tag:blogger.com,1999:blog-8847437553932078484.post3945145314755226690..comments2011-03-14T09:12:28.347-07:00Comments on Research of Severin Stalder: Cascaded Confidence Filtering for Improved Tracking-by-DetectionSeverin Stalderhttp://www.blogger.com/profile/14633972437196449653noreply@blogger.comBlogger4125tag:blogger.com,1999:blog-8847437553932078484.post-87850092542727434882011-03-14T09:12:28.347-07:002011-03-14T09:12:28.347-07:00Hi Qingsong,
Thanks for your interest in our work....Hi Qingsong,<br />Thanks for your interest in our work.<br />The presentation can be found here:<br />http://www.vision.ee.ethz.ch/%7Esstalder/presentations/ccfSlideShow.pdf<br /><br />We are currently working on publishing the source code of our implementation. It should be ready by mid-April. I will let you know. Best regards, Severin.Severin Stalderhttps://www.blogger.com/profile/14633972437196449653noreply@blogger.comtag:blogger.com,1999:blog-8847437553932078484.post-28415317810147046172011-03-03T23:32:37.088-08:002011-03-03T23:32:37.088-08:00Hi, Severin, your tracking by detection work is ve...Hi, Severin, your tracking by detection work is very impressive, and I think the performance of the detection parts could be improved by GPU acceleration to achieve real-time performance with some ROI restriction, actually the CUDA based HOG detection is implemented in opencv 2.2, you can try it. <br />In addition, would you like to share a copy of your presentation and code with me if it's convenient. My email is: qqsongzi@gmail.com<br />BRs, <br />QingsongAnonymoushttps://www.blogger.com/profile/11332591354970832243noreply@blogger.comtag:blogger.com,1999:blog-8847437553932078484.post-64441898090588687992010-12-13T00:13:29.276-08:002010-12-13T00:13:29.276-08:00Thanks for your interest in our work.
You are rig...Thanks for your interest in our work. <br />You are right, every pixel of this map corresponds to the raw output of the HoG SVM detector. The scale of the persons is assumed to be known in advance. More precisely, we estimate the ground plane on which persons walk. With the assumption of a flat ground plane, it is easily possible to infer the height of persons at each location in the image.<br /><br />If you have further questions, please do not hesitate to contact me again.Severin Stalderhttps://www.blogger.com/profile/14633972437196449653noreply@blogger.comtag:blogger.com,1999:blog-8847437553932078484.post-89242151939167747762010-12-03T02:53:17.246-08:002010-12-03T02:53:17.246-08:00I've read your papper and found it very intere...I've read your papper and found it very interesting. I've one question about your object detection confidence map. How do you compute it ? Is every pixel of this map corresponds to the raw output of the hog svm detector ? And how do you integrate the scale in this map ?<br /><br />Regards,<br /><br />JaonaryJaonarynoreply@blogger.com