Multi-thread significance method based on light field camera

Abstract

The present invention discloses a multi-thread significance method based on a light field camera. The method comprises: 1, employing a Lytro light field camera to collect five-dimensional light field data in a scene and obtains light field full-focusing images, depth images, a focus stack image sequence and a multi-view image sequence; 2, performing super-pixel segmentation of the full-focusing images, and extracting the color, the position and the depth difference characteristics between the pixel pairs on different light field images; 3, respectively extracting the average optical flow characteristics of an adjacent focal plane image and an adjacent visual angle image, and calculating the focus flow difference characteristics and the visual angle flow difference characteristics; 4, performing weighting and summation of the color, the depth, the focus flow and the visual angle flow difference characteristics, and taking the position difference characteristic as a weight, and obtaining the original substantial results of multiple clues; and 5, optimizing the original substantial results, and obtaining the multiple-clue significance of the light field camera. The multi-thread significance method based on a light field camera is able to solve the defect that the current two-dimensional and three-dimensional significance extraction method cannot obtain and use the vision multiple clues so as to effectively improve the extraction precision of the image significance in the complex changeable scene.

Description

Technical field [0001] The invention belongs to the fields of computer / machine vision, image processing and analysis, and specifically is a multi-cue saliency extraction method based on a light field camera. Background technique [0002] With the rapid development of multimedia information technology, the complexity and diversity of image data continue to increase. The effective acquisition and processing of visual information is the key to accurately and efficiently describing the externally variable environment. One of the purposes of saliency extraction is to select important parts of interest from a large amount of visual information, and give priority to the salient parts extracted to allocate resources to speed up information processing and effects. It is one of the research hotspots in the computer / machine vision field. It has been widely used in the fields of image and video compression, target tracking and recognition, and image retrieval. [0003] According to the availa...

AI Technical Summary

Problems solved by technology

[0008] The present invention aims to solve the defect that the current two-dimensional or three-dimensional saliency extraction method cannot obtain and effectively use visual multi-cues, pays attention to all visual elements contained in the plenoptic function, and provides a multi-cue saliency extraction method based on a light field camera. In order to improve the accuracy of image saliency extraction in complex and changeable scenes, so as to deeply understand the internal attention mechanism guided by different visual cues, and provide a new idea for the visual application of light field cameras

Images