Bird small target detection method based on density map estimation

A small target detection and density map technology, applied in the field of bird small target detection based on density map estimation, can solve the problems of difficulty, small scale, and decreased detection effect, and achieve the effect of reducing dependence and reducing the work of manual annotation.

Inactive Publication Date: 2019-09-24
PEKING UNIV SHENZHEN GRADUATE SCHOOL
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The small scale of bird individuals, overlapping occlusions and other issues lead to the loss of effective feature information in the image; at the same time, a large number of densely distributed small bird targets bring difficulties

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
  • Bird small target detection method based on density map estimation
  • Bird small target detection method based on density map estimation
  • Bird small target detection method based on density map estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0036] The present invention provides a small bird target detection method based on density map estimation, which utilizes the example-based learning method to learn the density map, realizes small bird target detection under a small-sample training set, reduces the dependence on the training set scale, and at the same time The work of manually labeling a large number of tedious training samples is reduced; the method of the invention can better match the shape and outline of small targets, and the detection accuracy is higher.

[0037] The method of the present invention can be applied to a PC (Personal computer), and can also be applied to mobile terminal devices such as mobile phones and tablet computers, which is not limited herein.

[0038] The method of the invention includes a density map esti...

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 a bird small target detection method based on density map estimation, and relates to the ecological monitoring technology based on computer vision. The bird small target detection method comprises a training stage and a detection stage, including learning a density map by utilizing a method based on instance learning, estimating the position of a bird small target on the density map through a sliding window and a method for solving a local extreme value in the window, carrying out super-pixel-based bounding box estimation, and realizing bird small target detection under a small sample training set. The bird small target detection method reduces the dependence on the scale of the training set while reducing the manual marking work of a large number of tedious training samples, can preferably match the shape and the contour of a small target, and is high in the detection precision.

Description

technical field [0001] The invention belongs to the field of computer vision technology and target detection technology, and relates to an ecological monitoring technology based on computer vision, in particular to a small bird target detection method based on density map estimation. Background technique [0002] Birds are one of the most studied and frequently investigated animal groups due to their wide distribution, diverse species, and easy identification. They are also a group of animals that are extremely sensitive to habitat changes and environmental changes. The composition, quantity, diversity and community characteristics of bird species can directly reflect the suitability of habitats, the health of ecosystems and biodiversity, the degree of disturbance of human activities on ecosystems, and the impact of land use and landscape changes on ecosystems. degree, and the quality of the regional ecological environment. So far, the field monitoring stations mainly follo...

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): G06K9/62
CPCG06F18/28G06F18/23G06F18/214
Inventor 邹月娴周小群
Owner PEKING UNIV SHENZHEN GRADUATE SCHOOL
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