Edge Based Adaptive Kalman Filtering for Real-time Video Stabilization
Ohyun Kwon, Jeong-Ho Shin, Joonki Paik · 2006
Image stabilization, particularly during zoom-in is an important feature in consumer cameras. Existing methods to stabilize an image often make an incorrect motion vector by an improper choice of motion estimation or correction method. The proposed algorithm is simple and effective; it is suitable for low cost camcorders, digital cameras, CCTV, surveillance video systems, and television broadcasting systems.