Interactive projector with free input

Abstract

The present invention provides an interactive projector with a free input end, comprising: a motion capture module, used to lock a target person and obtain the motion information of the target person; an intention confirmation module, used to analyze based on the motion information, determine the operation intention of the target person, and determine the final operation of the target person according to the operation intention; and a control module, used to control the current real-time image of the projector according to the final operation to generate a new projection screen. The present invention captures the motion of the target person, determines the operation of the target person, and controls the current real-time image of the projector according to the operation, thereby enhancing the human-computer interactivity of the projector, so that the target person can control the projection screen without other devices, and reduces the restrictions of the projector on the lecturer.

Description

Technical Field

[0001] The invention relates to the technical field of optical instruments, and in particular to an interactive projector with a free input end. Background Art

[0002] A projector is a device that can project images or videos onto a screen. It is widely used in homes, offices, schools and entertainment venues. Traditional projector operation requires clicking on the computer with a mouse to display the screen and then operate the projected screen. This operation method requires the projector operator to always stand in front of the computer, which greatly limits the range of activities of the speaker.

[0003] Therefore, the present invention proposes an interactive projector with a free input end, so that the lecturer can control the projection image without using other devices, thereby reducing the restrictions of the projector on the lecturer. Summary of the invention

[0004] The present invention provides an interactive projector with a free input end, which captures the actions of a target person and determines the operation of the target person, and controls the current real-time image of the projector according to the operation, thereby enhancing the human-computer interactivity of the projector of the present invention, so that a lecturer can control the projected image without other equipment, thereby reducing the restrictions of the projector on the lecturer.

[0005] The present invention provides an interactive projector with a free input end, comprising:

[0006] A motion capture module is used to lock a target person and obtain motion information of the target person;

[0007] An intention confirmation module, used to analyze the action information to determine the operation intention of the target person, and determine the final operation of the target person according to the operation intention;

[0008] The control module is used to control the current real-time image of the projector according to the final operation to generate a new projection picture.

[0009] Preferably, the motion capture module comprises:

[0010] A first determination unit is used to obtain the entry time of a person who enters the projection range of the projector, and when the entry time is greater than or equal to a first preset time, determine that the person is a target person;

[0011] A tracking and locking unit, used to generate a target tracker according to the target person information, and lock and track the target person;

[0012] A motion capture unit is used to collect motion information of the target person based on the target tracker.

[0013] Preferably, the motion capture module further includes:

[0014] A second determination unit is configured to obtain the target person's exit time when it is detected that the target person is not within the projection range, and determine that the target person tracking is invalid when the exit time is greater than or equal to a second preset time, end the tracking, and delete the target tracker corresponding to the target person information;

[0015] When the picture exiting time is less than the second preset time, the target tracker corresponding to the target person information keeps tracking.

[0016] Preferably, the motion capture unit is further used for:

[0017] Obtaining the number of target persons at the same time, and when there are multiple target persons, adding person numbers to the target persons, and adding digital tags to the target tracker based on the person code numbers;

[0018] At the same time, the action information collected by the target tracker is stored according to the digital tag.

[0019] Preferably, an interactive projector with a free input end further comprises:

[0020] A priority determination module, used to obtain the current application scene information of the projector when there are multiple target persons, and determine whether there is a priority setting for the target person in the current application scene;

[0021] If so, the target person with a high priority is determined as the main tracking person. When multiple target persons issue operation instructions at the same time, the operation instructions of the main tracking person are executed first.

[0022] Preferably, the intention confirmation module includes:

[0023] An analysis unit, configured to obtain a motion feature of the target person based on the motion information of the target person, query a preset gesture database according to the motion feature, obtain a similar motion, and determine a similarity between the similar motion and the motion of the target person;

[0024] A first confirmation unit, configured to compare the action similarities, obtain a target action corresponding to the highest action similarity, and determine the operation intention of the target person based on the target action;

[0025] A second confirmation unit is used to determine whether the operation intention is consistent with the current projection scene, and if so, determine the final operation of the target person according to the operation intention;

[0026] Otherwise, it is determined that the operation intention confirmation is wrong, and the action information is sent to the first analysis unit for re-analysis.

