CN110889382A - Virtual image rendering method and device, electronic equipment and storage medium - Google Patents
Virtual image rendering method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110889382A CN110889382A CN201911203909.6A CN201911203909A CN110889382A CN 110889382 A CN110889382 A CN 110889382A CN 201911203909 A CN201911203909 A CN 201911203909A CN 110889382 A CN110889382 A CN 110889382A
- Authority
- CN
- China
- Prior art keywords
- target object
- gesture
- hand
- region
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009877 rendering Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000006399 behavior Effects 0.000 claims abstract description 73
- 238000012545 processing Methods 0.000 claims abstract description 43
- 230000009471 action Effects 0.000 claims abstract description 32
- 230000008921 facial expression Effects 0.000 claims abstract description 32
- 210000000746 body region Anatomy 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims description 56
- 238000004590 computer program Methods 0.000 claims description 15
- 230000003542 behavioural effect Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 18
- 238000004891 communication Methods 0.000 description 10
- 230000003993 interaction Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 5
- 210000003811 finger Anatomy 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 210000003128 head Anatomy 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 210000004247 hand Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 210000004932 little finger Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present disclosure relates to a method and apparatus for rendering an avatar, an electronic device, and a storage medium, the method including: detecting a video frame in an acquired video stream, and determining an object region of a target object in the video frame, wherein the object region comprises a body region, a face region and a hand region; processing an object region of the target object, and determining a first behavior gesture of the target object, wherein the first behavior gesture comprises a body gesture, a facial expression and a hand gesture of the target object; and rendering a preset virtual image according to the first behavior gesture of the target object. The embodiment of the disclosure can realize real-time driving of the whole body action change of the virtual image.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for rendering an avatar, an electronic device, and a storage medium.
Background
With the development of science and technology, the performance of the terminal is rapidly improved, so that powerful technical support is provided for the generation and development of more and more applications. In order to increase the stickiness of the user to the application, a common service is to provide a personalized and humanized interaction manner for the user to improve the interaction interest of the user.
The current interaction mode is single, interaction is generally realized through touch operation, keyboard operation, mouse operation and the like, hands cannot be liberated, and interaction experience is tedious.
Disclosure of Invention
The utility model provides a real-time whole body action that drives the avatar changes, can enrich the avatar rendering technical scheme of the interactive mode of target object and avatar.
According to an aspect of the present disclosure, there is provided an avatar rendering method, including:
detecting a video frame in an acquired video stream, and determining an object region of a target object in the video frame, wherein the object region comprises a body region, a face region and a hand region;
processing an object region of the target object, and determining a first behavior gesture of the target object, wherein the first behavior gesture comprises a body gesture, a facial expression and a hand gesture of the target object;
and rendering a preset virtual image according to the first behavior gesture of the target object.
In one possible implementation, the processing the object region of the target object and determining the first behavior pose of the target object includes:
carrying out human body detection on the body area in the video frame to obtain a group of first key point information corresponding to the body part of the target object under a first action posture;
and determining the rotation quaternion information corresponding to the body part according to the group of first key point information.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object includes:
and controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the body part.
In one possible implementation, the processing the object region of the target object and determining the first behavior pose of the target object includes:
performing face detection on the face area in the video frame to obtain a group of second key point information corresponding to the target object face under the first action posture;
and determining the expression base coefficient corresponding to each expression base according to the group of second key point information.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object includes:
and controlling the facial expression in the virtual image to be transformed according to the expression base coefficient.
In one possible implementation, the processing the object region of the target object and determining the first behavior pose of the target object includes:
performing gesture detection on a hand area in the video frame to obtain a group of third key point information and/or gesture information corresponding to the target object hand in the first behavior posture;
and determining rotation quaternion information corresponding to each part of the hand according to a group of third key point information and/or gesture information corresponding to the hand.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object includes:
and controlling each part of the hand of the virtual image to rotate according to the rotation quaternion information corresponding to each part of the hand.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object includes:
determining position information and rotation quaternion information of collision bodies arranged at each part of the virtual image body under the first action posture;
and under the condition that the position information of the colliders of all the parts is not overlapped, controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the first behavior posture.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object further includes:
under the condition that the position information of the collision bodies of all the parts is overlapped, adjusting the position information and/or the rotation quaternion information of the overlapped parts to obtain adjusted rotation quaternion information;
and controlling the body part in the virtual image to rotate according to the adjusted rotating quaternion information so as to prevent the position information of the collision body of each part from being overlapped.
In a possible implementation manner, the detecting a video frame in the captured video stream and determining an object region of a target object in the video frame includes at least one of the following methods:
performing human body detection on a video frame of the acquired video stream, and determining a first key point corresponding to the face and a second key point corresponding to the hand of a target object in the video frame;
determining a face area according to the size of the face area corresponding to the face and the first key point;
and determining the hand area according to the hand area size corresponding to the hand and the second key point.
In one possible implementation, a video frame in the video stream includes color information and depth information.
