<div dir="ltr">I don't remember the name, but the process could be constrained to only allow the type of transform that allows translation and scaling (no rotation, etc.).</div><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Mar 12, 2018 at 10:59 AM, Matt Brown <span dir="ltr"><<a href="mailto:matt.brown@kitware.com" target="_blank">matt.brown@kitware.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div><div>I have an application where I would like to significantly reduce the resolution of an image using pyramid reductions, run a detector on that reduced-resolution image, and then warp the resulting bounding box back up to the native-resolution coordinate system. However, I have some questions about dealing with the bounding box coordinates and how detectors treat, or should treat, these coordinates.<br><br>I wrote a new OCV image_pyramid process, which can be configured to apply multiple iterations of OCV's pyrUp or pyDown and can emit a homography (there is actually a 0.5 pixel translation on each level, so it's not just a scaling) representing the warping from output image back to source image. I am also writing a <b>detected_object_bounding_box_<wbr>warp</b> node to apply a homography to each bounding box in a detected_object_set. Basically, it will warp the top-left and bottom-left coordinates with the homography. Though, I admit it is a little weird applying a homography to a bounding box that has to remain an axis-aligned rectangle. So, maybe there is a discussion about renaming or reworking this.<br><br></div>My question is related to the precise definition of the bounding box, which encodes the upper left and lower right coordinates of the box. Do we have a standard enforced for how detectors populate these bounding boxes? Let's say you have a detection covering a rectangle of pixels starting at upper-left pixel indices (x1,y1) to lower-right (x2,y2) inclusive, I would think the bounding box definition should be (x1-0.5,y1-0.5) to lower-right (x2+0.5,y2+0.5), which is the box in image coordinates completely containing the area of the pixels. A different of a half pixel may seem trivial, but in my case, I am detecting on a highly reduced version of the image and then upscaling the bounding boxes, so that half pixel of different can be compounded many times.<br><br></div>Thanks,<br></div>Matt<br></div>
<br>______________________________<wbr>_________________<br>
Kwiver-users mailing list<br>
<a href="mailto:Kwiver-users@public.kitware.com">Kwiver-users@public.kitware.<wbr>com</a><br>
<a href="https://public.kitware.com/mailman/listinfo/kwiver-users" rel="noreferrer" target="_blank">https://public.kitware.com/<wbr>mailman/listinfo/kwiver-users</a><br>
<br></blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div>Paul Tunison<br>Senior R&D Engineer</div><div>Kitware, Inc.</div><div>28 Corporate Drive</div><div>Clifton Park, NY 12065 USA</div><div><br></div><div>Phone: (518) 371-3971 Ext.164</div></div></div></div>
</div>