[0027] Preferably, the analysis unit is used to:

[0028] Based on the motion information of the target person, obtaining hand motion information of the target person;

[0029] According to the hand motion information and based on a virtual gesture simulation system, the hand gesture of the target person is simulated to obtain hand gesture change data of the target person;

[0030] According to the hand posture change data, a hand posture dynamic curve is constructed to obtain the hand change trajectory of the target person, wherein the hand change trajectory includes the finger change trajectory and the wrist change trajectory;

[0031] According to the hand change trajectory, a hand gesture direction change feature of the target person is acquired, and the hand gesture direction change feature is used as a first action feature;

[0032] Based on the hand change trajectory, obtaining first posture data of the target person's initial gesture change and second posture data of the gesture change completed;

[0033] Obtaining posture difference data from the first posture data and the second posture data of the gesture, and determining a second action feature of the target person based on the posture difference data;

[0034] Based on the first action feature, query in a preset gesture database to obtain a same-direction operation gesture;

[0035] respectively acquiring third action features of the same-direction operation gestures, comparing the third action features with the second action features, and determining whether the same-direction operation gestures are similar actions;

[0036] When the difference between the third action feature and the second action feature is within a preset range, determining that the same-direction operation gesture is a similar action;

[0037] Acquire a standard gesture image of the similar action and a final gesture image of the target person after the gesture change is completed;

[0038] Acquire hand model parameters of a standard gesture image, locate gesture key points on the final gesture image, and adjust hand parameters on the final gesture image based on gesture key point positioning according to the hand model parameters to obtain a hand image to be matched;

[0039] The standard gesture image is overlapped with the hand image to be matched, an overlapping area between the standard gesture image and the hand image to be matched is obtained, and the action similarity between the similar action and the action of the target person is calculated based on the overlapping area and the hand deflection direction.

[0040] Preferably, the intention confirmation module further includes:

[0041] A scene confirmation unit, used to obtain a currently projected environment image and a gray level co-occurrence matrix of the environment image, and determine texture features of each still object on the environment image based on the gray level co-occurrence matrix;

[0042] Marking still objects in the environment image according to the texture features, and respectively acquiring physical features of the still objects;

[0043] According to the physical features, based on an Internet query, determine the name of the still life;

[0044] Acquire all application simulation scenes of the projector and the scenery objects of the application simulation scenes, and filter out multiple possible scenes based on the names of the objects;

[0045] Obtaining rendering effect images of the multiple possible scenes respectively and comparing them with the environment image to determine the locations of rendering effect differences;

[0046] At the same time, respectively obtaining scene usage instructions for the multiple possible scenes, and determining the primary scenery areas and the secondary scenery areas for the multiple possible scenes based on the scene usage instructions;

[0047] When the presentation effect difference position is in the secondary scenery area, the presentation effect difference position is judged to be a secondary difference; when the presentation effect difference position is in the primary scenery area, the presentation effect difference position is judged to be a primary difference;

[0048] When there are major differences between possible scenarios, the possible scenarios are used as the first target scenarios;

[0049] Obtain a current environment plan view, and based on the current environment plan view, determine whether a major difference of the first target scene is an uncontrollable difference caused by environmental restrictions, and if so, set the major difference as a special minor difference;

[0050] Otherwise, determining that the first target scene corresponding to the main difference is not the current projection scene;

[0051] Taking a possible scene in which all presentation effect difference positions are minor differences and special minor differences as a second target scene, acquiring a plurality of historical projection data of the second target scene, and comparing the plurality of historical projection data to determine a first projection data feature of the second target scene;

[0052] Based on the current projection picture, a second projection data feature of the current projection data is obtained; when the first projection data feature is consistent with the second projection data feature, the first target scene is determined to be the current projection scene.

[0053] Preferably, the control module comprises:

[0054] A control unit, used to confirm a corresponding operation instruction according to the final operation, and send the operation instruction to the operation unit;

[0055] An operating unit, used to receive the operating instruction and perform a control operation on the current real-time image of the projector according to the operating instruction to generate a new projection picture;

[0056] The projection unit is used to display the new projection image on a projector external device.

[0057] Preferably, an interactive projector with a free input end further comprises: a projection connection module for receiving projection data, including:

[0058] A wireless connection unit, used for an external device to transmit the projection data to the projector via wireless transmission;

[0059] The wired transmission unit is used for an external device to transmit the projection data to the projector via a USB port.

