Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Inter-frame difference and convolutional neural network fusion-based ship video detection method

A convolutional neural network and video detection technology, applied in the field of image processing, can solve problems such as limited applicable scenarios, failure to meet requirements, and insufficient use of ship video detection accuracy, etc., to reduce the detection area, facilitate feature selection, and background interference small effect

Inactive Publication Date: 2018-06-29
NANJING UNIV
View PDF4 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The problem to be solved by the present invention is: the existing ship detection technology does not make full use of the feature detection accuracy rate of the ship video and cannot meet the requirements, and the applicable scenarios are limited

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
  • Inter-frame difference and convolutional neural network fusion-based ship video detection method
  • Inter-frame difference and convolutional neural network fusion-based ship video detection method
  • Inter-frame difference and convolutional neural network fusion-based ship video detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention provides a ship video detection method based on the fusion of inter-frame differences and convolutional neural networks. The inter-frame differences are obtained for ship videos, and the requirements are obtained based on the inter-frame differences and the ship's position detected in the previous frame. The detected ship may have an area. As the ROI area, the ROI area is divided into small areas to extract shallow features, and then the modified and trained VGG16 network is used to extract high-level features for each frame of image, and the shallow features and high-level features are cascaded as A feature vector is input into the subsequent softmax classifier to judge the salient degree of the ship in the ROI area, so as to obtain the final detection effect.

[0020] The present invention mainly includes four parts: preprocessing the video such as suppressing noise and image sharpening, extracting the difference between ship video frames to obtai...

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 discloses an inter-frame difference and convolutional neural network fusion-based ship video detection method. The method comprises the four parts of preprocessing a video; obtaining anROI of each frame and extracting low layer features; obtaining high layer features of each frame of image by using a modified VGG16 network; and predicting a ship saliency map of the ROI of each frameand extracting a ship target. A relationship between continuous video frames is fully utilized; the interference of a background is reduced; a moving ship is accurately located; a ship moving regionis obtained; and compared with ship image saliency detection only using the low layer features, the method not only can be directly applied to the ship video detection but also reduces the situation of incomplete ship detection, has higher adaptability to a complex inland river moving ship scene, has higher detection precision, solves the problem of inaccurate inland river ship target saliency detection, and has extremely high practical application values.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to video image processing, that is, computer vision detection technology, which is used for video detection of inland waterway ships, and is a ship video detection method based on the fusion of inter-frame differences and convolutional neural networks. Background technique [0002] Compared with road transportation, inland waterway shipping is cheaper, about 1 / 10 of road transportation, especially suitable for the transportation of bulk goods, and has a wide range of applications. Although monitoring cameras have been gradually deployed along the waterway, the automation of monitoring video is still relatively backward. Interference such as sparkling water surface, water surface not like asphalt road surface, poor contrast, synchronous mopping at the stern of a ship undoubtedly increases the difficulty of waterway video detection. In addition, in order to accurately control ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/46G06K9/62G06N3/04
CPCG06V20/40G06V10/25G06V10/50G06V10/56G06N3/045G06F18/253
Inventor 阮雅端张宇杭张园笛王麟皇赵博睿陈启美
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com