The paper presents a modular approach for the estimation of a leading vehicle's velocity based on a non-intrusive stereo camera where SiamMask is used for leading vehicle tracking, Kernel Density estimate (KDE) is used to smooth the distance prediction from a disparity map, and LightGBM is used for leading vehicle velocity estimation. Our approach yields an RMSE of 0.416 which outperforms the baseline RMSE of 0.582 for the SUBARU Image Recognition Challenge

翻译：本文提出一种基于非侵入式立体相机的前车速度估计模块化方法，其中SiamMask用于前车跟踪，核密度估计用于平滑视差图距离预测，LightGBM用于前车速度估计。该方法在斯巴鲁图像识别挑战赛中获得0.416的均方根误差，优于基线模型的0.582均方根误差。