{"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/birdnet-a-3d-object-detection-framework-from","title":"BirdNet: a 3D Object Detection Framework from LiDAR information","arxiv_id":"1805.01195","date":"2018-05-03","proceeding":null,"authors":["Jorge Beltran","Carlos Guindel","Francisco Miguel Moreno","Daniel Cruzado","Fernando Garcia","Arturo de la Escalera"],"abstract":"Understanding driving situations regardless the conditions of the traffic\nscene is a cornerstone on the path towards autonomous vehicles; however,\ndespite common sensor setups already include complementary devices such as\nLiDAR or radar, most of the research on perception systems has traditionally\nfocused on computer vision. We present a LiDAR-based 3D object detection\npipeline entailing three stages. First, laser information is projected into a\nnovel cell encoding for bird's eye view projection. Later, both object location\non the plane and its heading are estimated through a convolutional neural\nnetwork originally designed for image processing. Finally, 3D oriented\ndetections are computed in a post-processing phase. Experiments on KITTI\ndataset show that the proposed framework achieves state-of-the-art results\namong comparable methods. Further tests with different LiDAR sensors in real\nscenarios assess the multi-device capabilities of the approach.","url_abs":"http://arxiv.org/abs/1805.01195v1","url_pdf":"http://arxiv.org/pdf/1805.01195v1.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":"birdnet-a-3d-object-detection-framework-from","repo_url":"https://github.com/AlejandroBarrera/birdnet2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"birdnet-a-3d-object-detection-framework-from","repo_url":"https://github.com/beltransen/lidar_bev","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.01195","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}