[0060] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0061] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0063] Figure 1 It is a schematic diagram of the structure of an interactive projector with a free input end in an embodiment of the present invention;

[0064] Figure 2 It is a schematic diagram of the structure of an interactive projector motion capture module with a free input end in an embodiment of the present invention;

[0065] Figure 3It is a schematic diagram of the structure of an interactive projector intention confirmation module with a free input end in an embodiment of the present invention;

[0066] Figure 4 The figure is a schematic diagram of the structure of an interactive projector control module with a free input end in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0068] Embodiment 1:

[0069] The present invention provides an interactive projector with a free input end, comprising:

[0070] A motion capture module is used to lock a target person and obtain motion information of the target person;

[0071] An intention confirmation module, used to analyze the action information to determine the operation intention of the target person, and determine the final operation of the target person according to the operation intention;

[0072] The control module is used to control the current real-time image of the projector according to the final operation to generate a new projection picture.

[0073] In this embodiment, the action information refers to the body changes of the target person.

[0074] In this embodiment, the operation intention refers to the effect that the target person wants to achieve, and the final operation is the operation that the target person wants to achieve on the current projection screen according to the analyzed action changes of the target person, such as turning pages, partial zooming, etc.

[0075] The beneficial effects of the above embodiments are as follows: the present invention captures the motions of the target person, determines the operations of the target person, and controls the current real-time image of the projector according to the operations, thereby enhancing the human-computer interactivity of the projector of the present invention, allowing the target person to control the projected image without other devices, thereby reducing the restrictions of the projector on the lecturer.

[0076] Embodiment 2:

[0077] On the basis of embodiment 1, the motion capture module includes:

[0078] A first determination unit is used to obtain the entry time of a person who enters the projection range of the projector, and when the entry time is greater than or equal to a first preset time, determine that the person is a target person;

[0079] A tracking and locking unit, used to generate a target tracker according to the target person information, and lock and track the target person;

[0080] A motion capture unit is used to collect motion information of the target person based on the target tracker.

[0081] In this embodiment, the entry time refers to the time when a person enters the projection range of the projector.

[0082] In this embodiment, the first preset time refers to the shortest time for a person to enter the projection range of the projector and be determined as a target person.

[0083] In this embodiment, a Kalman filter is provided inside the target tracker to ensure the timing of the tracking action.

[0084] The beneficial effects of the above embodiment: the present invention determines whether a person is a target person according to the time when the person enters the projection range of the projector, and establishes a target tracker to track the target person after locking the target person, ensuring that the action information of each target person is accurately obtained, providing a basis for accurately completing the operation of the target person.

[0085] Embodiment 3:

[0086] On the basis of embodiment 2, the motion capture module further includes:

[0087] A second determination unit is configured to obtain the target person's exit time when it is detected that the target person is not within the projection range, and determine that the target person tracking is invalid when the exit time is greater than or equal to a second preset time, end the tracking, and delete the target tracker corresponding to the target person information;

[0088] When the picture exiting time is less than the second preset time, the target tracker corresponding to the target person information keeps tracking.

[0089] In this embodiment, the exit time refers to the time when the target person leaves the projection range of the projector.

[0090] In this embodiment, the second preset time refers to the shortest time when the target person leaves the projection range of the projector and is judged as tracking failure. Tracking failure refers to the situation that the target person leaves the monitoring range (projector projection range) for a long time so that the target tracker cannot capture the target person in the monitoring range for a long time.

[0091] The beneficial effects of the above embodiment are as follows: when the present invention detects that the target person is not within the projection range, the target person's exit time is obtained. When the exit time is greater than or equal to the second preset time, it is determined that the tracking of the target person is invalid, the tracking is ended, and the target tracker corresponding to the target person information is deleted. The invalid tracker is cleared in time to avoid redundant data. At the same time, a larger data space is provided for other target trackers to ensure the rapid operation of other target trackers.

[0092] Embodiment 4:

[0093] Based on Example 2, the motion capture unit is further used for:

[0094] Obtaining the number of target persons at the same time, and when there are multiple target persons, adding person numbers to the target persons, and adding digital tags to the target tracker based on the person code numbers;

[0095] At the same time, the action information collected by the target tracker is stored according to the digital tag.

[0096] In this embodiment, the digital tag refers to a number added to the target tracker corresponding to the target person according to the person number of the target person.

