基于集成学习的风沙跃移轨迹自动识别模型
周虹吉, 梅凡民, 蒲梦洁, 林川, 苏进, 陈金广

Ensemble models for identifying automatically aeolian saltating tracks driven by datasets
Hongji Zhou, Fanmin Mei, Mengji Pu, Chuan Lin, Jin Su, Jinguang Chen
图2 由KF-H算法提取视频M1中的第27号正确的上升轨迹(A),第7号正确的下降轨迹(B)和第16号错误轨迹(C)以及5 756条正确轨迹的拟合二次曲线的决定系数(R2 )的概率分布(D)
Fig.2 The 27th true ascent trajectory (A), the 7th true descent trajectory (B) and the 16th false trajectory (C)in video M1 extracted by the KF-H algorithm, respectively; Probability distribution of the determination coefficient (R2 ) for fitting quadratic curves of 5 756 true trajectories (D)