According to an aspect of the present disclosure, there is provided an avatar rendering apparatus including:
the detection module is used for detecting a video frame in the acquired video stream and determining an object region of a target object in the video frame, wherein the object region comprises a body region, a face region and a hand region;
the processing module is used for processing the object area of the target object and determining a first behavior gesture of the target object, wherein the first behavior gesture comprises a body gesture, a facial expression and a hand gesture of the target object;
and the rendering module is used for rendering a preset virtual image according to the first behavior gesture of the target object.
In one possible implementation manner, the processing module is further configured to:
carrying out human body detection on the body area in the video frame to obtain a group of first key point information corresponding to the body part of the target object under a first action posture;
and determining the rotation quaternion information corresponding to the body part according to the group of first key point information.
In one possible implementation, the rendering module is further configured to:
and controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the body part.
In one possible implementation manner, the processing module is further configured to:
performing face detection on the face area in the video frame to obtain a group of second key point information corresponding to the target object face under the first action posture;
and determining the expression base coefficient corresponding to each expression base according to the group of second key point information.
In one possible implementation, the rendering module is further configured to:
and controlling the facial expression in the virtual image to be transformed according to the expression base coefficient.
In one possible implementation manner, the processing module is further configured to:
performing gesture detection on a hand area in the video frame to obtain a group of third key point information and/or gesture information corresponding to the target object hand in the first behavior posture;
and determining rotation quaternion information corresponding to each part of the hand according to a group of third key point information and/or gesture information corresponding to the hand.
In one possible implementation, the rendering module is further configured to:
and controlling each part of the hand of the virtual image to rotate according to the rotation quaternion information corresponding to each part of the hand.
In one possible implementation, the rendering module is further configured to:
determining position information and rotation quaternion information of collision bodies arranged at each part of the virtual image body under the first action posture;
and under the condition that the position information of the colliders of all the parts is not overlapped, controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the first behavior posture.
In one possible implementation, the rendering module is further configured to:
under the condition that the position information of the collision bodies of all the parts is overlapped, adjusting the position information and/or the rotation quaternion information of the overlapped parts to obtain adjusted rotation quaternion information;
and controlling the body part in the virtual image to rotate according to the adjusted rotating quaternion information so as to prevent the position information of the collision body of each part from being overlapped.
In a possible implementation manner, the detection module is further configured to at least one of:
performing human body detection on a video frame of the acquired video stream, and determining a first key point corresponding to the face and a second key point corresponding to the hand of a target object in the video frame;
determining a face area according to the size of the face area corresponding to the face and the first key point;
and determining the hand area according to the hand area size corresponding to the hand and the second key point.
In one possible implementation, a video frame in the video stream includes color information and depth information.
According to an aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.
According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.
In this way, the video frame of the acquired video stream can be detected, the object region including the body region, the face region and the hand region of the target object in the video frame is determined, the body region, the face region and the hand region are processed respectively, the first behavior posture including the body posture, the facial expression and the hand gesture of the target object can be obtained, and the rendering of the virtual image is controlled through the body posture, the facial expression and the hand gesture of the target object. According to the avatar rendering method and device, the electronic device and the storage medium provided by the disclosure, the display of the avatar can be controlled through the first behavior gesture of the target object, the whole body action change of the avatar is driven in real time, and the interaction mode of the target object and the avatar can be enriched.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.
Fig. 1 shows a flow diagram of an avatar rendering method according to an embodiment of the present disclosure;
FIG. 2 shows a schematic diagram of an avatar rendering method according to an embodiment of the present disclosure;
FIG. 3 shows a block diagram of an avatar rendering apparatus according to an embodiment of the present disclosure;
FIG. 4 shows a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure;
fig. 5 illustrates a block diagram of an electronic device 1900 in accordance with an embodiment of the disclosure.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.
Fig. 1 shows a flowchart of an avatar rendering method according to an embodiment of the present disclosure, which may be performed by an electronic device such as a terminal device or a server, the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like, and the method may be implemented by a processor calling computer readable instructions stored in a memory. Alternatively, the method may be performed by a server.
As shown in fig. 1, the avatar rendering method may include:
in step S11, a video frame in the captured video stream is detected, and an object region of a target object in the video frame is determined, where the object region includes a body region, a face region, and a hand region.
When the avatar is rendered and driven according to the video frame, if feature point detection is directly performed on the video frame to obtain each body part, facial expression and hand gesture of the target object, high computational effort is required, so that the feature point detection efficiency is low, and further the avatar driving is delayed, that is, the avatar cannot move synchronously with the target object in the video frame. The problem is not solved, the present disclosure obtains the object regions (body region, face region and hand region) of the target object after detecting the video frame, and performs feature point detection on each object region, so as to reduce computational effort, improve feature point detection efficiency, and implement synchronous action of the virtual image and the target object in the video frame.
For example, a video stream may be acquired in real time, and a video frame corresponding to the current time in the acquired video stream may be detected to determine a body region corresponding to the body of the target object, a face region corresponding to the face, and a hand region corresponding to the hand in the video frame.
