Revision history [back]

HI! I download dataset from gdo152.ucllnl.org (15 cm per pixel) and right now have: 6 700 positive tiles (with vehicle) and 7 000 negative (other object&nature) each 120x120 pixel. Then I training HOG + linear SVM, test on learning data with this result: True Positives: 6409 True Negatives: 6393 False Positives: 607 False Negatives: 309 and when I test my descriptor on Selwyn aerial, I have a lot of false positive and negative alarm (red circle) C:\fakepath\8.png C:\fakepath\9.png how to make result better: -it is possible to make samples less? -apply filters? -Change the ratio of positive and negative images in the training sample?

I will be happy with the advice. Thank you! C:\fakepath\15.png

HI! I download dataset from gdo152.ucllnl.org (15 cm per pixel) and right now have: 6 700 positive tiles (with vehicle) and 7 000 negative (other object&nature) each 120x120 pixel. Then I training HOG + linear SVM, test on learning data with this result: result:
True Positives: 6409 6409
True Negatives: 6393 6393
False Positives: 607 607
False Negatives: 309 309
and when I test my descriptor on Selwyn aerial, I have a lot of false positive and negative alarm (red circle) C:\fakepath\8.png
C:\fakepath\9.png
how to make result better: better:
-it is possible to make samples less? less?
-apply filters? filters?
-Change the ratio of positive and negative images in the training sample?

HI! I download dataset from gdo152.ucllnl.org https://gdo152.llnl.gov/cowc/ (15 cm per pixel) and right now have: 6 700 positive tiles (with vehicle) and 7 000 negative (other object&nature) each 120x120 pixel. Then I training HOG + linear SVM, test on learning data with this result:
True Positives: 6409
True Negatives: 6393
False Positives: 607
False Negatives: 309
and when I test my descriptor on Selwyn aerial, I have a lot of false positive and negative alarm (red circle) C:\fakepath\8.png
C:\fakepath\9.png
how to make result better:
-it is possible to make samples less?
-apply filters?
-Change the ratio of positive and negative images in the training sample?

I will be happy with the advice.
Thank you!
C:\fakepath\15.png