[0097] The beneficial effects of the above embodiments are as follows: when there are multiple target persons within the projection range, the present invention adds a person number to the target person, and adds a digital label to the target tracker based on the person code number, thereby ensuring the orderliness of motion information collection; at the same time, the motion information collected by the target tracker is stored according to the digital label, and the digital labels are used to distinguish different target persons, thereby avoiding data storage confusion and providing convenience for data call during motion information analysis.

[0098] Embodiment 5:

[0099] Based on Embodiment 1, an interactive projector with a free input terminal further includes:

[0100] A priority determination module, used to obtain the current application scene information of the projector when there are multiple target persons, and determine whether there is a priority setting for the target person in the current application scene;

[0101] If so, the target person with a high priority is determined as the main tracking person. When multiple target persons issue operation instructions at the same time, the operation instructions of the main tracking person are executed first.

[0102] In this embodiment, the current application scenario information refers to the environmental information of the current use scenario of the projector, for example, the current application of the projector and the conference discussion scenario.

[0103] In this embodiment, the main tracking person refers to the target person with the highest action operation priority. For example, in a conference discussion scenario, it is necessary to determine a conference speaker, and the speaker is the main tracking person.

[0104] The beneficial effects of the above embodiment are as follows: when there are multiple target persons, the present invention obtains the current application scene information of the projector and determines whether there is a priority setting for the target person of the previous application scene; if so, the target person with a high priority is determined as the main tracking person, and when multiple target persons issue operation instructions at the same time, the operation instructions of the main tracking person are executed first, ensuring that the main tracking person has control over the projection operation of the current application scene and ensuring the normal display of the projection picture in the current application scene.

[0105] Embodiment 6:

[0106] Based on Example 1, the intention confirmation module includes:

[0107] An analysis unit, configured to obtain a motion feature of the target person based on the motion information of the target person, query a preset gesture database according to the motion feature, obtain a similar motion, and determine a similarity between the similar motion and the motion of the target person;

[0108] A first confirmation unit, configured to compare the action similarities, obtain a target action corresponding to the highest action similarity, and determine the operation intention of the target person based on the target action;

[0109] A second confirmation unit is used to determine whether the operation intention is consistent with the current projection scene, and if so, determine the final operation of the target person according to the operation intention;

[0110] Otherwise, it is determined that the operation intention confirmation is wrong, and the action information is sent to the first analysis unit for re-analysis.

[0111] In this embodiment, the similar action refers to the hand action in the preset gesture database that is the same as the action performed by the target person.

[0112] In this embodiment, the action similarity refers to the degree of similarity between the similar action and the action of the target person.

[0113] In this embodiment, the action feature includes a first action feature and a second action feature.

[0114] The beneficial effects of the above embodiments are as follows: the present invention obtains the operation intention of the character through the action characteristics of the target character based on the preset posture database analysis, and then determines whether the operation intention is consistent with the current projection scene, thereby ensuring the accuracy of the target character action analysis.

[0115] Embodiment 7:

[0116] On the basis of Example 6, the analysis unit is used for:

[0117] Based on the motion information of the target person, obtaining hand motion information of the target person;

[0118] According to the hand motion information and based on a virtual gesture simulation system, the hand gesture of the target person is simulated to obtain hand gesture change data of the target person;

[0119] According to the hand posture change data, a hand posture dynamic curve is constructed to obtain the hand change trajectory of the target person, wherein the hand change trajectory includes the finger change trajectory and the wrist change trajectory;

[0120] According to the hand change trajectory, a hand gesture direction change feature of the target person is acquired, and the hand gesture direction change feature is used as a first action feature;

[0121] Based on the hand change trajectory, obtaining first posture data of the target person's initial gesture change and second posture data of the gesture change completed;

[0122] Obtaining posture difference data from the first posture data and the second posture data of the gesture, and determining a second action feature of the target person based on the posture difference data;

[0123] Based on the first action feature, query in a preset gesture database to obtain a same-direction operation gesture;

[0124] respectively acquiring third action features of the same-direction operation gestures, comparing the third action features with the second action features, and determining whether the same-direction operation gestures are similar actions;

[0125] When the difference between the third action feature and the second action feature is within a preset range, determining that the same-direction operation gesture is a similar action;

[0126] Acquire a standard gesture image of the similar action and a final gesture image of the target person after the gesture change is completed;

[0127] Acquire hand model parameters of a standard gesture image, locate gesture key points on the final gesture image, and adjust hand parameters on the final gesture image based on gesture key point positioning according to the hand model parameters to obtain a hand image to be matched;

[0128] The standard gesture image is overlapped with the hand image to be matched, an overlapping area between the standard gesture image and the hand image to be matched is obtained, and the action similarity between the similar action and the action of the target person is calculated based on the overlapping area and the hand deflection direction.