In a possible implementation manner, a video frame in the video stream may include color information and depth information, where the color information may include information collected by an RGB (red green blue color mode) camera, and the depth information may include information collected by a TOF (Time of flight ranging) camera.
In a possible implementation manner, the detecting a video frame in the captured video stream and determining an object region of the target object in the video frame may include at least one of the following methods:
performing human body detection on a video frame of the acquired video stream, and determining a first key point corresponding to the face and a second key point corresponding to the hand of a target object in the video frame;
determining a face area according to the size of the face area corresponding to the face and the first key point;
and determining the hand area according to the hand area size corresponding to the hand and the second key point.
For example, the position information of a first key point corresponding to the face of a target object in a video frame can be determined by performing human body detection on the video frame, and then an area corresponding to a preset face area size is determined as a face area in the video frame by taking the position information of the first key point as a center; similarly, the position information of the second key point corresponding to the hand of the target object in the video frame is determined, and then the area corresponding to the preset size of the hand area is determined as the hand area by taking the position information of the second key point as the center in the video frame, wherein the values of the preset size of the face area and the preset size of the hand area can be set according to the requirements, and the disclosure does not limit the values.
In step S12, the object region of the target object is processed to determine a first behavioral pose of the target object, where the first behavioral pose includes a body pose, a facial expression, and a hand gesture of the target object.
For example, the first behavioral gesture may be a gesture presented by a limb, a facial expression, and a hand gesture of the target object. After the body area, the face area, and the hand area of the target object are determined, the body area, the face area, and the hand area of the target object may be detected, respectively, to obtain a first behavior pose of the target object. For example: the body detection is carried out on the body area to obtain the body posture information of the target object, the face detection is carried out on the face area to obtain the facial expression information of the target object, the hand detection is carried out on the hand area to obtain the hand gesture information of the target object, and therefore the body posture, the facial expression and the hand gesture of the target object can be obtained simultaneously under the condition of reducing computing power by respectively detecting different object areas.
In step S13, a preset avatar is rendered according to the first behavior pose of the target object.
For example, a preset avatar may be rendered according to a first behavior pose of the target object, such as: the body posture of the avatar is made to be consistent with the body posture of the target object, the facial expression of the avatar is made to be consistent with the facial expression of the target object, and the hand gesture of the avatar is made to be consistent with the hand gesture of the target object, so that the avatar presents the first behavior posture of the target object, or the posture presented by the avatar is made to be close to the first behavior posture of the target object.
In this way, the video frame of the acquired video stream can be detected, the object region including the body region, the face region and the hand region of the target object in the video frame is determined, the body region, the face region and the hand region are processed respectively, the first behavior posture including the body posture, the facial expression and the hand gesture of the target object can be obtained, and the rendering of the virtual image is controlled through the body posture, the facial expression and the hand gesture of the target object. According to the virtual image rendering method provided by the disclosure, the display of the virtual image can be controlled through the first action posture of the target object, the whole body action change of the virtual image is driven in real time, and the interaction mode of the target object and the virtual image can be enriched.
In a possible implementation manner, the processing the object region of the target object and determining the first behavior posture of the target object may include:
carrying out human body detection on the body area in the video frame to obtain a group of first key point information corresponding to the body part of the target object under a first action posture;
and determining the rotation quaternion information corresponding to the body part according to the group of first key point information.
For example, after the body region of the video frame is determined, human body detection may be performed on the body region in the video frame to obtain a set of first keypoint information of the body part of the target object, and the set of first keypoint information may be cached (the body detection result of the video frame at the next time may be optimized by the cached first keypoint information). The set of first keypoint information may include at least location information and confidence level of each first keypoint. For example, a pre-trained neural network for human body detection may be used to perform human body detection on a body region of a video frame to obtain a set of first keypoint information, where the set of first keypoint information includes first keypoint information corresponding to each body part, and the method for human body detection is not specifically limited in the present disclosure.
After determining a set of first key point information, for a plurality of first key points corresponding to any body part (for example, body parts such as a left arm, a right arm, a head, a left leg, a right leg, and a waist), rotation quaternion information corresponding to the body part can be determined according to the first key point information corresponding to the plurality of first key points. For example: in a group of first key point information obtained by human body detection, the first key points 1 to 5 correspond to the shanks of the target object, and the rotation quaternion information of the shanks of the target object can be obtained according to the first key point information corresponding to the five first key points of the first key points 1 to 5. The rotation quaternion information can be used for describing the rotation amplitude of the body part in the space, and the body part corresponding to the virtual image can be rotated according to the rotation quaternion information of the body part.
In one possible implementation, when detecting the first keypoint information of the target object in the video frame, the first keypoint of the video frame may be predicted by a preset number of video frames before the video frame, for example: the human body detection can be performed on the video frames through a pre-trained neural network for human body detection, wherein the input of the neural network is a preset number of video frames before the video frames and the video frames, and the output is a group of first key point information of the body parts of the video frames.
Therefore, the problems of key point jumping and shaking of continuous frames can be reduced, and the smoothness and stability of virtual image actions can be improved.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object may include:
and controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the body part.
For example, when the avatar currently presents the second behavior gesture (the gesture presented before the avatar is transformed into the first behavior gesture), the body part of the avatar may be rotated by a corresponding angle according to the rotation quaternion information, so that the avatar may be synchronously transformed from the body gesture of the second behavior gesture into the body gesture of the first behavior gesture when the body gesture of the target object is transformed from the body gesture of the second behavior gesture into the body gesture of the first behavior gesture.
In a possible implementation manner, the processing the object region of the target object and determining the first behavior posture of the target object may include:
performing face detection on the face area in the video frame to obtain a group of second key point information corresponding to the target object face under the first action posture;
and determining the expression base coefficient corresponding to each expression base according to the group of second key point information.
For example, after determining the face region of the video frame, face detection may be performed on the face region in the video frame to obtain a set of second keypoint information of the face of the target object. The group of second keypoint information at least includes position information and confidence corresponding to each second keypoint. For example, a pre-trained neural network for face detection may be used to perform face detection on a face region of a video frame to obtain second keypoint information corresponding to the facial expression bases, and the face detection method is not specifically limited in the present disclosure.
After determining a set of second keypoint information, at least one expression base of the face and an expression base coefficient corresponding to the at least one expression base may be determined according to a plurality of second keypoint information, where the expression base coefficient may be used to describe a variation amplitude of the expression base, for example: the extent to which the eyes are open, the extent to which the corners of the mouth are raised, etc. For example: in a group of second keypoint information obtained by face detection, the corresponding expression base can be determined to be the open eye and the expression base coefficient (the amplitude of the open eye) according to 10 pieces of second keypoint information corresponding to the second keypoints 1 to 10. And further, the expression bases corresponding to the virtual image are transformed according to the expression base coefficients corresponding to the expression bases.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object may include:
and controlling the facial expression in the virtual image to be transformed according to the expression base coefficient.
For example, when the avatar currently presents the second behavior gesture, the expression base of the avatar may be adjusted according to the expression base coefficient, so that the facial expression of the target object is changed from the facial expression of the second behavior gesture to the facial expression of the first behavior gesture, the avatar may be simultaneously changed from the facial expression of the second behavior gesture to the facial expression of the first behavior gesture, for example: the target subject's eyes are transformed from half-open to full-open, and the avatar synchronously transforms the eyes from half-open to full-open.
In a possible implementation manner, the processing the object region of the target object and determining the first behavior posture of the target object may include:
performing gesture detection on a hand area in the video frame to obtain a group of third key point information and/or gesture information corresponding to the target object hand in the first behavior posture;
and determining rotation quaternion information corresponding to each part of the hand according to a group of third key point information and/or gesture information corresponding to the hand.
For example, after determining the hand region of the video frame, gesture detection may be performed on the hand region in the video frame to obtain a set of third key point information and/or gesture information corresponding to each joint of the hand of the target object (the gesture information may be a gesture posture presented by the hand, for example, a gesture such as a gesture of V, heart, etc.). The set of third keypoint information may include at least position information and confidence level of the third keypoint. For example, a pre-trained neural network for gesture detection may be used to perform gesture detection on a hand region of a video frame to obtain third key point information and/or gesture information corresponding to each joint of a hand part, and the gesture detection method is not specifically limited in the present disclosure.
After determining a set of third key point information, for a third key point corresponding to a plurality of joints of any hand part (for example, any hand part such as thumb, index finger, middle finger, ring finger, little finger, palm, etc.), rotation quaternion information corresponding to the hand part can be determined according to the third key point information corresponding to the plurality of third key points. For example: in a group of third key point information obtained by gesture detection, the third key points 1 to 3 correspond to the index finger of the target object, and then the rotation quaternion information of the index finger of the target object can be obtained according to the third key point information corresponding to the three third key points of the third key points 1 to 3, or after the gesture information is determined, the rotation quaternion information corresponding to the gesture information (each gesture information corresponds to a group of fixed rotation quaternion information) can be determined. The rotation quaternion information can be used for describing the rotation angle of the hand part in the space, and then the hand part corresponding to the virtual image is rotated according to the rotation quaternion information of the hand part.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object may include:
and controlling each part of the hand of the virtual image to rotate according to the rotation quaternion information corresponding to each part of the hand.
For example, the avatar currently presents the second behavior gesture, and can rotate each part of the hand of the avatar by a corresponding angle according to the rotation quaternion information corresponding to each part of the hand, so that when the hand gesture of the target object is changed from the hand gesture of the second behavior gesture to the hand gesture of the first behavior gesture, the avatar is synchronously changed from the hand gesture of the second behavior gesture to the hand gesture of the first behavior gesture.
In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object may further include:
determining the position information of collision bodies arranged on each part of the body of the virtual image under the first action posture;
and under the condition that the position information of the colliders of all the parts is not overlapped, controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the first behavior posture.
For example, collision volumes may be provided for various parts of the body of the avatar, such as: collision bodies are respectively arranged on the head, the left hand, the right hand, the left foot, the right foot and the abdomen of the virtual image. The collision body can be a model for performing collision detection instead of the virtual image, and whether at least two parts of the virtual image collide exist can be detected through the collision bodies arranged on all parts of the body of the virtual image, so that the phenomena of body puncture and the like are prevented, and the rendered virtual image is more real.
After the first behavior posture is determined, the position information of the virtual object after rendering each part of the body may be determined based on the rotation quaternion information corresponding to the first behavior posture, and the position information of the collision body of each part of the body may be determined when the virtual object is in the first behavior posture based on the position information after rendering each part of the body. Under the condition that the position information of the collision bodies of all the parts is not overlapped, the body parts in the virtual image can be controlled to rotate directly according to the rotation quaternion information corresponding to the first action posture, so that the virtual image presents the first action posture. In a possible implementation manner, the rendering a preset avatar according to the first behavior gesture of the target object may further include:
under the condition that the position information of the collision bodies of all the parts is overlapped, adjusting the position information and/or the rotation quaternion information of the overlapped parts to obtain adjusted rotation quaternion information;
and controlling the body part in the virtual image to rotate according to the adjusted rotating quaternion information so as to prevent the position information of the collision body of each part from being overlapped.
When the position information of the collision bodies of the respective portions is overlapped, the position information of the overlapped portion is adjusted, and the adjusted rotational quaternion information is determined again based on the adjusted position information, or the rotational quaternion information may be directly adjusted to obtain the adjusted rotational quaternion information. And controlling the body part in the virtual image to rotate according to the adjusted rotating quaternion information, so that the position information of the collision body of each adjusted part is not overlapped, and the posture presented by the virtual image is close to the posture of the first behavior.
Illustratively, when the display of the virtual image is rendered through the first action gesture, the virtual image can be rendered by directly performing rendering on the body part without overlapping according to the rotating quaternion information corresponding to the body part in the first action gesture, so that the body part is transformed from the second action posture before the transformation is not generated into the first action posture, adjusting the rotational quaternion information corresponding to the overlapped body part (for example, adjusting the rotational quaternion information corresponding to the body part in the second behavior posture corresponding to the previous frame of video frame), rendering according to the adjusted rotational quaternion information, so that the collider of the body part does not overlap with the colliders of other body parts (for example, the second action posture is kept unchanged), and therefore, the virtual image mold penetrating effect can be avoided (for example, the effect of passing a hand through the chest can be avoided).
At the same time, depending on the actual probability of two colliders, it is not necessary to compare the position information of the colliders with respect to the part of the body where no collision is possible, for example: the head and the foot are unlikely to collide, so that comparison of position information of collision bodies of the head and the foot is not necessary, which can reduce calculation time.
In order that those skilled in the art will better understand the embodiments of the present disclosure, the following description illustrates the embodiments of the present disclosure by way of specific examples:
as shown in fig. 2, the video frames may be acquired through an RGB camera and a TOF camera in response to the acquisition instruction of the image information, and human body detection may be performed on the video frames including color information and depth information corresponding to the current time to determine a body region, a face region, and a hand region of the target object in the video frames, and human body detection may be performed on the body region to obtain a set of first key point information of the body part, and obtain rotational quaternion information corresponding to the body posture according to the set of first key point information of the body; performing face detection on the facial area to obtain a group of second key point information of the face, and obtaining an expression base coefficient corresponding to the facial expression according to the group of second key point information of the face; and performing gesture detection on the hand region to obtain a group of third key point information and/or gesture information of the hand, and obtaining rotation quaternion information corresponding to each part of the hand according to the group of third key point information and/or gesture information of the hand. Rendering the body posture of the virtual image through the rotating quaternion information corresponding to the body posture, and rendering the facial expression of the virtual image through the expression base coefficient corresponding to the facial expression; and rendering the hand gesture of the virtual image through the rotating quaternion information corresponding to each part of the hand, so that the displayed virtual image and the displayed gesture of the target object are the same.
It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.
In addition, the present disclosure also provides an avatar rendering apparatus, an electronic device, a computer-readable storage medium, and a program, which can be used to implement any one of the avatar rendering methods provided by the present disclosure, and the corresponding technical solutions and descriptions and corresponding records in the methods section are not repeated.
Fig. 3 illustrates a block diagram of an avatar rendering apparatus according to an embodiment of the present disclosure, the avatar rendering apparatus including, as shown in fig. 3:
the detection module 301 may be configured to detect a video frame in an acquired video stream, and determine an object region of a target object in the video frame, where the object region includes a body region, a face region, and a hand region;
a processing module 302, configured to process an object region of the target object, and determine a first behavioral pose of the target object, where the first behavioral pose includes a body pose, a facial expression, and a hand gesture of the target object;
the rendering module 303 may be configured to render a preset avatar according to the first behavior gesture of the target object.
In this way, the video frame of the acquired video stream can be detected, the object region including the body region, the face region and the hand region of the target object in the video frame is determined, the body region, the face region and the hand region are processed respectively, the first behavior posture including the body posture, the facial expression and the hand gesture of the target object can be obtained, and the rendering of the virtual image is controlled through the body posture, the facial expression and the hand gesture of the target object. According to the virtual image rendering device provided by the disclosure, the display of the virtual image can be controlled through the first action posture of the target object, the whole body action change of the virtual image is driven in real time, and the interaction mode of the target object and the virtual image can be enriched.
In a possible implementation manner, the processing module may be further configured to:
carrying out human body detection on the body area in the video frame to obtain a group of first key point information corresponding to the body part of the target object under a first action posture;
and determining the rotation quaternion information corresponding to the body part according to the group of first key point information.
In a possible implementation manner, the rendering module may be further configured to:
and controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the body part.
In a possible implementation manner, the processing module may be further configured to:
performing face detection on the face area in the video frame to obtain a group of second key point information corresponding to the target object face under the first action posture;
and determining the expression base coefficient corresponding to each expression base according to the group of second key point information.
In a possible implementation manner, the rendering module may be further configured to:
and controlling the facial expression in the virtual image to be transformed according to the expression base coefficient.
In a possible implementation manner, the processing module may be further configured to:
performing gesture detection on a hand area in the video frame to obtain a group of third key point information and/or gesture information corresponding to the target object hand in the first behavior posture;
and determining rotation quaternion information corresponding to each part of the hand according to a group of third key point information and/or gesture information corresponding to the hand.
In a possible implementation manner, the rendering module may be further configured to:
and controlling each part of the hand of the virtual image to rotate according to the rotation quaternion information corresponding to each part of the hand.
In a possible implementation manner, the rendering module may be further configured to:
determining position information and rotation quaternion information of collision bodies arranged at each part of the virtual image body under the first action posture;
and under the condition that the position information of the colliders of all the parts is not overlapped, controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the first behavior posture.
In a possible implementation manner, the rendering module may be further configured to:
under the condition that the position information of the collision bodies of all the parts is overlapped, adjusting the position information and/or the rotation quaternion information of the overlapped parts to obtain adjusted rotation quaternion information;
and controlling the body part in the virtual image to rotate according to the adjusted rotating quaternion information so as to prevent the position information of the collision body of each part from being overlapped.
In a possible implementation manner, the detection module may be further configured to at least one of:
performing human body detection on a video frame of the acquired video stream, and determining a first key point corresponding to the face and a second key point corresponding to the hand of a target object in the video frame;
determining a face area according to the size of the face area corresponding to the face and the first key point;
and determining the hand area according to the hand area size corresponding to the hand and the second key point.
In one possible implementation, a video frame in the video stream includes color information and depth information.
In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.
Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium.
An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.
The disclosed embodiments also provide a computer program product comprising computer readable code, which when run on a device, a processor in the device executes instructions for implementing the avatar rendering method as provided in any of the above embodiments.
The embodiments of the present disclosure also provide another computer program product for storing computer readable instructions, which when executed, cause a computer to perform the operations of the avatar rendering method provided in any of the above embodiments.
The electronic device may be provided as a terminal, server, or other form of device.
Fig. 4 illustrates a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal.
Referring to fig. 4, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.
The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.
The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.
Fig. 5 illustrates a block diagram of an electronic device 1900 in accordance with an embodiment of the disclosure. For example, the electronic device 1900 may be provided as a server. Referring to fig. 5, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.
The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.
The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. An avatar rendering method, comprising:
detecting a video frame in an acquired video stream, and determining an object region of a target object in the video frame, wherein the object region comprises a body region, a face region and a hand region;
processing an object region of the target object, and determining a first behavior gesture of the target object, wherein the first behavior gesture comprises a body gesture, a facial expression and a hand gesture of the target object;
and rendering a preset virtual image according to the first behavior gesture of the target object.
2. The method of claim 1, wherein the processing the object region of the target object to determine the first behavioral pose of the target object comprises:
carrying out human body detection on the body area in the video frame to obtain a group of first key point information corresponding to the body part of the target object under a first action posture;
and determining the rotation quaternion information corresponding to the body part according to the group of first key point information.
3. The method of claim 1, wherein the processing the object region of the target object to determine the first behavioral pose of the target object comprises:
performing face detection on the face area in the video frame to obtain a group of second key point information corresponding to the target object face under the first action posture;
and determining the expression base coefficient corresponding to each expression base according to the group of second key point information.
4. The method of claim 1, wherein the processing the object region of the target object to determine the first behavioral pose of the target object comprises:
performing gesture detection on a hand area in the video frame to obtain a group of third key point information and/or gesture information corresponding to the target object hand in the first behavior posture;
and determining rotation quaternion information corresponding to each part of the hand according to a group of third key point information and/or gesture information corresponding to the hand.
5. The method according to any one of claims 1 to 4, wherein said rendering a preset avatar according to a first behavioral pose of said target object comprises:
determining position information and rotation quaternion information of collision bodies arranged at each part of the virtual image body under the first action posture;
and under the condition that the position information of the colliders of all the parts is not overlapped, controlling the body part in the virtual image to rotate according to the rotating quaternion information corresponding to the first behavior posture.
6. The method of claim 5, wherein rendering a preset avatar according to the first behavior pose of the target object, further comprises:
under the condition that the position information of the collision bodies of all the parts is overlapped, adjusting the position information and/or the rotation quaternion information of the overlapped parts to obtain adjusted rotation quaternion information;
and controlling the body part in the virtual image to rotate according to the adjusted rotating quaternion information so as to prevent the position information of the collision body of each part from being overlapped.
7. The method according to any one of claims 1 to 6, wherein the detecting the video frame in the captured video stream and the determining the object region of the target object in the video frame comprise at least one of the following methods:
performing human body detection on a video frame of the acquired video stream, and determining a first key point corresponding to the face and a second key point corresponding to the hand of a target object in the video frame;
determining a face area according to the size of the face area corresponding to the face and the first key point;
and determining the hand area according to the hand area size corresponding to the hand and the second key point.
8. An avatar rendering apparatus, comprising:
the detection module is used for detecting a video frame in the acquired video stream and determining an object region of a target object in the video frame, wherein the object region comprises a body region, a face region and a hand region;
the processing module is used for processing the object area of the target object and determining a first behavior gesture of the target object, wherein the first behavior gesture comprises a body gesture, a facial expression and a hand gesture of the target object;
and the rendering module is used for rendering a preset virtual image according to the first behavior gesture of the target object.
9. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1 to 7.
10. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911203909.6A CN110889382A (en) | 2019-11-29 | 2019-11-29 | Virtual image rendering method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911203909.6A CN110889382A (en) | 2019-11-29 | 2019-11-29 | Virtual image rendering method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110889382A true CN110889382A (en) | 2020-03-17 |
Family
ID=69749639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911203909.6A Pending CN110889382A (en) | 2019-11-29 | 2019-11-29 | Virtual image rendering method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110889382A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020147794A1 (en) * | 2019-01-18 | 2020-07-23 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image device and storage medium |
| CN111694429A (en) * | 2020-06-08 | 2020-09-22 | 北京百度网讯科技有限公司 | Virtual object driving method and device, electronic equipment and readable storage |
| CN113011290A (en) * | 2021-03-03 | 2021-06-22 | 上海商汤智能科技有限公司 | Event detection method and device, electronic equipment and storage medium |
| CN113158918A (en) * | 2021-04-26 | 2021-07-23 | 深圳市商汤科技有限公司 | Video processing method and device, electronic equipment and storage medium |
| CN114327705A (en) * | 2021-12-10 | 2022-04-12 | 重庆长安汽车股份有限公司 | Vehicle-mounted assistant virtual image self-defining method |
| CN114422862A (en) * | 2021-12-24 | 2022-04-29 | 上海浦东发展银行股份有限公司 | Service video generation method, device, equipment, storage medium and program product |
| CN114786040A (en) * | 2022-06-15 | 2022-07-22 | 阿里巴巴（中国）有限公司 | Data communication method, system, electronic device and storage medium |
| US11468612B2 (en) | 2019-01-18 | 2022-10-11 | Beijing Sensetime Technology Development Co., Ltd. | Controlling display of a model based on captured images and determined information |
| WO2022222572A1 (en) * | 2021-04-19 | 2022-10-27 | 上海商汤智能科技有限公司 | Method and apparatus for driving interaction object, device, and storage medium |
| WO2023229527A3 (en) * | 2022-05-27 | 2024-01-25 | 脸萌有限公司 | Virtual image rendering method and apparatus, electronic device and storage medium |
| CN117745597A (en) * | 2024-02-21 | 2024-03-22 | 荣耀终端有限公司 | Image processing method and related device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106415665A (en) * | 2014-07-25 | 2017-02-15 | 英特尔公司 | Avatar facial expression animations with head rotation |
| CN107067451A (en) * | 2017-04-07 | 2017-08-18 | 广州爱九游信息技术有限公司 | The implementation method and device of dynamic bone in animation |
| CN108234276A (en) * | 2016-12-15 | 2018-06-29 | 腾讯科技（深圳）有限公司 | Interactive method, terminal and system between a kind of virtual image |
| US20190325658A1 (en) * | 2016-10-17 | 2019-10-24 | Samsung Electronics Co., Ltd. | Device and method for rendering image |
| CN110390705A (en) * | 2018-04-16 | 2019-10-29 | 北京搜狗科技发展有限公司 | A kind of method and device generating virtual image |
-
2019
- 2019-11-29 CN CN201911203909.6A patent/CN110889382A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106415665A (en) * | 2014-07-25 | 2017-02-15 | 英特尔公司 | Avatar facial expression animations with head rotation |
| US20190325658A1 (en) * | 2016-10-17 | 2019-10-24 | Samsung Electronics Co., Ltd. | Device and method for rendering image |
| CN108234276A (en) * | 2016-12-15 | 2018-06-29 | 腾讯科技（深圳）有限公司 | Interactive method, terminal and system between a kind of virtual image |
