Cooperative detection method and system based on motion platform and illumination

Abstract

The invention discloses a cooperative detection method and system based on a motion platform and illumination, and the method comprises the steps: carrying a laser transmitting device and a camera on the motion platform, enabling the laser transmitting device and the camera to be in a cooperative mode, constructing a second scene picture set and a first scene picture set, defining a frame difference picture sequence based on picture comparison of the same time frame; defining each pixel value of the frame difference picture sequence, marking an abnormal feature according to each pixel value, defining an abnormal position where the abnormal feature is located, freeze-drying the abnormal position where the abnormal feature is located, and defining a brightness change gradient based on brightness comparison of the abnormal position in the second scene picture set; the final position of the pinhole camera is defined according to the detection of the brightness change gradient of each abnormal position, so that the final position of the pinhole camera is controlled based on multiple dimensions, and a better detection effect of the high-precision pinhole camera is realized on the basis of a single light source.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative detection based on a motion platform and lighting, and in particular to a collaborative detection method and system based on a motion platform and lighting. Background Art

[0002] With the development of science and technology, in the field of security protection applications, pinhole cameras have gradually become popular in indoor scenes such as conference venues, private rooms, technical laboratories, exhibition halls and cinemas. However, the detection of pinhole cameras is only carried out through a single detection in the indoor scene under the lighting state, and the final position of the pinhole camera is not controlled based on multiple dimensions, which affects the detection effect of the pinhole camera. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a collaborative detection method and system based on a motion platform and lighting. A laser emitting device and a camera are carried on the motion platform. The laser emitting device and the camera are in a collaborative mode. The laser emitting device and the camera perform image control on the illumination state and the non-illumination state of the scene. At this time, a second scene image set and a first scene image set are constructed, and a frame difference image sequence is defined based on the image comparison of the same time frame; each pixel value of the frame difference image sequence is defined, and abnormal features are marked according to each pixel value and the abnormal position where the abnormal features are located is defined, the abnormal position where the abnormal features are located is frozen, and a brightness change gradient is defined based on the brightness comparison of the abnormal position in the second scene image set; the final position of the pinhole camera is defined according to the detection of the brightness change gradient of each abnormal position, so that the final position of the pinhole camera is controlled based on multiple dimensions, and a better high-precision pinhole camera detection effect is achieved on the basis of a single light source, the interference of other parameters is reduced, and the false alarm rate of the pinhole camera in the scene is effectively reduced.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a collaborative detection method based on a motion platform and lighting, which is applied to the collaborative detection scenario of a pinhole camera;

[0005] The collaborative detection method based on the motion platform and lighting comprises:

[0006] The motion platform carries a laser emitting device and a camera, and the camera shoots a scene without lighting as the motion platform moves dynamically to collect a first scene picture set; at this time, the laser emitting device and the camera are in a collaborative mode;

[0007] The change of the lighting state is triggered based on the completion of the collection of the first scene picture set, and the lighting state of the scene is defined, and the laser emission device is started to achieve fill light. At the same time, the camera shoots the scene of the lighting state as the motion platform moves dynamically to collect the second scene picture set;

[0008] Associating the second scene picture set and the first scene picture set, and defining a frame difference picture sequence based on picture comparison of the same time frame;

[0009] Defining the pixel values ​​of the frame difference image sequence, marking abnormal features according to the pixel values, and defining the abnormal positions where the abnormal features are located;

[0010] Freeze the abnormal position where the abnormal feature is located, and define a brightness change gradient based on the brightness contrast of the abnormal position in the second scene picture set;

[0011] The final position of the pinhole camera is defined based on the detection of the brightness change gradient at each abnormal position.

[0012] Optionally, the motion platform carries a laser emitting device and a camera, and the camera shoots a scene without lighting as the motion platform moves dynamically to collect a first scene picture set; at this time, the laser emitting device and the camera are in a collaborative mode, including:

[0013] Carrying a laser emitting device and a camera on a motion platform, and locating the positions of the laser emitting device and the camera;

[0014] Collect regional parameters of the bearing surface of the motion platform, adjust the position of the laser emitting device and the position of the camera according to the regional parameters of the bearing surface and the scene type, and define a collaborative mode according to the position of the laser emitting device and the position of the camera. At this time, the laser emitting device and the camera are in the collaborative mode, and the illumination node of the laser emitting device and the shooting node of the camera are adjusted in the collaborative mode;

[0015] After the position of the laser emitting device and the position of the camera are adjusted, the environmental parameters in the scene are collected, and the state of the scene is defined according to the environmental parameters in the scene; the state of the scene includes a non-lighting state and a lighting state;

[0016] If the scene is in an unlit state, the camera shoots the unlit scene as the motion platform moves dynamically, so as to collect a plurality of unlit environment pictures of the scene;

[0017] Based on a plurality of unlit environment pictures of the scene, corresponding shooting times are matched, and a first scene picture set is constructed.

