Salient target detection method and system based on based on weakly supervised spatial-temporal cascaded neural network

A neural network and target detection technology, applied in the field of salient target detection method and system based on weakly supervised space-time cascaded neural network, can solve the problems of poor accuracy and robustness, and achieve the goal of improving accuracy and robustness Effect

Active Publication Date: 2018-07-06
SHENZHEN UNIV
View PDF5 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a salient object detection method and system based on a weakly supervised spatio-te

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Salient target detection method and system based on based on weakly supervised spatial-temporal cascaded neural network
  • Salient target detection method and system based on based on weakly supervised spatial-temporal cascaded neural network
  • Salient target detection method and system based on based on weakly supervised spatial-temporal cascaded neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0023] In order to make the objectives, technical solutions and advantages of the present invention clearer, the following further describes the present invention in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention.

[0024] In order to solve the problem of poor accuracy and robustness of existing video salient target detection methods in complex scenes, an embodiment of the present invention proposes a salient target detection method based on weakly supervised spatio-temporal cascaded neural network. The hand-calibrated strong label image containing label data and the weak label image containing a large amount of weak label data generated under the unsupervised method are trained to obtain a robust saliency prediction model. In addition, the embodiment of the present invention also proposes a spatiotemporal...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention is applicable to the field of video and image identification, and provides a salient target detection method. A spatial-temporal cascaded neural network consists of a first fully convolutional network and a second fully convolutional network. The method comprises the following steps: inputting a current frame of image of a to-be-detected video to the first fully convolutional networkto obtain a spatial prior map; generating a temporal prior map according to the current frame of image and the optical flow map thereof; carrying out element operation on the spatial priori map and the temporal prior map to get a spatial-temporal prior map; and inputting the spatial-temporal priori map and the next frame of image to the second fully convolutional network to get a spatial-temporalsaliency map. According to the embodiments of the invention, in the detection of a salient target in a video with a complex scene, the spatial prior information of the video frame image and the temporal prior information based on the optical flow are integrated to eliminate a static salient region and generate a final spatial-temporal saliency map in a dynamic scene, so that more and richer information can be obtained in the dynamic scene, and the accuracy and robustness are improved.

Description

technical field [0001] The invention belongs to the field of video and image recognition, in particular to a salient target detection method and system based on a weakly supervised space-time cascaded neural network. Background technique [0002] Salient object detection aims to identify relatively attractive objects or regions in images or videos. It has a wide range of applications in object segmentation, object recognition, object tracking and other fields, and is the focus of computer vision research. Salient object detection for static images only considers spatial information, while salient object detection for dynamic videos considers both spatial and temporal information. Therefore, deep learning models for static images are less effective in dynamic video scenes. [0003] How to eliminate the interference of relatively complex background areas in videos is a key issue in salient object detection. Existing saliency detection methods can be divided into two categorie...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/217
Inventor 罗海丽唐毅邹文斌李霞徐晨
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products