P1t's profile - activity

Ok, thank you for your answers. I will try some minor changes (parametric overlap, reduce lock of mutex) and I will come back to give you my results. If it's not enough and if I have enough time, I will try to change the haar cascade.

I have some ideas but most of those are not compatible with LBP or HOG detector (setImage once in detectmultiscale, update pointer in setwindow, scale feature during pointer updating ...). I'm not sure (I'm not sure to well understand ystep) but it seems that the detector run for each line. Is this necessary? 1/2 or 2/3 of overlap is not enough?

1. TBB is activated. I modified some lines in the part of code to reduce the overhead time due to lock by it don't change a lot.
2. That's interesting. Is there specific place where this community discuss about that? I work to understand this part of code and find bottleneck. I'm interesting to know on which way you are working and me give my help. (For example, do you know if there is some works to use natural optimization of haar features (resize feature not the image)...)
3. I use haar features, not tilted, Gentle AdaBoost, hit rate 0.999, false alarm 0.5, other parameters are default.

.

Hi, I use a cascade classifier from Opencv to detect some objects in real time (12801024px image) but It too slow for me. I use 20 stages cascade on 2020px patch with a scale factor of 1.1. I'm about 2.5FPS on an embedded computer. I would like about 10FPS.

Here is my questions :

Is there some well known bottlenecks in this part of Opencv that I could rapidly fix?

Is there some projects (github ...) to improve this part of Opencv?

Is there some libraries (open source or not) that have a faster implementation of Viola Jones detector (cascade classifier)?

I use OpenCV because I do lot of processing on those images. The compression part is just the result step. This is why I was looking for openCV's solutions. Btw thank you for your answer

Image compression is pretty new for me, do you know some algorithm that allow this functionality? I would like to compress some image with loss except in the roi that need to be lossless.

After looking the jasper's FAQ, it seems that only the decoder can handle roi functionality.

Hi,

I would like to use the roi functionality of JPEG2000 in imencode function. This functionality allows to compress some parts with a level of compression lower than the rest of the image. I don't find any documentation about this in OpenCV doc and I would like to if OpenCV can handle this.

Thank you in advance

PS : I use Opencv 2.4 (for nom) on Ubuntu OS