目标跟踪的视觉注意计算模型

Abstract

中文摘要：借鉴心理学中有关视觉注意的研究成果，提出一种应用于视频图像序列的注意焦点计算模型。针对Itti 模型算法计算复杂度高、运算速度慢等缺点，通过对注意焦点的跟踪来降低计算量，实现注意焦点的实时监测。利用相邻帧之间的相似性，通过加权颜色直方图，以最大匹配度作为预测模型，得到下一帧注意焦点的位置。实验结果表明，该注意焦点计算鲁棒性较好，可以满足动态场景实时监测的需要。 英文摘要：This paper proposes a model of the focus of attention in video sequences. The Itti model has the complex and slow computation, so it reduces computation to monitor the focus of attention through tracking the focus of attention. It uses the similarity between the adjacent frames,establishes the color histogram, selects the maximum similarity as predicable model, and gets position of the focus of attention in the next fame. The experimental results indicate that this model is effective in robustness and real-time.