dumbogeorge's profile - activity

Stereo Calibration using sample code Hi Guys, I wish to calibrate a stereo setup using the sample code provided by Open

I wish to process an image (YUV domain) and do basic thresholding for purpose of object detection. I have currently used HSV frames (converted from BGR) to come up with thresholding values which helps me extract the object of interest. However, I would like to make use of YUV frame directly (instead of BGR frames) without any conversion to HSV/BGR to save computation to achieve the same result. Following is the code snippet which I would like to convert to make it work in YUV domain.

Thresholding implemented in HSV domain : currframe(BGR frame)

cvtColor(currFrame, HSVThreshImage, CV_BGR2HSV ,0); Scalar threshmin = Scalar(13, 0, 114); Scalar threshmax = Scalar(128, 255, 255); inRange(HSVThreshImage , threshmin, threshmax, HSVThreshImage);

I am able to get the object region using this code snippet.Kindly guide me to somehow achieve the same result as I am getting using this snippet but in YUV domain. Is there a way to directly convert thresholding and obtain values in YUV domain. Please help me out. Once I get the implementation I would like to apply it for YUV420p image format

Hi,

I am using EM class to train a single GMM depicting a small object in a video sequence for tracking use case. Provided that I get object samples for few number of frames initially, I use the RGB values of every pixel belonging to the object appearing in all the frame as feature vector and train the GMM with number of clusters = 3. Using the trained GMM model I try to find out which foreground blob in the next frame is most likely to represent the object that I have trained for and willing to track.

When I try to do so using EM predict2 function, I sometimes get positive values for loglikelihood returned. I am unable to comprehend the positive nature of the values since likelihood represents probability ranging from 0 to 1. Can someone please help me out with the basic understanding I am lacking about GMM / EM. How can I interpret the positive/negative values and take a decision whether the blob under consideration can represent the object or not.