- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I'm wondering if I can get the landmarks of an external image from a dataset using the SDK Intel algorithms. Or if I can convert this one to an 'Intel Image'.
Thanks in advance
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi MQMQ,
I'm not sure if this is possible, there's an internal RealSense SDK format, which is .rssdk, and this is the file type the SDK expects. I haven't heard of anyone trying to convert a different file format into RealSense SDK format and I haven't try it myself, however, I'm not aware of any tool able to do this.
Regards,
Pablo M.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi MQMQ, there was a discussion last month about the .RSSDK format, which Pablo also commented on.
There was also this one about the data encoded in the .RSSDK file format.
If .RSSDK is an H.264 format video, then you could try converting a non-RealSense video to the H.264 format and see if it can be read by the SDK as an .RSSDK file. I have no idea if it would work, but it seems like the course of action most likely to succeed.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thanks both for the answers, but they didn't solved my problem...
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Could you explain more please about what you are aiming to do? Thanks!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I want to upload an image (RGB) from a dataset and get the landmarks with the Intel's SDK in the same way that I get the landmarks from an Intel picture
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
When you say 'image', do you mean a static picture or a moving video?
RealSense has a mode where you can load in a pre-recorded stream as an .RSSDK file instead of using live input. The purpose of this mode was to allow testing of applications without having to use a camera.
https://software.intel.com/en-us/blogs/2015/10/15/how-to-record-and-playback-streaming-sequences-in-intel-realsense-sdk RealSense - How to Record and Playback Streaming Sequences in Intel® RealSense™ SDK | Intel® Software
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I mean a static picture, a photo in RGB format, not a video.
PD: Thanks for the post it's really helpful and interesting for making myself a database in the future!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I tried rephrasing the keywords of what you were trying to do to 'realsense get landmarks from a 2d picture'. This led me to this link, where Intel staffer David Lu suggests using an API called PXCVideoModule in response to another person who wanted to get the landmarks from a picture.
https://software.intel.com/en-us/node/623478 Capture 2D Landmarks of picture
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I was not be able to follow the steps. I think they are use some deprecated functions (like PXCVideoModule)
I tried to compile this code but I can't. In line 12, can't made the convertion Mat to uchar... and ALIGN64 is not defined.
//First define an ImageInfo object
PXCImage::ImageInfo info={};
info.format=PXCImage::PIXEL_FORMAT_RGB32; //Change this to match your data
//You can get these easily from an OpenCV Mat
info.width=image_width;
info.height=image_height;
//And now define the actual Image data
PXCImage::ImageData data={};
data.format=PXCImage::PIXEL_FORMAT_RGB32;//This should match the info object I reckon
data.planes[0]=image_buffer; //This is the critical bit. This is the actual data, the uchar array from cv::Mat
data.pitches[0]=ALIGN64(info.width*4); //This is because RGB32 is used (8bits * 4), change accordingly
// Finally Create the image instance
PXCImage *image=session->CreateImage(&info,0,&data);
//Now you have image ready to roll.
Anyone knows how to solve this?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Sadly, advanced stream programming is outside of my field of knowledge. Updates to this discussion do not appear on the front page of the forum because the discussion is old. If you want help with this particular question, I think the best way for people who can help to see it will be to post it and the above script code as a new question to the forum so it goes to the top of the list.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page