[0129] In this embodiment, the hand motion information refers to the target person's finger and wrist posture change information.

[0130] In this embodiment, the hand posture change data refers to the position data of the fingers and wrist joints when the hand gesture of the target person changes.

[0131] In this embodiment, the hand gesture dynamic curve refers to a curve that depicts the changes in the target person's hand gestures.

[0132] In this embodiment, the gesture direction change feature refers to the movement direction of the hand of the target person during the gesture change process, and the first action feature refers to the gesture direction change feature.

[0133] In this embodiment, the first posture data refers to the unchanged gesture data when the target person's gesture begins to change, and the data refers to the position of the target person's fingers and wrist joints; the second posture data refers to the gesture data when the target person's gesture change has just been completed.

[0134] In this embodiment, the posture difference data refers to the position difference of the hand joints of the target person when the gestures are unchanged and when the gestures are changed.

[0135] In this embodiment, the second action feature refers to the position change feature of the hand joints of the target person whose gestures have not changed and have been changed.

[0136] In this embodiment, the same-direction operation gesture refers to an operation gesture in the gesture database that has the same direction of change as the target person's gesture.

[0137] In this embodiment, the third action feature refers to the action feature of the same-direction operation gesture.

[0138] In this embodiment, the similar action refers to a same-direction operation gesture with a hand joint position similar to that of the target person's gesture.

[0139] In this embodiment, the standard gesture image refers to a depiction image of a similar gesture in a posture database.

[0140] In this embodiment, the final gesture image refers to the final gesture image after the gesture change of the target person is completed.

[0141] In this embodiment, the hand model parameters refer to the hand parameters used when describing each operation gesture in the posture database, such as the size of the hand, the length of the fingers, etc.

[0142] In this embodiment, the key points of the gesture refer to the positioning points of the fingers and wrist joints in the gesture.

[0143] In this embodiment, the hand image to be matched refers to an image obtained by adjusting the hand parameters on the final gesture image to be consistent with the standard gesture image without changing the positions and directions of the gesture key points on the final gesture image of the target person.

[0144] In this embodiment, the similarity between the similar action and the action of the target person is calculated based on the overlapping area and the hand deflection direction, as follows:

[0145]

[0146] Where α represents the bending angle error of the hand when the standard gesture image overlaps with the hand image to be matched; W 1 Represents the hand direction vector on the standard gesture image; W 2 Represents the hand direction vector on the hand image to be matched; |W 1 | represents the magnitude of the hand direction vector on the standard gesture image; |W 2 | represents the modulus of the hand direction vector on the hand image to be matched; δ represents the deviation rate of the hand direction vector selection on the hand image, which is (0, 0.1);

[0147]

[0148] Among them, θ represents the action similarity between the similar action and the target person's action; B represents the hand area of ​​the hand model on the standard gesture image; A represents the overlapping area of ​​the standard gesture image and the hand image to be matched; α 1 Represents the hand deflection angle on the standard gesture image.

[0149] The beneficial effects of the above embodiments are as follows: the present invention obtains the hand motion information of the target person based on the motion information of the target person; according to the hand motion information and based on the virtual gesture simulation system, the hand posture of the target person is simulated to accurately obtain the change data of the fingers and wrists of the target person, thereby ensuring the accuracy of the hand posture dynamic curve; then, through the hand posture dynamic curve, the hand change trajectory of the target person is obtained, the gesture direction change characteristics are determined, and the same-direction operation gestures are screened out; and then, through the posture difference data before and after the gesture change, similar actions are screened out in the same-direction operation gestures, thereby providing an effective reference for the final operation determination of the target person.

[0150] According to the hand model parameters of the standard gesture image, based on the positioning of the gesture key points on the final gesture image, the hand parameters on the final gesture image are adjusted to obtain the hand image to be matched, and the standard gesture image is overlapped with the hand image to be matched to ensure the accuracy of the action similarity calculation and the accuracy of the determination of the target person's operation intention.

