CAJ | 학술논문

目标跟踪是计算机视觉领域的研究热点。该文提出了一种结合卡尔曼滤波和粒子滤波的目标跟踪算法。可以结合卡尔曼滤波算法计算量小，实时度高和粒子滤波算法准确度高，可以在非线性系统下稳定工作的优点。实验结果表明，该方法在计算速度和跟踪准确度上均能取得较满意的结果，具有一定的价值。
목표근종시계산궤시각영역적연구열점。해문제출료일충결합잡이만려파화입자려파적목표근종산법。가이결합잡이만려파산법계산량소，실시도고화입자려파산법준학도고，가이재비선성계통하은정공작적우점。실험결과표명，해방법재계산속도화근종준학도상균능취득교만의적결과，구유일정적개치。
Target tracking is a hot research field of computer vision. This paper proposes a combination of Kalman filter and parti-cle filter target tracking algorithm. Kalman filter algorithm has advantages of a small amount of calculation and high real-time, Particle filter algorithm has advantage of high accuracy and working work in a nonlinear system. The experimental results show that this method with a certain value has achieved satisfactory results in the speed and the accuracy.