Moving Object Proposal by Grouping with Motion Feature

Abstract

Recently, object recognition is improved accuracy by Convolutional Neural Network(CNN) and growing object recognition demand for automatic driving system and security and so on. However, one of the problem of object recognition is to extract object region which have various size, scale and form. This paper propose moving object proposal for object recognition. Using region grouping and scoring with optical flow, we can propose object proposal for moving objects. The object proposal experiments show effective results compared with previous method on the UCF crowd dataset.