Eff i cient Non-Maximum SuppressionAlexander NeubeckETH Zurich, SwitzerlandComputer Vision Labaneubeck@vision.ee.ethz.chAbstractIn this work we scrutinize a low level computer visiontask – non-maximum suppression (NMS) – which is a cru-cial preprocessing step in many computer vision applica-tions....
The area under the curve (AUC) is calculated as the performance criterion (see the pseudocode in the appendix to this section). Note that a classifier with AUC=1 is perfect, whereas a classifier with AUC=0.5 is as good as a random guess. 16.3.3.3 Results and Discussions The methodology ...
a logistic regression (LR) classifier was constructed using the training set samples; in order to avoid overfitting, a cross-validation approach was utilized54. The detailed procedure used to build the classifier is described below, and code (with inline pseudocode in the comments) ...