balance fine-scale features alongside global semantics. It introduces a new Integrated Feature Pyramid structure for hierarchical integration, and uses a Classification Fusion Factor to balance information across levels. A regression IoU loss improves curve regression quality. Experiments on three benchmark datasets achieve state-of-the-art accuracy and efficiency.",{"@graph":69,"@context":121},[70,84,104],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/ifpnet-integrated-feature-pyramid-network-with-fusion-factor-lane-detection-paper/649642/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":98,"encodingFormat":97,"isAccessibleForFree":99,"interactionStatistic":100},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/ifpnet-integrated-feature-pyramid-network-with-fusion-factor-lane-detection-paper/649642.png","ImageObject",300,407,{"name":92,"@type":93},"kopisore","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-24",true,{"@type":101,"interactionType":102,"userInteractionCount":8},"InteractionCounter",{"@type":103},"ViewAction",{"@type":105,"mainEntity":106},"FAQPage",[107,113,117],{"name":108,"@type":109,"acceptedAnswer":110},"What problem does IFPNet target in lane detection?","Question",{"text":111,"@type":112},"It targets improved lane detection accuracy under complex and diverse road conditions by better learning and balancing fine-scale features and global semantics.","Answer",{"name":114,"@type":109,"acceptedAnswer":115},"What is the Integrated Feature Pyramid (IFP) in IFPNet?",{"text":116,"@type":112},"IFP is a new FPN-style structure proposed to improve hierarchical information learning and integration for lane detection.",{"name":118,"@type":109,"acceptedAnswer":119},"How does IFPNet improve curve regression accuracy?",{"text":120,"@type":112},"It designs a regression IoU (RIoU) loss that measures overlap between predicted and ground-truth lane lines more effectively.","https://schema.org",{"og:url":83,"og:type":123,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":125,"canonical":83},"index,follow",{"doc_id":127,"site_id":62},649642,1792833495,{"code":4,"msg":5,"data":130},{"doc_id":127,"user_id":131,"nickname":92,"user_avatar":132,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":133,"file_id":134,"file_url":135,"file_type":136,"file_size":137,"view_count":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":138,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":139,"faqs":140,"seo_title":141,"seo_description":67,"update_tm":142,"read_time":143},962090880963,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","This ICCV workshop paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.  \nIFPNet: Integrated Feature Pyramid Network with Fusion Factor for Lane  \nDetection  \nZinan Lv 1 Dong Han 1 Wenzhe Wang2 ,3 Cheng Chen 1  \n1Harbin Engineering University 2Zhejiang University 3Westlake University  \nAbstract  \nLane detection is a basic but challenging task in autonomous driving systems. With a combination of highlevel and low-level information, early studies of lane detection have achieved promising results in some scenes. However, achieving better performance is still an urgent need for complex and diverse road conditions. We assume that learning and balancing the finer-scale features and global semantics is one of the keys to improving lane detection performance under these road conditions. In this paper, we propose an integrated feature pyramid network with fusion factor (IFPNet) for better hierarchical information learning and balancing, where a novel FPN structure named Integrated Feature Pyramid (IFP) is proposed for better hierarchical information integration. Classification Fusion Factor (CFF) is also utilized for the balance of hierarchical information. Moreover, we design the regression IoU (RIoU) loss for curve regression, which measures the overlap of the predicted and ground truth lane lines more effectively. We conduct experiments on three benchmark datasets of lane detection and achieve state-of-the-art results with high accuracy and efficiency.  \n1. Introduction  \nLane detection is a fundamental but challenging task in autonomous driving systems, which can help vehicles get their relative location and respond to emergencies in realtime. Traditional autonomous driving techniques rely on multi-sensor fusion, which requires expensive inertial guidance components and LIDAR [29] . But with the help of lane detection, vehicles can automatically detect lane lines from images captured only by front-mounted cameras.  \nEarly studies of lane detection focus on the utilization of manually extracted features based on priors such as color and structure [12, 13, 33] . After pre-processing the possible lane lines obtained from the extracted features, methods like Hough transform [18] and Kalman filter [40] are used to fil-  \nFigure 1 . Examples of complex and diverse road conditions in the lane detection task. (a) The case where the curve at the end of the field of view can be easily ignored and mistaken as a straightaway by detection methods. (b) Crowded scenes during peak periods where most of the lane lines are hidden. (c) The shadows of trees make light spots on the ground look like lane lines. (d) The case where there is no obvious white or yellow line on the ground. (a) and (b) indicate complex road conditions in the lane detection task whereas (c) and (d) indicate diverse road conditions in the task.  \nter out unreal or densely predicted lines to output the final lane lines. These methods commonly get limited results in various road environments. Recently, with the development of CNN, segmentation-based methods [24, 41, 43] are proposed for lane detection. However, treating lane detection as a common segmentation task ignores lane lines’ narrow, continuous, and structured characteristics. To alleviate this issue, anchor-based [14, 28, 31] and curve-based [4, 20, 35] methods with faster speed are proposed to achieve better detection results.  \nAlthough better results have been obtained, further improving the accuracy of lane detection is still a vital task. As shown in Fig. 1, recently proposed lane detection methods may still suffer from unsatisfactory results in some complex and diverse road conditions. In Fig. 1(a), a curve isin front of the vehicle and at the end of the field of view. It can be easily ignored and mistaken as a straightaway by lane detection methods, leadin","cbCaidhCj8TZY3yy","https://ap.wps.com/l/cbCaidhCj8TZY3yy","pdf",1519183,"English","# Introduction\n## Lane detection in autonomous driving\n## Limitations of existing methods\n## Motivation for fine-scale features and global semantics\n## Proposed approach and contributions","[{\"question\":\"What problem does IFPNet target in lane detection?\",\"answer\":\"It targets improved lane detection accuracy under complex and diverse road conditions by better learning and balancing fine-scale features and global semantics.\"},{\"question\":\"What is the Integrated Feature Pyramid (IFP) in IFPNet?\",\"answer\":\"IFP is a new FPN-style structure proposed to improve hierarchical information learning and integration for lane detection.\"},{\"question\":\"How does IFPNet improve curve regression accuracy?\",\"answer\":\"It designs a regression IoU (RIoU) loss that measures overlap between predicted and ground-truth lane lines more effectively.\"}]","IFPNet - Integrated Feature Pyramid Network with Fusion Factor - Lane detection paper | PDF",1792803149,25]