李德仁, 胡晓光, 朱欣焰. 基于视觉反差的显著图生成与目标检测[J]. 武汉大学学报 ( 信息科学版), 2012, 37(4): 379-383.
引用本文: 李德仁, 胡晓光, 朱欣焰. 基于视觉反差的显著图生成与目标检测[J]. 武汉大学学报 ( 信息科学版), 2012, 37(4): 379-383.
LI Deren, HU Xiaoguang, ZHU Xinyan. Visual Contrast Based Saliency Map Generation and Object Detection[J]. Geomatics and Information Science of Wuhan University, 2012, 37(4): 379-383.
Citation: LI Deren, HU Xiaoguang, ZHU Xinyan. Visual Contrast Based Saliency Map Generation and Object Detection[J]. Geomatics and Information Science of Wuhan University, 2012, 37(4): 379-383.

基于视觉反差的显著图生成与目标检测

Visual Contrast Based Saliency Map Generation and Object Detection

  • 摘要: 以认知神经科学的研究成果为依据,对视网膜会强烈响应大反差视觉刺激的现象和初级视觉皮层上视觉信息的生成机制进行了模拟,提出了一种基于视觉反差的显著图生成与目标检测方法。本方法可以在不考虑目标的形状、边缘或其他形式先验知识的情况下检测出场景中具有显著反差的目标。在对地场景中车辆目标的检测实验里,将其与另外两种典型的显著图生成方法进行了对比,结果显示,这种基于视觉反差的目标检测方法能够较好地将注意力集中在场景中具有较大反差的目标之上,且具有高效性和鲁棒性。

     

    Abstract: The phenomenon that the retina will strongly respond to large contrast visual stimulation and the generation mechanism of visual information in the primary visual cortex can be simulated.Therefore,In this paper,we propose a method generating saliency map and detecting object according to the cognitive neuroscience research.The method can detect significant contrast object without considering the shape,edge,or other forms of prior knowledge of the objects.We compare the method with the other two typical saliency methods in detecting vehicle target from ground scenes.The results show the detection method based on visual contrast can better concentrate on the object with greater contrast and is fast and robust.

     

/

返回文章
返回