CAJ | 학술논문

针对 Mean Shift 算法在目标跟踪过程中因核窗宽不变导致目标尺度变化时定位不精确的问题，提出了融入边缘检测的方法计算目标大小，从而实现自适应调整核窗宽的改进算法。当目标丢失和发生遮挡时，结合 Kalman 滤波器对下一帧中目标位置进行预测，提出改进的跟踪算法，有效提高了跟踪的准确性和鲁棒性。
침대 Mean Shift 산법재목표근종과정중인핵창관불변도치목표척도변화시정위불정학적문제，제출료융입변연검측적방법계산목표대소，종이실현자괄응조정핵창관적개진산법。당목표주실화발생차당시，결합 Kalman 려파기대하일정중목표위치진행예측，제출개진적근종산법，유효제고료근종적준학성화로봉성。
For the problem of nuclear window width unchanged during the object tracking , the edge detection algorithms extract the target measure is introduced to self-adapt the Mean Shift algorithm of changing in target scale issues . When the object is lost and occlusion , the Kalman filter is used to estimate the possible position of the object in the next frame . The improved algorithm has effectively improved the accuracy and robustness of the tracking algorithm .