Visual Stimulus Detection Using Multiple Foveas
Multifoveation, visual stimuli, visual detection, gradient descent, maximum likelihood, trilateration and barycentric coordinates
The multifoving technique allows the addition of several focuses in the image, which can be explored as points of visual attention in contexts of detection, identification and / or object recognition. However, the use of the multifoving technique requires knowledge of the position of visual stimuli. In this work we propose a new approach to detect visual stimuli using the structure of multiple foveas. For this, we use mathematical strategies adapted to the context of computational vision, which take into account the distribution of the foveas to estimate the location of visual stimuli in the image. The mathematical strategies adopted were the descent of the gradient (potential field), maximum likelihood, multilateration, trilateration and barycentric coordinates. The results show that the algorithms converge for the position of the visual stimulus, with the exception of the local potential intersection algorithm due to the sensitivity to local minimums. In addition, the algorithms that use potential fields require more processing time and computational resources compared to other strategies. However, it is possible to affirm that three fóveas are sufficient to estimate the position of a visual stimulus in the image making use of the trilateration algorithms and baricentric coordinates. We conclude that the multi-panning associated with mathematical strategies can be applied in visual detection and presents convergence with at least three foveae.