Method, device and system for positioning and attitude estimation of moving object
A gesture, multi-target technology, applied in the field of computer vision, can solve problems such as large amount of calculation, limitation, no somatosensory interaction, etc., to achieve the effect of small visible light impact, low implementation cost, and low computational consumption
Inactive Publication Date: 2018-03-06
蒋博 +1
View PDF4 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This kind of tracking has the advantage of a large range of movement, but the need to arrange a large number of tracking points in advance is the main reason hindering its introduction to the consumer market. In addition, their tracking only has head tracking and no somatosensory interaction, so that users still cannot interact with VR. The world conducts in-depth "communication"
The second main direction is self-positioning and natural gesture recognition without tracking point arrangement, but this algorithm has a huge amount of calculation and is easily affected by light. For example, positioning and tracking cannot be performed in a dark room. Greatly limit the application of this 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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0043] The present invention will be further described in detail below through specific embodiments in conjunction with the accompanying drawings.
[0044] figure 1 It is a flow chart of a method for real-time posture tracking and positioning of multiple targets based on illuminants according to an embodiment of the present invention.
[0045] S101. Waiting for a synchronization signal to start synchronization;
[0046] S102. Acquiring the tag ID in frame synchronization;
[0047] S103, judging whether the ID meets the requirements; if so, proceed to S104, otherwise return to S101;
[0048] S104, tracking mark;
[0049] S105, whether to follow the mark point; if yes, then return to S101; otherwise, enter S106;
[0050] S106. Estimating the pose of the tracked object.
[0051] The first step in the implementation is to allow the processing device to obtain the markers installed on the tracked object and their ID codes. This step is achieved through the timing synchronizat...
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
Login to View More Abstract
The present invention discloses a method for multi-target real-time attitude tracking and positioning based on luminous bodies. At least one image collector and devices and apparatuses such as at least one luminous body arranged on a tracked object are required by the method. The method comprises the steps that: exposure of the at least one image collector and the brightness of the at least one luminous body are synchronized, codes of each luminous body are determined by employing a method for distinguishing different luminous bodies in the luminous bodies, and each luminous body is tracked; after the codes of the at least one luminous body are determined, all the luminous bodies are input into an attitude solution algorithm according to a set sequence to perform solution, and attitude andposition information of moving objects provided with the luminous bodies is obtained; and if the tracking is lost, the synchronization is performed again, and codes of different luminous bodies are identified. The method can accurately track attitudes and moving tracks of moving objects at the same time.
Description
technical field [0001] The invention relates to the field of computer vision, in particular to a posture tracking and positioning method and device. Background technique [0002] There are three main optical-based tracking and positioning solutions currently on the market: OptiTrack, Lighthouse, and camera self-positioning. [0003] The OptiTrack solution should be the one with the highest accuracy rate and the most tracking targets among all optical positioning, but the site layout of this solution is complicated and the acquisition equipment is expensive. Before using the OptiTrack system, it is necessary to set up multiple dedicated cameras and perform complex calibration before data collection and calculation can be performed. Based on the site layout alone, this solution is not suitable for ordinary consumer users. [0004] The Lighthouse solution is currently the one with the largest range of use and the best user experience among the three major "PC-level" VRs. Howev...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/215G06T7/246H04N5/235
CPCG06T2207/10016H04N23/73
Inventor 蒋博李旭
Owner 蒋博