ROV deformed target and small target recognition method based on convolution kernel screening SSD network

A recognition method and a convolution kernel technology, which are applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the need for large amounts of calculations, deep learning cannot run in real time, power consumption increases, and it is difficult to solve, etc. problem, to achieve the effect of reducing weight parameters, improving real-time performance, reducing occupied volume and calculation amount

Active Publication Date: 2019-02-22
OCEAN UNIV OF CHINA
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To this end, we have introduced an underwater robot control platform based on Raspberry Pi and flight control. For the current deep learning model, the deeper the model contains more parameters, which brings a signific

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
  • ROV deformed target and small target recognition method based on convolution kernel screening SSD network
  • ROV deformed target and small target recognition method based on convolution kernel screening SSD network
  • ROV deformed target and small target recognition method based on convolution kernel screening SSD network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Embodiment 1: Sea cucumbers in the marine underwater environment are taken as detection objects.

[0025] The specific flow chart of this embodiment is as follows figure 2 shown.

[0026] The following steps should be described in detail in conjunction with the accompanying drawings and specific results, and should only be outlined steps in the summary of the invention.

[0027] Step 1. Equipped with ROV (Underwater Robot Control Platform), in which the Raspberry Pi is used as the upper computer, responsible for image transmission and basic calculations, the Intel Network Neural Stick is used as the Raspberry Pi coprocessor for deep learning model calculations, and the flight controller is used as the motion controller. control platform. The hardware block diagram of the present invention is as figure 1 shown.

[0028] Step 2. Collect the underwater sea cucumber video (1920*1080 pixels, 25 frames per second) collected by the underwater robot motion control platform...

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 provides a target re-identification method based on hypersphere embedding of a densely connected convolution network. At first, that features of underwater deformation object in the video sequence are extracted according to the secret-level connected convolution network DenseNet, so that that gradient disappear is greatly reduced, feature propagation is enhanced, feature reuse and parameter learning processes are supported; from the viewpoint of fine-grained classification, from local integration to global integration, the characteristics of underwater deformation targets are extracted by means of grouping average pooling, the more accurate feature expression ability of underwater deformation target is obtained; focusing on the inter-class difference of underwater deformation individual targets by using hypersphere loss, i.e. angular triple loss, the difference in regional classification are classified to avoid the direct measurement of the Euclidean distance between theindividual target coding features of underwater deformation, a complete and continuous underwater deformed individual target re-recognition model based on multi-point placement is constructed. The invention finally completes the close supervision and process tracking of the underwater deformation target individual in the close-range multi-field observation.

Description

technical field [0001] The invention relates to a detection method based on underwater deformation targets and small targets, and belongs to the technical fields of intelligent information processing, target detection and underwater robots. Background technique [0002] The detection of underwater deformable targets and small targets is an indispensable link in most vision systems. In specific scene applications (such as video surveillance and other fields), automatic, fast, and highly robust target tracking has attracted attention. It has broad application prospects in video surveillance, traffic detection, intelligent robots, and submarine target detection and tracking. In addition, based on the strategic significance of the ocean, the ocean must be rationally developed, researched and utilized. [0003] Underwater robot (Remote Operated Vehicle, ROV) can replace human beings to work in complex and dangerous underwater environments due to its flexible maneuverability and ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/10G06N3/045G06F18/214
Inventor 年睿王孝润李晓雨何慧
Owner OCEAN UNIV OF CHINA
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap