Lappe Markus, Wittinghofer Karin, de Lussanet Marc H E
Institute for Psychology, University of Muenster Muenster, Germany.
Front Integr Neurosci. 2015 Mar 24;9:24. doi: 10.3389/fnint.2015.00024. eCollection 2015.
The visual recognition of action is one of the socially most important and computationally demanding capacities of the human visual system. It combines visual shape recognition with complex non-rigid motion perception. Action presented as a point-light animation is a striking visual experience for anyone who sees it for the first time. Information about the shape and posture of the human body is sparse in point-light animations, but it is essential for action recognition. In the posturo-temporal filter model of biological motion perception posture information is picked up by visual neurons tuned to the form of the human body before body motion is calculated. We tested whether point-light stimuli are processed through posture recognition of the human body form by using a typical feature of form recognition, namely size invariance. We constructed a point-light stimulus that can only be perceived through a size-invariant mechanism. This stimulus changes rapidly in size from one image to the next. It thus disrupts continuity of early visuo-spatial properties but maintains continuity of the body posture representation. Despite this massive manipulation at the visuo-spatial level, size-changing point-light figures are spontaneously recognized by naive observers, and support discrimination of human body motion.
动作的视觉识别是人类视觉系统在社会层面最重要且计算要求最高的能力之一。它将视觉形状识别与复杂的非刚性运动感知结合在一起。以点光动画形式呈现的动作，对于任何首次看到它的人来说都是一种引人注目的视觉体验。在点光动画中，关于人体形状和姿势的信息很稀少，但对于动作识别至关重要。在生物运动感知的姿势 - 时间滤波模型中，在计算身体运动之前，视觉神经元会通过对人体形态的调谐来提取姿势信息。我们通过使用形状识别的一个典型特征，即大小不变性，来测试点光刺激是否通过人体形态的姿势识别进行处理。我们构建了一种只能通过大小不变机制感知的点光刺激。这种刺激在相邻图像之间大小快速变化。因此，它破坏了早期视觉空间属性的连续性，但保持了身体姿势表征的连续性。尽管在视觉空间层面进行了如此大规模的操作，但大小变化的点光人物仍能被未经训练的观察者自发识别，并支持对人体运动的辨别。
