trops's profile - activity

Ohhh, on the results page. Got it. I do see the code projects now. Was completely missing it. So although its not C++ Ill try my best at figuring out how to run Torch7. Was hoping to use opencv and c++. Never touched torch before. Ill give it a shot!

Thats what I thought :-) So here is my issue. I have the need to detect body points for my application. I am trying to find code that is written in C++ that will allow me to do this. I have found a few libraries that contain code to detect points using different models.

I would like to find out how to detect the body points in a 2d image. I hope this makes sense.

Thanks again for your help! John

Hi, thanks for the answer, I have found this dataset before and I guess my struggle is HOW to use it ;-) I think this would be fantastic, and have downloaded the evaluation toolkit but I guess my question is how to use the dataset to detect positions. Im quite new to this so any help is appreciated. Im trying to get this running with C++ not matlab if possible.

I am trying to find a reliable pose estimation sample out there and have run across several codebases on github. wg-perception being one of them. I ended up running a codebase that I found and while it compiles and runs, the joints that are detected using the model are far from great.

I found this online: http://www.comp.leeds.ac.uk/mat4saj/l...

And while I see the annotations on the images, I was hoping the resulting detections would look like that ;-)

My goal is to detect the joints of the human body from still images. I know this is a big issue, but it would really be fantastic.

Thanks, John

I tried to answer my own question but it wouldn't let me, but here is what worked.

The libraries that were "missing" were actually located in the following directory:

/usr/lib/x86_64-linux-gnu/

So I had to execute the following line:

export PKG_CONFIG_PATH=/usr/lib/x86_64-linux-gnu/pkgconfig

And then I ran all my installation scripts as usual.

I tried to paste the entire script for installation (that works actually) and the formatting was insane.

Send me a note if you want the script for installing opencv3 with opencv_contrib on ubuntu.

Thanks everyone for your answers!

Yes, I have installed the required packages and confirmed that they are installed. It seems they aren't linked possibly? Or opencv3 can't find them for some reason.

Hi guys and gals,

Ive been trying to compiles opencv3 on ubuntu and am hitting this error:

* No rule to make target /usr/include/../lib/libavcodec.a', needed bylib/libopencv_videoio.so.3.1.0'. Stop.

I have ffmpeg installed, and cannot figure out who to get this to work properly. Any ideas?

Thanks, John

Yeah, that is what I thought too, but then I found this post which got me thinking that it is. I could not find this line of code in the opencv 3.1 file mentioned but I DID find getDecisionFunction method. Im just not sure how to use it, its a bit over my head.

Im trying to detect multiple positions of one human in a video. Someone told me a multi class SVM is the way to go, and I have the code working, just doesn't give probability...so this method is moot if I can't get that. When I run the video it will classify the first 100 frames as "1" the next 100 as "2", and so forth. I just need the BEST match for each class that I train in the SVM.

Im curious about how to go about using the predict method in SVM for a multi class object detector using BoF and SIFT.

Ive trained the svm with 8 classes, and when I call predict it determines the class label. Thats all well and good but I am trying to determine the probability. I am reading video frames and each frame is so closely related that the label alone will not help.

I need to figure out how to calculate the probability so that I can choose the closest match possible after reading all of the frames.

I am looking into getDecisionFunction but the result is always the same (0.986196) for each frame in the video that I am using the SVM to predict.

Is there a step that I need to take in order to fetch the probability of the prediction?

I am using openCV 3.1 if this helps.

Thanks, John