[0151] Embodiment 8:

[0152] Based on Example 6, the intention confirmation module further includes:

[0153] A scene confirmation unit, used to obtain a currently projected environment image and a gray level co-occurrence matrix of the environment image, and determine texture features of each still object on the environment image based on the gray level co-occurrence matrix;

[0154] Marking still objects in the environment image according to the texture features, and respectively acquiring physical features of the still objects;

[0155] According to the physical features, based on an Internet query, determine the name of the still life;

[0156] Acquire all application simulation scenes of the projector and the scenery objects of the application simulation scenes, and filter out multiple possible scenes based on the names of the objects;

[0157] Obtaining rendering effect images of the multiple possible scenes respectively and comparing them with the environment image to determine the locations of rendering effect differences;

[0158] At the same time, respectively obtaining scene usage instructions for the multiple possible scenes, and determining the primary scenery areas and the secondary scenery areas for the multiple possible scenes based on the scene usage instructions;

[0159] When the presentation effect difference position is in the secondary scenery area, the presentation effect difference position is judged to be a secondary difference; when the presentation effect difference position is in the primary scenery area, the presentation effect difference position is judged to be a primary difference;

[0160] When there are major differences between possible scenarios, the possible scenarios are used as the first target scenarios;

[0161] Obtain a current environment plan view, and based on the current environment plan view, determine whether a major difference of the first target scene is an uncontrollable difference caused by environmental restrictions, and if so, set the major difference as a special minor difference;

[0162] Otherwise, determining that the first target scene corresponding to the main difference is not the current projection scene;

[0163] Taking a possible scene in which all presentation effect difference positions are minor differences and special minor differences as a second target scene, acquiring a plurality of historical projection data of the second target scene, and comparing the plurality of historical projection data to determine a first projection data feature of the second target scene;

[0164] Based on the current projection picture, a second projection data feature of the current projection data is obtained; when the first projection data feature is consistent with the second projection data feature, the first target scene is determined to be the current projection scene.

[0165] In this embodiment, the environment image refers to an image of the environment in which the projector works.

[0166] In this embodiment, the texture feature refers to the grayscale changes of pixels of each still object in the working environment of the projector represented on the environment image.

[0167] In this embodiment, the physical features refer to the size, color, shape and other characteristics of each still object in the environment image.

[0168] In this embodiment, the scenery items refer to conventional layout items that can be used in projector application scenarios.

[0169] In this embodiment, the possible scene refers to a scene that may correspond to the current environment determined by comparing objects in the current projection environment, for example, a seminar scene, a press conference scene, and the like.

[0170] In this embodiment, the presentation effect diagram refers to a conventional image of the effect presented by the conventional arrangement of each possible scene.

[0171] In this embodiment, the presentation effect difference position refers to the different positions of objects in the renderings of the current scene and the possible scenes presented by the environment image.

[0172] In this embodiment, the scene adaptation description refers to the purpose of each scene application; the main scenery area refers to the area setting that must exist in the scene due to the application purpose of a certain scene, for example, the speaker area and the audience area that must exist in a lecture scene; the secondary scenery area refers to the area setting that can exist in the scene due to the application purpose of a certain scene, for example, the flower basket placement area in a lecture scene.

[0173] In this embodiment, the minor difference refers to the different positions of objects in the current scene presented by the environment image and the rendering of the possible scene, in the minor setting area of ​​the possible scene.

[0174] In this embodiment, the main difference refers to the different positions of objects in the current scene presented by the environment image and the rendering of the possible scene, which is the main setting area of ​​the possible scene.

[0175] In this embodiment, the first target scene refers to a possible scene with major differences.

[0176] In this embodiment, the uncontrollable difference refers to the main difference caused by environmental reasons. For example, in a lecture scene, the listening area is divided into multiple areas due to the large area, but there is only one listening area in the presentation effect diagram of this possible scene.

[0177] In this embodiment, the special minor difference refers to the major difference caused by environmental restrictions.

[0178] In this embodiment, the second target scenario refers to a possible scenario in which all presentation effect difference positions are minor differences and special minor differences.

[0179] In this embodiment, the first projection data feature refers to the projection data feature of the second target scene; the second projection data feature refers to the feature of the current projection data.

[0180] The beneficial effects of the above embodiments are as follows: the present invention analyzes the current environment image of the projector to determine the possible scenes of the projector, and then determines the current projection length by comparing the current projection data, thereby completing the autonomous determination of the projection environment and providing a basis for judging the target person's operating intention.

