Ramirez-Moreno David F, Schwartz Odelia, Ramirez-Villegas Juan F
Computational Neuroscience, Department of Physics, Universidad Autonoma de Occidente, Cali, Colombia.
Biol Cybern. 2013 Apr;107(2):141-60. doi: 10.1007/s00422-012-0542-2. Epub 2013 Jan 12.
This work proposes a model of visual bottom-up attention for dynamic scene analysis. Our work adds motion saliency calculations to a neural network model with realistic temporal dynamics [(e.g., building motion salience on top of De Brecht and Saiki Neural Networks 19:1467-1474, (2006)]. The resulting network elicits strong transient responses to moving objects and reaches stability within a biologically plausible time interval. The responses are statistically different comparing between earlier and later motion neural activity; and between moving and non-moving objects. We demonstrate the network on a number of synthetic and real dynamical movie examples. We show that the model captures the motion saliency asymmetry phenomenon. In addition, the motion salience computation enables sudden-onset moving objects that are less salient in the static scene to rise above others. Finally, we include strong consideration for the neural latencies, the Lyapunov stability, and the neural properties being reproduced by the model.
这项工作提出了一种用于动态场景分析的视觉自下而上注意力模型。我们的工作将运动显著性计算添加到具有逼真时间动态的神经网络模型中[(例如，在De Brecht和Saiki的《神经网络》19:1467 - 1474，(2006)的基础上构建运动显著性)]。由此产生的网络对移动物体引发强烈的瞬态响应，并在生物学上合理的时间间隔内达到稳定。这些响应在早期和后期运动神经活动之间，以及在移动物体和非移动物体之间的统计上是不同的。我们在一些合成和真实动态电影示例上展示了该网络。我们表明该模型捕捉到了运动显著性不对称现象。此外，运动显著性计算使在静态场景中不太显著的突然出现的移动物体能够脱颖而出。最后，我们充分考虑了神经潜伏期、李雅普诺夫稳定性以及模型所再现的神经特性。
