Unconstrained in-video salient object detection method combined with objectness degree

Abstract

The invention discloses an unconstrained in-video salient object detection method combined with an objectness degree. The unconstrained in-video salient object detection method specifically comprises the steps of: (1) inputting an original video sequence F={F<1>, F<2>, ..., F<M>}, wherein a t-th frame in the sequence is referred to as F<t>; (2) adopting a video saliency model and an objectiveness object detection algorithm for the video frame F<t>, so as to obtain an initial rectangular region for salient object detection; (3) updating an objectness degree probability graph and an object probability graph through iteration for the video frame F<t>, and adjusting the size of the rectangular region for salient object detection continuously, so as to obtain a single-frame salient object detection result; (4) and utilizing a dense optical flow method algorithm to obtain a motion vector field of pixel points of the video frame F<t>, and calculating the overlapping degree of the rectangular regions for salient object detection of the adjacent frames, so as to obtain a final salient object detection result. The unconstrained in-video salient object detection method updates the objectness degree probability graph and the object probability graph through iteration, enhances the precision of spatial domain salient object detection results, improves time consistency through sequence-level refining, and can detect salient objects in a video more accurately and completely.

Description

technical field [0001] The invention relates to computer vision and video processing technical fields, in particular to a method for detecting salient objects in unconstrained video combined with similarity degree. Background technique [0002] The human visual system can quickly and accurately locate the area of ​​interest of the human eye from a complex environment and respond accordingly. According to research in psychology and perception science, in most cases, the human eye is observing an image When drawing an image, attention will not be evenly distributed over the entire image, but attention will be focused on a certain area in the image, which is called a salient object. The salient object detection method uses the saliency image corresponding to the image attention to detect the salient objects in the image accurately and quickly. The result of the detection is to mark a rectangular area in the image, which contains as many salient objects as possible and as littl...

AI Technical Summary

Problems solved by technology

[0015] However, the shortcomings of the above methods are that the three method models are not robust to video sequences with complex motion and rely on the quality of the saliency map

In summary, the existing salient object detection methods cannot accurately and completely extract salient objects in unconstrained video sequences, which hinders the wide application of salient object detection

Images