Machine learning method and device based on intelligent fishing rod

A machine learning and machine learning model technology, applied in the field of underwater fish image acquisition devices, can solve problems such as large misjudgment rate, inability to determine whether hook fish or other debris, poor user experience, etc., to increase robustness sexual effect

Active Publication Date: 2021-08-03
深圳市众凌汇科技有限公司
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since its working principle is often based on whether the acceleration value collected by the acceleration sensor is greater than the preset threshold range to determine whether there is a fish biting the hook, the sensitivity of this type of device depends heavily on the pr

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
  • Machine learning method and device based on intelligent fishing rod

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present application will be clearly and completely described below in conjunction with the embodiments of the present invention and the accompanying drawings.

[0045] Concrete this method comprises the following steps:

[0046] Step 1: Establish a fish database corresponding to different fishing scenarios, the steps include:

[0047] Step 1.1: For the pond area, according to different water depths, collect image data of different types of fish in the water and no fish in the water to establish the pond fish database A1, and then perform step 2.1;

[0048] Step 1.2: For the river area, collect different types of fish according to the upstream and downstream to establish the river fish database B1, and then perform step 2.2:

[0049] Step 2: Increase the robustness of the fish database, the steps include;

[0050] Step 2.1: For the image data sets in the pond fish database A1 and the river fish database B1, divide them into the pond fish training data set ATr1, the...

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 machine learning method based on an intelligent fishing rod, a terminal and a computer storage medium, and the method comprises the steps of building fish databases corresponding to different fishing scenes, increasing the robustness of the fish databases, building a machine learning fish image data classification model based on an expanded training data set, selecting the fishing scene in a fishing process, acquiring water area scene information, acquiring fish target information, and identifying a fish target. According to the invention, the fish condition images in the water are stably and accurately obtained, and the fish condition images in the water are classified and identified; the function that the intelligent fishing rod can obtain the fish condition in water and can also judge the type of the fish in water is realized.

Description

technical field [0001] The invention belongs to the field of outdoor sports, and in particular relates to an underwater fish image collection device based on a fishing rod and an automatic image classification method. Background technique [0002] Currently. The smart fishing rods on the market can use the acceleration sensor on the fishing line or the float to obtain the instantaneous downward pulling force generated when the fish bites the hook, so as to judge whether there is a fish biting the hook. Since its working principle is often based on whether the acceleration value collected by the acceleration sensor is greater than the preset threshold range to determine whether there is a fish biting the hook, the sensitivity of this type of device depends heavily on the preset threshold and the accuracy of the acceleration sensor. There is a large misjudgment rate in actual use. In addition, this type of device cannot judge whether it is fish or other sundries on the hook,...

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): G06K9/00G06K9/62G06N20/00
CPCG06N20/00G06V20/41G06F18/214G06F18/241
Inventor 娄毅
Owner 深圳市众凌汇科技有限公司
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