摘要
This paper proposes a new neural algorithm to perform the segmentation of an observed scene into regions corresponding to different moving objects byanalyzing a time-varying images sequence. The method consists of a classificationstep, where the motion of small patches is characterized through an optimizationapproach, and a segmentation step merging neighboring patches characterized bythe same motion. Classification of motion is performed without optical flow computation, but considering only the spatial and temporal image gradients into anappropriate energy function minimized with a Hopfield-like neural network givingas output directly the 3D motion parameter estimates. Network convergence is accelerated by integrating the quantitative estimation of motion parameters with aqualitative estimate of dominant motion using the geometric theory of differentialequations.
This paper proposes a new neural algorithm to perform the segmentation of an observed scene into regions corresponding to different moving objects byanalyzing a time-varying images sequence. The method consists of a classificationstep, where the motion of small patches is characterized through an optimizationapproach, and a segmentation step merging neighboring patches characterized bythe same motion. Classification of motion is performed without optical flow computation, but considering only the spatial and temporal image gradients into anappropriate energy function minimized with a Hopfield-like neural network givingas output directly the 3D motion parameter estimates. Network convergence is accelerated by integrating the quantitative estimation of motion parameters with aqualitative estimate of dominant motion using the geometric theory of differentialequations.
