A model of saliency-based visual attention for rapid scene analysis
A model of saliency-based visual attention for rapid scene analysis
复制标题
DOI：
10.1109/34.730558
复制
发表时间：
1998-11-01
影响因子：
23.6
通讯作者：
Niebur, E
中科院分区：
文献类型：
--
作者：
Itti, L;Koch, C;Niebur, E
视觉注意系统，灵感来自早期灵长类动物视觉系统的行为和神经元结构，提出。多尺度图像特征被组合成一个单一的地形显着图。然后，动态神经网络按照显着性降低的顺序选择关注的位置。该系统打破了场景理解的复杂问题，通过快速选择，在计算效率的方式，显着的位置进行详细分析。
A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail.