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

Posture state estimation device and posture state estimation method

A state estimation and posture technology, applied in computing, computer components, image analysis, etc., can solve the problems of inability to distinguish multiple posture states of silhouettes, and inability to estimate human posture states with high precision

Active Publication Date: 2015-10-14
PANASONIC CORP
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] However, there is the following problem in the prior art: since it is impossible to distinguish multiple posture states with similar silhouettes, it is impossible to estimate the posture state of a person with high accuracy

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
  • Posture state estimation device and posture state estimation method
  • Posture state estimation device and posture state estimation method
  • Posture state estimation device and posture state estimation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0054] Embodiment 1 of the present invention is an example in which the present invention is applied to a device for estimating whether a captured posture state of a person matches a posture state designated by a user.

[0055] In the following description, a "part" refers to a collection of parts divided by joints in the human body. That is, the parts are, for example, the head, the shoulders, the right upper arm, the right forearm, the left upper arm, the left forearm, the right thigh, the right calf, the left thigh, and the left calf. In addition, the "part area" refers to an area that a certain part can occupy in an image, that is, a movable range of a part.

[0056]In addition, the "posture state" to be estimated refers to the postures of two or more parts to be paid attention to (hereinafter referred to as "parts of interest"). In addition, "posture" refers to a posture represented by information such as the positions of joints connecting the parts of interest in a two-...

Embodiment approach 2

[0183] Embodiment 2 of the present invention is an example in which a learning likelihood map is simultaneously generated in a posture state estimation device. The posture state estimating device according to the present embodiment performs a learning phase process of generating a learning likelihood map in addition to an estimation phase process of estimating a posture state.

[0184] Figure 17 It is a block diagram showing an example of the configuration of a posture state estimation device according to Embodiment 2 of the present invention, which is similar to that of Embodiment 1. figure 1 corresponding figure. right with figure 1 The same parts are given the same reference numerals, and descriptions thereof are omitted.

[0185] Such as Figure 17 As shown, the posture state estimation device 100a of this embodiment has a likelihood map generation unit 150a different from that of the first embodiment.

[0186] Image data acquiring section 130 and part area estimatin...

Embodiment approach 3

[0209] Figure 20 It is a block diagram showing the main configuration of the posture state estimation device according to Embodiment 3 of the present invention, and is similar to that of Embodiment 1. figure 1 The figure corresponding to the posture state estimation device 100. In addition, in Figure 20 in, for with figure 1 Common structural parts endowed with figure 1The same reference numerals are used, and explanations are omitted.

[0210] Figure 20 In the posture state estimation device 100b, except figure 1 In addition to the structure of , it also has a concave-convex map estimation unit 145b.

[0211] The unevenness map estimation unit 145b generates an unevenness map for each part. More specifically, the unevenness map estimation unit 145b inputs the estimated likelihood map and estimated image data from the likelihood map generation unit 150 . Then, unevenness map estimation section 145b generates an unevenness map based on the input information, and outp...

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

Disclosed is an orientation state estimation device capable of estimating with high accuracy the orientation state of a jointed body. An orientation state estimation device (100) estimates the orientation state of a body on the basis of image data of the body having multiple parts connected by joints. The device is provided with: a likelihood map generation unit (150) which, from the image data, for at least two parts of the jointed body, generates a likelihood map showing the plausibility distribution of where each part is most plausibly positioned; and an orientation state estimation unit (160) which, when a learning likelihood map, which is associated in advance with an orientation state, and an estimated likelihood map, which is generated on the basis of the image data, coincide to a high degree, estimates that the orientation state associated with said learning likelihood map is the orientation state of the object.

Description

technical field [0001] The present invention relates to a posture state estimation device and a posture state estimation method for estimating the posture state of an object based on image data obtained by photographing an object having a plurality of parts connected by joints. Background technique [0002] In recent years, research on human pose estimation based on image data of captured moving images has been actively conducted. This is because if it is possible to determine human behavior from moving images by computer analysis, it is possible to perform behavior analysis in various fields without relying on manpower. Examples of behavior analysis include abnormal behavior detection on the street, purchase behavior analysis in stores, work efficiency assistance in factories, and posture guidance in sports. [0003] Therefore, for example, Non-Patent Document 1 describes a technique for estimating a person's posture state based on image data captured by a monocular camera...

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 Patents(China)
IPC IPC(8): G06T7/20G06T1/00G06T7/00
CPCG06K9/00335G06T7/0048G06T2207/30164G06T7/77G06V40/20
Inventor 川口京子田靡雅基丸谷健介里雄二藤田光子
Owner PANASONIC CORP