A fast classification and recognition method based on small moving objects

A technology of fast classification and recognition methods, applied in the field of image processing, can solve the difficulty of extracting the periodicity of the angle of the observed target, the poor classification effect of multiple periodic and multiple non-periodic moving targets, and the periodicity of the target Complicated calculations and other issues to achieve the effect of ensuring classification accuracy, low time complexity, and improving robustness

CN109344800AActive Publication Date: 2019-02-15NANCHANG INST OF TECH
6 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2019-02-15

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a fast classification and recognition method based on small moving objects, According to the characteristics of small target, the contour of moving target is extracted first, and then the contour is fitted with rectangle and ellipse. The shape describing parameters of contour, rectangle and ellipse are combined to form a new robust shape describing operator. Finally, a treeclassifier is designed to classify the moving objects. The moving objects are divided into three categories: pedestrians, cyclists and automobiles. The tree classifier not only has low time complexity, but also can improve the robustness in different situations on the premise of guaranteeing the accuracy of classification.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of image processing, in particular to a fast classification and recognition method based on small moving objects. Background technique

[0002] The ultimate goal of the video surveillance system is to analyze and understand the behavior of moving objects in the scene, and it has a wide range of applications in intelligent security monitoring, security systems, traffic road supervision systems, etc. For example: in an intelligent security monitoring system, it is necessary to analyze and judge the behavior of moving objects appearing in the monitoring scene. First, it is necessary to classify and identify the detected moving objects, and adopt different processing methods for different types of moving objects. . For example: when the target "person" enters a sensitive area of ​​a specific scene, an alarm occurs; when a "car" enters a specific area of ​​the scene, tracking, license plate recognition, speed me...

Examples

Embodiment Construction

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0019] refer to figure 1 , the embodiment of the present invention provides a fast classification and recognition method based on small moving objects, the method includes the following steps:

[0020] Step 1, extract the contours of objects, each contour corresponds to a detected object. The extracted contours are divided into two layers: the outer boundary of the connected domain and the inner boundary of the hole. The connected domain analysis of the targ...