Unlock instant, AI-driven research and patent intelligence for your innovation.

Pig weight estimation method

A weight and fisheye image technology, applied in the field of deep learning, can solve the problems of high labor cost, heavy workload, and low accuracy, and achieve the effect of improving accuracy, improving weight estimation efficiency, and reducing errors

Pending Publication Date: 2021-10-19
深圳喜为智慧科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of high human cost input, heavy workload, low efficiency and low accuracy in the prior art, the purpose of the present invention is to provide a pig estimation system with low cost input, low workload, high efficiency and high accuracy. heavy method

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
  • Pig weight estimation method
  • Pig weight estimation method
  • Pig weight estimation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as figure 1 As shown, the present embodiment provides a pig weight estimation method, comprising the following steps:

[0056] Establishing a pig detection model based on deep learning includes the following steps:

[0057] Obtain a pig fisheye image dataset, and preprocess all the images in the pig fisheye image dataset to obtain a preprocessed pig fisheye image dataset;

[0058] Preprocessing includes geometric transformation processing, optical transformation processing, adding noise processing and normalization processing;

[0059] Geometric transformation processing enriches the position and scale of objects in the image, so as to satisfy the translation invariance and scale invariance of the model, such as translation, flipping, zooming and cropping, etc.; optical transformation processing increases images under different lighting and scenes, typically The operations include random perturbation of brightness, contrast, hue and saturation, and conversion bet...

Embodiment 2

[0095] like Figure 5 As shown, on the basis of Embodiment 1, this embodiment provides a pig weight estimation system, which is applied to the pig weight estimation method in Embodiment 1. The pig weight estimation system includes a camera unit and a data processing center, and the camera unit Communicate with the data processing center;

[0096] The camera unit is used to obtain the fisheye image of the pig to be detected in real time, and send the fisheye image of the pig to be detected to the data processing center;

[0097] The data processing center is used to establish a pig detection model based on deep learning, receive the fisheye image of the pig to be detected, input the fisheye image of the pig to be detected into the pig detection model for detection, and obtain all pig targets and their pixel areas , and obtain the pig weights of all pig targets according to the corresponding pixel area;

[0098] The camera unit includes a main control module, a camera and a co...

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 belongs to the technical field of deep learning, and discloses a pig weight estimation method which comprises the following steps: establishing a pig detection model based on deep learning; acquiring a fisheye image of the pig to be detected in real time; inputting the fisheye image of the pig to be detected into the pig detection model for detection to obtain all pig targets and pixel areas thereof; and obtaining pig weights of all pig targets according to the corresponding pixel areas. According to the invention, the problems of high labor cost input, large workload, low efficiency and low accuracy in the prior art are solved.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to a pig weight estimation method. Background technique [0002] With the development of the economy, people's demand for pork is getting higher and higher, and the output of pork is also getting higher and higher. At present, the most widely used breeding mode is large-scale pig raising, which has realized the transformation of the pig raising industry from a free-range model to a large-scale and intensive one. This breeding mode is characterized by high density and large number of pigs. Its advantages are saving land, increasing the number of heads per unit, suitable for intensive farming, and easy to count. It is clear at a glance that sows live in large pens. Statistical listing, not easy to make mistakes. [0003] In traditional technology, pigs are weighed manually. This method involves high labor costs, heavy workload and low efficiency. With the populariza...

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): G06K9/00G06K9/32G06K9/62G06K9/46G06N3/04G06N3/08G06N20/00G06T3/00G06T7/00G06T7/62
CPCG06T7/0002G06T7/62G06N3/08G06N20/00G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/20104G06N3/045G06F18/22G06F18/241G06F18/214G06T3/047
Inventor 柯海滨刘云明杨恒
Owner 深圳喜为智慧科技有限公司