TechWizard's profile - activity

@StevenPuttemans I've just realised that some of my positive samples are really dark and of really bad quality. Could this be the reason for the lot of false positives? Another thing: the training with 700 positive/1200 negative images of a 20-layer cascade takes only ~40 minutes on a 4-core i5 laptop. Isn't that too fast? Could it be that the training is not performed properly?

@StevenPuttemans I tried to train a cascade classifier by using only my dataset. The problem is that it produces an awful lot of false positives (while the haarcascade_frontalface_alt.xml has max. 1-2 false positives, my custom classifier has sometimes 40-50 false positives) during detection. Do you have any suggestions how could I make it more accurate? Here is my current setup: I have 6 fullHD videos (400 frames each) together with their ground-truth. I extracted all faces based on the ground-truth and scaled them to 24x24 pixel images. From this I have ~760 positive samples. Furthermore, I extracted ~1300 fullHD (1920x1080 pixel) frames, where nothing is going on (no annotation in the ground-truth), these are my background/negative samples. I created a 20 layer cascade.

Hi Steven, for a research project I would also need the opportunity to update some of the included models (e.g., haarcascade_frontalface_alt.xml). Do you think it would be possible to use exactly the same settings and dataset by which the haarcascade_frontalface_alt.xml file was generated, complement the dataset with my own images, and run it again? Are these settings and dataset available somewhere?

I got the same error at first. After adding the following cmake cache entries, the compilation of OpenCV 3.0.0-beta was successful.

-D CUDA_ARCH_BIN=3.2
-D CUDA_ARCH_PTX=3.2

Note: I have Linux for Tegra R21.3 with CUDA 6.5 and ffmpeg-2.5.4* installed on my Jetson TK1 dev-board.

*Don't forget to compile with the --enable-shared config option!