[0181] Embodiment 9:

[0182] Based on Example 1, the control module includes:

[0183] A control unit, used to confirm a corresponding operation instruction according to the final operation, and send the operation instruction to the operation unit;

[0184] An operating unit, used to receive the operating instruction and perform a control operation on the current real-time image of the projector according to the operating instruction to generate a new projection picture;

[0185] The projection unit is used to display the new projection image on a projector external device.

[0186] In this embodiment, the projector external device refers to a device that can display a projection image like a projection screen.

[0187] The beneficial effects of the above embodiment are as follows: the present invention confirms the corresponding operation instruction according to the final operation, and sends the operation instruction to the operation unit, which controls the current real-time image of the projector to generate a new projection screen, so that the target person can control the projection screen without other devices, thereby realizing the target person's direct control over the projector.

[0188] Embodiment 10:

[0189] Based on the first embodiment, an interactive projector with a free input terminal further includes: a projection connection module for receiving projection data, including:

[0190] A wireless connection unit, used for an external device to transmit the projection data to the projector via wireless transmission;

[0191] The wired transmission unit is used for an external device to transmit the projection data to the projector via a USB port.

[0192] In this embodiment, the wireless transmission method includes Bluetooth transmission and WIFI transmission.

[0193] Beneficial effects of the above embodiments: The projection data of the present invention can be transmitted to the projector via wireless transmission and a USB port, thereby achieving diversification of projector data connections.

[0194] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An interactive projector with a free input port, characterized in that: include: A motion capture module is used to lock a target person and obtain motion information of the target person; An intention confirmation module, used to analyze the action information to determine the operation intention of the target person, and determine the final operation of the target person according to the operation intention; A control module, used to control the current real-time image of the projector according to the final operation to generate a new projection picture; Wherein, the intention confirmation module includes: An analysis unit, configured to obtain a motion feature of the target person based on the motion information of the target person, query a preset gesture database according to the motion feature, obtain a similar motion, and determine a similarity between the similar motion and the motion of the target person; A first confirmation unit, configured to compare the action similarities, obtain a target action corresponding to the highest action similarity, and determine the operation intention of the target person based on the target action; A second confirmation unit is used to determine whether the operation intention is consistent with the current projection scene, and if so, determine the final operation of the target person according to the operation intention; Otherwise, determining that the operation intention confirmation is wrong, and sending the action information to the first analysis unit for re-analysis; Wherein, the analysis unit is used for: Based on the motion information of the target person, obtaining hand motion information of the target person; According to the hand motion information and based on a virtual gesture simulation system, the hand gesture of the target person is simulated to obtain hand gesture change data of the target person; According to the hand posture change data, a hand posture dynamic curve is constructed to obtain the hand change trajectory of the target person, wherein the hand change trajectory includes the finger change trajectory and the wrist change trajectory; According to the hand change trajectory, a hand gesture direction change feature of the target person is acquired, and the hand gesture direction change feature is used as a first action feature; Based on the hand change trajectory, obtaining first posture data of the target person's initial gesture change and second posture data of the gesture change completed; Obtaining posture difference data from the first posture data and the second posture data of the gesture, and determining a second action feature of the target person based on the posture difference data; Based on the first action feature, query in a preset gesture database to obtain a same-direction operation gesture; respectively acquiring third action features of the same-direction operation gestures, comparing the third action features with the second action features, and determining whether the same-direction operation gestures are similar actions; When the difference between the third action feature and the second action feature is within a preset range, determining that the same-direction operation gesture is a similar action; Acquire a standard gesture image of the similar action and a final gesture image of the target person after the gesture change is completed; Acquire hand model parameters of a standard gesture image, locate gesture key points on the final gesture image, and adjust hand parameters on the final gesture image based on gesture key point positioning according to the hand model parameters to obtain a hand image to be matched; Overlapping the standard gesture image with the hand image to be matched, obtaining an overlapping area between the standard gesture image and the hand image to be matched, and calculating the action similarity between the similar action and the action of the target person based on the overlapping area and the hand deflection direction; The similarity between the similar action and the action of the target person is calculated based on the overlapping area and the hand deflection direction, as follows: Wherein, α represents the bending angle error of the overlapping hand between the standard gesture image and the hand image to be matched; W1 represents the hand direction vector on the standard gesture image; W2 represents the hand direction vector on the hand image to be matched; |W1| represents the modulus of the hand direction vector on the standard gesture image; |W2| represents the modulus of the hand direction vector on the hand image to be matched; δ represents the deviation rate of the hand direction vector selection on the hand image, which is (0, 0.1); Among them, θ represents the action similarity between the similar action and the target person's action; B represents the hand area of ​​the hand model on the standard gesture image; A represents the overlapping area of ​​the standard gesture image and the hand image to be matched; α1 represents the hand deflection angle on the standard gesture image.

