HOG descriptor for pedestrian detection training

Question

I wonder why my HOG descriptor can't prevail the right silhouettes of the human body. I use the parameters like

CV_WRAP HOGDescriptor() : winSize(64,128), blockSize(16,16), blockStride(8,8),
        cellSize(8,8), nbins(9), derivAperture(1), winSigma(-1),
        histogramNormType(HOGDescriptor::L2Hys), L2HysThreshold(0.2), gammaCorrection(true),
        free_coef(-1.f), nlevels(HOGDescriptor::DEFAULT_NLEVELS), signedGradient(false)
    {}

When I plot them why I don't have correct silhouettes as the one sample shown in this discussion. The two images are attached. Color image is my hog descriptor and gray is the one from the above link.

What are the facts I need to look at to have correct silhouettes as shown in the image in the above discussion?

The gray image is the positive weighted image to the HOG descriptor. Not the pure descriptor. I wonder how Opencv's default people detector is trained. The trained SVM detector size is only a few kilobyte and detection rate is good. My trained detector has Megabyte of size and hit rate is poor/false alarm rate is high. — batuman, Jan 27 '16 at 08:49
This website might help you: http://www.geocities.ws/talh_davidc/ — SomethingSomething, Feb 18 '16 at 14:54

score 0 · Accepted Answer · answered Jan 27 '16 at 08:50

0

The gray image is the positive weighted image to the HOG descriptor. Not the pure descriptor. I wonder how Opencv's default people detector is trained. The trained SVM detector size is only a few kilobyte and detection rate is good. My trained detector has Megabyte of size and hit rate is poor/false alarm rate is high.

answered Jan 27 '16 at 08:50

batuman

7,066
26
107
229

Now I can figure out how to train SVM with good false alarm rate and high detection. That is first prepare sets of positive images and negative images. Then train for Support Vectors. Then run the negative samples to get false positive detections. Then those false positives are added into negative samples and train again. This process is repeated two to three times till false positive rate is not much improved. Then that is the Support Vectors with good detection accuracy. – batuman Jan 28 '16 at 10:14

HOG descriptor for pedestrian detection training

1 Answers1