The success of handheld video capturing devices has further fueled the need of improved video stabilization. The videos often contain many foreground facial features like eyes, nose etc. These foreground features can be considered as feature points and may be used to stabilize videos. This paper proposes an innovative and effective digital video stabilization technique, which utilizes foreground features present in the video to produce consistent and stabilized output. It uses successive stages of Boosted HAAR cascade and representative point matching digital motion stabilization algorithm to identify and stabilize the video. The feature based tracking of object improves motion estimation accuracy between two frames thereby increasing the correlation calculation and compensation motion vector. This work achieves a significantly smoother sequence after the motion compensation. It also improves the robustness, precision and quality of the video when compared to traditional digital stabilization algorithms. The simulation results compared with pre-existing techniques reflect distinct improvements in Inter-Frame Transformation Fidelity values and Structural Similarity Index along with lesser standard deviation between image frames.

手持式视频捕获设备的成功进一步推动了对改进视频稳定性的需求。视频通常包含许多前景面部特征，例如眼睛，鼻子等。这些前景特征可被视为特征点，并可用于稳定视频。本文提出了一种创新有效的数字视频稳定技术，该技术利用视频中存在的前景特征来产生一致且稳定的输出。它使用Boosted HAAR级联和代表点匹配数字运动稳定算法的连续阶段来识别和稳定视频。基于特征的对象跟踪提高了两个帧之间的运动估计精度，从而增加了相关性计算和补偿运动矢量。这项工作可以在运动补偿后实现明显更平滑的序列。与传统的数字稳定算法相比，它还提高了视频的鲁棒性，精度和质量。与现有技术相比，仿真结果反映了帧间变换保真度值和结构相似性指数的显着提高，以及图像帧之间的标准差较小。