{"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/fast-robust-monocular-depth-estimation-for","title":"Fast Robust Monocular Depth Estimation for Obstacle Detection with Fully Convolutional Networks","arxiv_id":"1607.06349","date":"2016-07-21","proceeding":null,"authors":["Michele Mancini","Gabriele Costante","Paolo Valigi","Thomas A. Ciarfuglia"],"abstract":"Obstacle Detection is a central problem for any robotic system, and critical\nfor autonomous systems that travel at high speeds in unpredictable environment.\nThis is often achieved through scene depth estimation, by various means. When\nfast motion is considered, the detection range must be longer enough to allow\nfor safe avoidance and path planning. Current solutions often make assumption\non the motion of the vehicle that limit their applicability, or work at very\nlimited ranges due to intrinsic constraints. We propose a novel\nappearance-based Object Detection system that is able to detect obstacles at\nvery long range and at a very high speed (~300Hz), without making assumptions\non the type of motion. We achieve these results using a Deep Neural Network\napproach trained on real and synthetic images and trading some depth accuracy\nfor fast, robust and consistent operation. We show how photo-realistic\nsynthetic images are able to solve the problem of training set dimension and\nvariety typical of machine learning approaches, and how our system is robust to\nmassive blurring of test images.","url_abs":"http://arxiv.org/abs/1607.06349v1","url_pdf":"http://arxiv.org/pdf/1607.06349v1.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":"fast-robust-monocular-depth-estimation-for","repo_url":"https://github.com/EbadSyed/spadRGBD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"fast-robust-monocular-depth-estimation-for","repo_url":"https://github.com/LeonSun0101/CD-SD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"fast-robust-monocular-depth-estimation-for","repo_url":"https://github.com/fangchangma/sparse-to-dense.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-robust-monocular-depth-estimation-for","repo_url":"https://github.com/katieluo88/280finalproj_nyudepth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1607.06349","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}