| CN107067451A (en) * | 2017-04-07 | 2017-08-18 | 广州爱九游信息技术有限公司 | The implementation method and device of dynamic bone in animation |
| CN110390705A (en) * | 2018-04-16 | 2019-10-29 | 北京搜狗科技发展有限公司 | A kind of method and device generating virtual image |
Non-Patent Citations (1)
| Title |
|---|
| HANBYUL JOO ET AL.: "Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies", 《CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020147794A1 (en) * | 2019-01-18 | 2020-07-23 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image device and storage medium |
| US11741629B2 (en) | 2019-01-18 | 2023-08-29 | Beijing Sensetime Technology Development Co., Ltd. | Controlling display of model derived from captured image |
| US11538207B2 (en) | 2019-01-18 | 2022-12-27 | Beijing Sensetime Technology Development Co., Ltd. | Image processing method and apparatus, image device, and storage medium |
| US11468612B2 (en) | 2019-01-18 | 2022-10-11 | Beijing Sensetime Technology Development Co., Ltd. | Controlling display of a model based on captured images and determined information |
| CN111694429A (en) * | 2020-06-08 | 2020-09-22 | 北京百度网讯科技有限公司 | Virtual object driving method and device, electronic equipment and readable storage |
| CN111694429B (en) * | 2020-06-08 | 2023-06-02 | 北京百度网讯科技有限公司 | Virtual object driving method and device, electronic equipment and readable storage |
| CN113011290A (en) * | 2021-03-03 | 2021-06-22 | 上海商汤智能科技有限公司 | Event detection method and device, electronic equipment and storage medium |
| WO2022222572A1 (en) * | 2021-04-19 | 2022-10-27 | 上海商汤智能科技有限公司 | Method and apparatus for driving interaction object, device, and storage medium |
| CN113158918A (en) * | 2021-04-26 | 2021-07-23 | 深圳市商汤科技有限公司 | Video processing method and device, electronic equipment and storage medium |
| CN114327705A (en) * | 2021-12-10 | 2022-04-12 | 重庆长安汽车股份有限公司 | Vehicle-mounted assistant virtual image self-defining method |
| CN114327705B (en) * | 2021-12-10 | 2023-07-14 | 重庆长安汽车股份有限公司 | Vehicle assistant virtual image self-defining method |
| CN114422862A (en) * | 2021-12-24 | 2022-04-29 | 上海浦东发展银行股份有限公司 | Service video generation method, device, equipment, storage medium and program product |
| WO2023229527A3 (en) * | 2022-05-27 | 2024-01-25 | 脸萌有限公司 | Virtual image rendering method and apparatus, electronic device and storage medium |
| CN114786040B (en) * | 2022-06-15 | 2022-09-23 | 阿里巴巴（中国）有限公司 | Data communication method, system, electronic device and storage medium |
| CN114786040A (en) * | 2022-06-15 | 2022-07-22 | 阿里巴巴（中国）有限公司 | Data communication method, system, electronic device and storage medium |
| CN117745597A (en) * | 2024-02-21 | 2024-03-22 | 荣耀终端有限公司 | Image processing method and related device |
| CN117745597B (en) * | 2024-02-21 | 2024-07-02 | 荣耀终端有限公司 | Image processing method and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110991327A (en) | Interaction method and device, electronic equipment and storage medium | |
| CN110889382A (en) | Virtual image rendering method and device, electronic equipment and storage medium | |
| CN109816764B (en) | Image generation method and device, electronic equipment and storage medium | |
| CN107692997B (en) | Heart rate detection method and device | |
| WO2022179025A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| WO2020007241A1 (en) | Image processing method and apparatus, electronic device, and computer-readable storage medium | |
| CN111241887B (en) | Target object key point identification method and device, electronic equipment and storage medium | |
| CN110928627B (en) | Interface display method and device, electronic equipment and storage medium | |
| CN109446912B (en) | Face image processing method and device, electronic equipment and storage medium | |
| WO2022188305A1 (en) | Information presentation method and apparatus, and electronic device, storage medium and computer program | |
| CN110569777A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN109325908B (en) | Image processing method and device, electronic equipment and storage medium | |
| WO2022193466A1 (en) | Image processing method and apparatus, and electronic device and storage medium | |
| CN109685041B (en) | Image analysis method and device, electronic equipment and storage medium | |
| CN111242303A (en) | Network training method and device, and image processing method and device | |
| CN113763286A (en) | Image processing method and device, electronic equipment and storage medium | |
| WO2023040202A1 (en) | Face recognition method and apparatus, electronic device, and storage medium | |
| CN114067085A (en) | Virtual object display method and device, electronic equipment and storage medium | |
| CN112613447A (en) | Key point detection method and device, electronic equipment and storage medium | |
| CN109255839B (en) | Scene adjustment method and device | |
| CN106126104B (en) | Keyboard simulation method and device | |
| WO2022198821A1 (en) | Method and apparatus for performing matching between human face and human body, and electronic device, storage medium and program | |
| CN112651880B (en) | Video data processing method and device, electronic equipment and storage medium | |
| CN114266305A (en) | Object identification method and device, electronic equipment and storage medium | |
| CN109407942B (en) | Model processing method and device, control client and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200317 |