{"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-object-detection-in-compressed-jpeg","title":"Fast object detection in compressed JPEG Images","arxiv_id":"1904.08408","date":"2019-04-16","proceeding":null,"authors":["Benjamin Deguerre","Clément Chatelain","Gilles Gasso"],"abstract":"Object detection in still images has drawn a lot of attention over past few\nyears, and with the advent of Deep Learning impressive performances have been\nachieved with numerous industrial applications. Most of these deep learning\nmodels rely on RGB images to localize and identify objects in the image.\nHowever in some application scenarii, images are compressed either for storage\nsavings or fast transmission. Therefore a time consuming image decompression\nstep is compulsory in order to apply the aforementioned deep models. To\nalleviate this drawback, we propose a fast deep architecture for object\ndetection in JPEG images, one of the most widespread compression format. We\ntrain a neural network to detect objects based on the blockwise DCT (discrete\ncosine transform) coefficients {issued from} the JPEG compression algorithm. We\nmodify the well-known Single Shot multibox Detector (SSD) by replacing its\nfirst layers with one convolutional layer dedicated to process the DCT inputs.\nExperimental evaluations on PASCAL VOC and industrial dataset comprising images\nof road traffic surveillance show that the model is about $2\\times$ faster than\nregular SSD with promising detection performances. To the best of our\nknowledge, this paper is the first to address detection in compressed JPEG\nimages.","url_abs":"http://arxiv.org/abs/1904.08408v1","url_pdf":"http://arxiv.org/pdf/1904.08408v1.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-object-detection-in-compressed-jpeg","repo_url":"https://github.com/Shulk97/JPEG_detection_INSA_ROUEN_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"fast-object-detection-in-compressed-jpeg","repo_url":"https://github.com/Shulk97/JPEG_detection_Resnet_SSD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"ssd","method_name":"SSD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.08408","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}