Computational Intelligence and Neuroscience / 2018 / Article / Tab 1

Research Article

Real-Time Human Detection for Aerial Captured Video Sequences via Deep Models

Table 1

Accuracy comparison between CNN_soft-max, CNN_SVM, pretrained CNN, and HELM.

Cross validation (4 persons out of 12)Supervised CNN + soft-maxSupervised CNN + SVMPretrained CNN + SVMHELM

194.054291.896697.717094.7065
297.372691.913197.611597.9186
396.154292.983598.598896.0008
497.105692.819997.850997.4410
5 94.698291.198197.934494.9851
695.797491.2816 98.407795.7583
791.713187.882398.074992.3971
896.564992.782898.531196.5765
997.020793.612898.055697.3239
1095.518490.652498.125795.7467

Average accuracy95.5999%91.7023%98.0908%95.8855%

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.