A trainable object-tracking method using equivalent retinotopical sampling

摘要

In this article, a maximum likelihood based trainable object tracking method is proposed. The concept of Retinotopical Sampling (RS) was inspired by human saccadic eye movements and enables a quick recognition of eyes, mouth in static images. However, when the object size is inferred by RS the result tends to gravitate towards zero. In this article, Equivalent Retinotopical Sampling (ERS), which is an extension of RS, is proposed. ERS can infer the size of objects more accurately. Using ERS, a trainable object tracking method, with essentially only two parameters, has been formulated.