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

Target positioning method based on monocular vision

A monocular vision and target positioning technology, which is applied in the field of target positioning based on monocular vision, can solve the problems of poor positioning stability of the model, and achieve the effect of excellent positioning performance and easy installation and use

Active Publication Date: 2020-07-28
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generally speaking, such methods require a large number of datasets with labels of the target's true location, and in unfamiliar environments, the positioning stability of the model is poor

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
  • Target positioning method based on monocular vision
  • Target positioning method based on monocular vision
  • Target positioning method based on monocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] In this example, the camera is placed vertically, and multiple positionings are performed for different cars within 0 to 120 meters from the camera, and the attitude of the cars is kept vertical. In order to effectively detect targets distributed at different distances, three lenses with different focal lengths are selected in the example, and the specific parameters are shown in Table 1.

[0051] Table 1 Lens-related parameters (unit: pixel)

[0052]

[0053] Here, the performance of the method proposed in this experiment is verified by the control experiment I and the control experiment II. Among them, the control experiment I adopts the traditional monocular positioning model [1], the length, width and height of the target (car) are set to 4.75 meters, 1.93 meters and 1.8 meters respectively, and the control experiment II adopts the target positioning method based on constraints [2] . In our method, the Multi-bin[1] module is selected to return the target size a...

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 target positioning method based on monocular vision, and the method achieves the target detection and positioning ranging through a single RGB image, employs the deep learning technology to return to the target size, does not need to provide the prior information of a to-be-detected target in an interactive manner, and simplifies the whole positioning process. A traditional monocular positioning model is expanded to a three-dimensional space by introducing a scaling factor, a target positioning method based on an optimization theory is provided, a target positioning problem is converted into an optimization problem, and theoretically, high-precision target positioning can be realized for targets at different distances on the premise of a proper focal length; compared with binocular distance measurement, the method provided by the invention is theoretically not limited by a baseline, is easier to deploy in an outdoor complex environment, and is wider in application range; according to the method provided by the invention, a plurality of target objects on a single RGB image can be detected at the same time, and then a dynamic map of the whole scene is constructed.

Description

technical field [0001] The invention belongs to the technical field of target positioning, and in particular relates to a target positioning method based on monocular vision. Background technique [0002] Target positioning technology is one of the core issues of stereo vision, which is widely used in unmanned driving, aerial surveying and mapping, military reconnaissance and industrial inspection and other fields. As a branch of target positioning technology, target positioning technology based on monocular vision has received extensive attention in recent years. The corresponding research methods can be mainly divided into the following three categories: [0003] 1. Target positioning method based on traditional monocular positioning model. According to the principle of similar triangles, the traditional monocular positioning model believes that for a lens with a fixed focal length, when the projected size of the target is constant, the depth of the target is proportional...

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): G06T7/73G06T7/66G06T7/80G06T5/00
CPCG06T7/73G06T7/66G06T7/80G06T2207/10024G06T2207/20081G06T5/80
Inventor 邓方高峰姬艳鑫石翔李凌汉王向阳陈杰
Owner BEIJING INSTITUTE OF TECHNOLOGYGY