Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Object image detection method and object image detection device capable of improving classification performance

An image detection and object technology, applied in the field of object image detection that can improve the classification efficiency, can solve the problems of huge amount of calculation and long processing time.

Active Publication Date: 2015-06-10
AUTOMOTIVE RES & TESTING CENT
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The advantage of this strategy is that there is no need to use other assistive devices, but the disadvantage is that the calculation is huge and the processing time is long

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
  • Object image detection method and object image detection device capable of improving classification performance
  • Object image detection method and object image detection device capable of improving classification performance
  • Object image detection method and object image detection device capable of improving classification performance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Below in conjunction with accompanying drawing, structural principle and working principle of the present invention are specifically described:

[0029] For a preferred embodiment of the present invention, please refer to figure 1 As shown, an embedded system 10 is provided on the vehicle, and the embedded system 10 includes an image input unit 11, an image processing unit 12 and an output unit 13 connected in sequence, whereby the embedded system 10 The external image can be obtained by the image input unit 11, and the outline and type of obstacles in the image can be recognized by the image processing unit 12, and then the output unit 13 can issue a warning, so as to achieve the purpose of identifying obstacles around the vehicle.

[0030] The image input unit 11 is more than one CCD camera or more than one CMOS camera, and the image input unit 11 can be arranged at the front of the vehicle, the rear of the vehicle, the left side of the vehicle or the right side of th...

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 an object image detection method and an object image detection device capable of improving the classification performance. According to the object image detection method capable of improving the classification performance, an embedded system acquires image information, detects the image information to generate a circle-selection range of an obstacle as the initial contour of the obstacle, generates a correct contour of the obstacle by a Poisson vector active deformation contour algorithm based on the circle-selection range, using a multi-grid algorithm and a variable-size grid to improve the computing speed, and circle-selects a maximum boundary according to the correct contour of the obstacle to enable a classifier to identity the type of the obstacle. The object image detection method and the object image detection device of the invention have the advantage of being capable of improving complete circle-selection of dynamic objects and improving the accuracy of identification. The problem that an existing dynamic object detection and image recognition method has high probability of incorrect judgment, is time-consuming, and cannot be easily combined with an existing vehicle system is solved.

Description

technical field [0001] The invention relates to an object image detection method, in particular to an object image detection method capable of improving classification efficiency. Background technique [0002] The current dynamic object detection and recognition method used to identify various image formats can only circle some part of the obstacle in the image first, divide the part, and use the method of graphic comparison with multiple known graphics Therefore, the accuracy of its comparison and judgment ability will be affected by the integrity of the segmentation, that is, when the circled area is too small, each part is prone to produce discontinuous blocks and It is not easy to form a complete obstacle outline, resulting in a large increase in misjudgments and a long search time. [0003] If the aforementioned dynamic object detection and image recognition methods calculate the feature values ​​of each image in the segmented image and establish a logic mechanism to d...

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): G06K9/00G06K9/60
Inventor 杨志弘张国清
Owner AUTOMOTIVE RES & TESTING CENT
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com