2. The interactive projector with a free input end according to claim 1, characterized in that: The motion capture module comprises: A first determination unit is used to obtain the entry time of a person who enters the projection range of the projector, and when the entry time is greater than or equal to a first preset time, determine that the person is a target person; A tracking and locking unit, used to generate a target tracker according to the target person information, and lock and track the target person; A motion capture unit is used to collect motion information of the target person based on the target tracker.

3. The interactive projector with a free input end according to claim 2, characterized in that: The motion capture module further includes: A second determination unit is configured to obtain the target person's exit time when it is detected that the target person is not within the projection range, and determine that the target person tracking is invalid when the exit time is greater than or equal to a second preset time, end the tracking, and delete the target tracker corresponding to the target person information; When the picture exiting time is less than the second preset time, the target tracker corresponding to the target person information keeps tracking.

4. The interactive projector with a free input end according to claim 2, characterized in that: The motion capture unit is further used for: Obtaining the number of target persons at the same time, and when there are multiple target persons, adding person numbers to the target persons, and adding digital tags to the target tracker based on the person code numbers; At the same time, the action information collected by the target tracker is stored according to the digital tag.

5. The interactive projector with a free input port according to claim 1, characterized in that: Also includes: A priority determination module, used to obtain the current application scene information of the projector when there are multiple target persons, and determine whether there is a priority setting for the target person in the current application scene; If so, the target person with a high priority is determined as the main tracking person. When multiple target persons issue operation instructions at the same time, the operation instructions of the main tracking person are executed first.

6. The interactive projector with a free input port according to claim 1, characterized in that: The intention confirmation module further includes: A scene confirmation unit, used to obtain a currently projected environment image and a gray level co-occurrence matrix of the environment image, and determine texture features of each still object on the environment image based on the gray level co-occurrence matrix; Marking still objects in the environment image according to the texture features, and respectively acquiring physical features of the still objects; According to the physical features, based on an Internet query, determine the name of the still life; Acquire all application simulation scenes of the projector and the scenery objects of the application simulation scenes, and filter out multiple possible scenes based on the names of the objects; Obtaining rendering effect images of the multiple possible scenes respectively and comparing them with the environment image to determine the locations of rendering effect differences; At the same time, respectively obtaining scene usage instructions for the multiple possible scenes, and determining the primary scenery areas and the secondary scenery areas for the multiple possible scenes based on the scene usage instructions; When the presentation effect difference position is in the secondary scenery area, the presentation effect difference position is judged to be a secondary difference; when the presentation effect difference position is in the primary scenery area, the presentation effect difference position is judged to be a primary difference; When there are major differences between possible scenarios, the possible scenarios are used as the first target scenarios; Obtain a current environment plan view, and based on the current environment plan view, determine whether a major difference of the first target scene is an uncontrollable difference caused by environmental restrictions, and if so, set the major difference as a special minor difference; Otherwise, determining that the first target scene corresponding to the main difference is not the current projection scene; Taking a possible scene in which all presentation effect difference positions are minor differences and special minor differences as a second target scene, acquiring a plurality of historical projection data of the second target scene, and comparing the plurality of historical projection data to determine a first projection data feature of the second target scene; Based on the current projection picture, a second projection data feature of the current projection data is obtained; when the first projection data feature is consistent with the second projection data feature, the first target scene is determined to be the current projection scene.

7. The interactive projector with a free input port according to claim 1, characterized in that: The control module comprises: A control unit, used to confirm a corresponding operation instruction according to the final operation, and send the operation instruction to the operation unit; An operating unit, used to receive the operating instruction and perform a control operation on the current real-time image of the projector according to the operating instruction to generate a new projection picture; The projection unit is used to display the new projection image on a projector external device.

8. The interactive projector with a free input end according to claim 1, characterized in that: Also includes: The projection connection module is used to receive projection data, including: A wireless connection unit, used for an external device to transmit the projection data to the projector via wireless transmission; The wired transmission unit is used for an external device to transmit the projection data to the projector via a USB port.

Images