Fish, shrimp and sea cucumber breeding precise feeding system and device based on target detection and tracking

A technology of target detection and participation in breeding, applied in fish farming, program control in sequence/logic controller, electrical program control, etc., can solve problems such as fixed feeding points, food waste, polluted water quality, etc., and achieve convenient and accurate Effects of feeding, improving training efficiency, and reducing stress

Active Publication Date: 2019-12-20
CHONGQING TECH & BUSINESS UNIV +1
View PDF13 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, in the aquaculture industry, three methods are usually used for breeding and feeding: one is the purely artificial method, and the workers observe through experience to decide whether to feed and the amount of feeding. Using this method requires aquaculture with rich work experience It can only be realized by personnel, and secondly, a large amount of manpower is required for feeding, which wastes too much manpower
The second is a semi-mechanical method. Workers decide whether to feed and the amount of feeding through experience observation, so as to control the feeding device for feeding. Although this solves the manpower problem of feeding, it still requires experienced farmers. Secondly, the feeding point of the feeding device is fixed and inconvenient to move
The third is the fully automatic method, which uses the feeding device to feed regularly and quantitatively. Because the position of the cultured fish is different when feeding, their food intake is also different, and the food intake of fish at different stages is also different. Feeding amount and feeding time are different each time. Using regular and quantitative feeding method will easily cause food waste, pollute water quality, or make fish starve for a long time, which is not conducive to fish growth.

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
  • Fish, shrimp and sea cucumber breeding precise feeding system and device based on target detection and tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] A precision feeding system for fish, shrimp and ginseng farming based on target detection and tracking, as shown in the attached figure 1 As shown, it includes a feeding training subsystem, a feeding identification subsystem, a feeding control subsystem, a database, and an image acquisition terminal. Several feeding videos are preset in the database. The eating video is a complete video of the breeding organisms from feeding to eating. The breeding organisms can be aquatic products such as fish, shrimp, and ginseng, or livestock such as pigs, chickens, and ducks. Mobs are defined as fish. The eating video is collected through the image acquisition terminal. The image acquisition terminal can use the existing video acquisition device (such as a camera), and the eating video is manually screened to select the complete eating process (the complete eating process includes the start of eating, eating, and the end of eating) The video of eating is taken as the eating video, ...

Embodiment 2

[0042]In the process of fish eating, there may be a situation where the fish eats too little food, which leads to the slow growth of the fish, or it may happen that the fish eats too much food, which causes the fish to grow too fast. If the fish grows too slowly, the economic benefits will also be reduced. If the fish grows too fast, the meat quality will be poor, which will also lead to a low value of a single product, which will affect the overall economic benefits. Therefore, during the breeding process, this should be avoided. Two situations.

[0043] The difference between this embodiment and the first embodiment is that the precise feeding system for fish, shrimp and ginseng farming based on target detection and tracking also includes a feeding control subsystem and a water flow control device.

[0044] The feeding duration calculation module is used to send the feeding duration outputted by the Markov chain model to the feeding control subsystem.

[0045] Feed control ...

Embodiment 3

[0053] In order to realize precise feeding, the present application also provides a precision feeding device for fish, shrimp and ginseng farming based on target detection and tracking (the device is the feeding device described in the above system), and the device uses Embodiment 1 or Embodiment 1. No. 2 records the precision feeding system for fish, shrimp and ginseng farming based on target detection and tracking, including the controller and the feeding machine body. The feeding machine body adopts the existing feeding device that can set the working time. On the feeder body. The controller is used to control the feeding of the feeding machine body, generate a feeding start signal, and send it to the feeding identification subsystem; it is also used to receive control information, and set the working time according to the control information.

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 relates to the technical field of feeding devices, in particular to a fish, shrimp and sea cucumber breeding precise feeding system and device based on target detection and tracking. Thesystem comprises a feeding training sub system used for acquiring eating videos and a training model and utilizing the eating videos for training the training model so as to generate a hunger analysis model, a feeding recognition sub system used for acquiring eating images during feeding and conducting image analysis on the eating images to generate hunger indexes, and a feeding control sub system used for generating feeding duration according to the hunger indexes and generating control information according to the feeding duration to control a feeding device to feed creatures. By adopting scheme, the feeding device can be controlled to feed the bred creatures according to the hunger states of the bred creatures, and precise feeding is achieved.

Description

technical field [0001] The invention relates to the technical field of feeding devices, in particular to a precise feeding system and device for fish, shrimp and ginseng breeding based on target detection and tracking. Background technique [0002] At present, in the aquaculture industry, three methods are usually used for breeding and feeding: one is the purely artificial method, and the workers observe through experience to decide whether to feed and the amount of feeding. Using this method requires aquaculture with rich work experience Only personnel can realize it, and secondly also need a large amount of manpower to carry out throwing and feeding, waste too much manpower. The second is a semi-mechanical method. Workers decide whether to feed and the amount of feeding through experience observation, so as to control the feeding device for feeding. Although this solves the manpower problem of feeding, it still requires experienced farmers. Secondly, the feeding point of ...

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): A01K61/80G05B19/04
CPCA01K61/80G05B19/04Y02A40/81
Inventor 申渝彭玉陈猷鹏王建辉郭智威
Owner CHONGQING TECH & BUSINESS 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

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