[0018] Optionally, the triggering of the change of the lighting state based on the completion of the acquisition of the first scene picture set, defining the lighting state of the scene, starting the laser emission device to achieve fill light, and at the same time, the camera shoots the scene of the lighting state as the motion platform moves dynamically to acquire the second scene picture set, including:

[0019] Monitor the collection progress of the first scene picture set in real time, and define the time when the collection of the first scene picture set is completed;

[0020] triggering a lighting component of the scene based on the moment when the collection of the first scene picture set is completed, and outputting light to the environment according to the lighting component;

[0021] Collect the spatial layout style of the scene, and associate the spatial layout style and spatial area of ​​the scene;

[0022] Match the lighting pattern of the lighting fixtures according to the spatial layout style and spatial area;

[0023] The lighting state of the scene is defined based on the lighting mode of the lighting component, and the laser emission device is started to achieve fill light;

[0024] If the scene is in an illuminated state, the camera shoots the scene in the illuminated state as the motion platform moves dynamically, so as to collect a plurality of environmental pictures of the illumination of the scene;

[0025] Based on a plurality of environmental pictures of the lighting of the scene, the corresponding shooting times are matched, and a second scene picture set is constructed.

[0026] Optionally, associating the second scene picture set and the first scene picture set, and defining a frame difference picture sequence based on picture comparison of the same time frame, includes:

[0027] Freeze the second scene picture set and the first scene picture set, and dynamically match the time frames based on the second scene picture set and the first scene picture set;

[0028] Associating the second scene picture set with the first scene picture set, and defining a correlation coefficient between the second scene picture set and the first scene picture set;

[0029] defining a correlation level according to a correlation coefficient between the second scene picture set and the first scene picture set;

[0030] At this level of correlation, multiple time frames are acquired;

[0031] Filter the top three best timeframes based on multiple timeframes and correlation coefficients;

[0032] In the best first three time frames, triggering a picture comparison between the second scene picture set and the first scene picture set based on the same time frame;

[0033] Defining a frame difference picture sequence according to picture comparison between the second scene picture set and the first scene picture set to output three frame difference picture sequences;

[0034] An optimal frame difference picture sequence is defined based on the comparison of three frame difference picture sequences.

[0035] Optionally, defining the pixel values ​​of the frame difference picture sequence, marking abnormal features according to the pixel values, and defining the abnormal positions where the abnormal features are located, includes:

[0036] Freeze the best frame difference picture sequence;

[0037] Defining the value of each pixel based on the best frame difference picture sequence;

[0038] A pixel value difference is defined based on the comparison between the pixel values, and an abnormal part is marked according to each pixel value difference;

[0039] Perform targeted exception processing based on the abnormal part to construct the corresponding abnormal features;

[0040] The abnormal features are frozen, and the abnormal positions where the abnormal features are located are defined according to the abnormal features and the three-dimensional space of the scene.

[0041] Optionally, the abnormal position where the abnormal feature is frozen is defined with a brightness change gradient based on a brightness contrast of the abnormal position in the second scene picture set, including:

[0042] Freeze the abnormal position where the abnormal feature is located;

[0043] Triggering position detection based on the abnormal position where the abnormal feature is located;

[0044] In the location detection, a plurality of surrounding environment areas are defined according to the abnormal location where the abnormal features are located;

[0045] Defining regional brightness of each region according to regional contrast between a plurality of surrounding environment regions;

[0046] The fill light mode of the laser emission device is triggered according to the contrast between the regional brightness of each area, so as to ensure the correspondence between the regional brightness of each area and the brightness of the abnormal position where the abnormal feature is located;

[0047] In the second scene picture set, a plurality of corresponding brightnesses are defined based on the abnormal position where the abnormal feature is located and each time frame;

[0048] Comparison is performed based on multiple brightnesses, and a brightness difference between two adjacent brightnesses is defined. At this time, multiple brightness differences are collected, and a brightness change gradient is defined.

[0049] Optionally, the method of defining the final position of the pinhole camera according to the detection of the brightness change gradient of each abnormal position includes:

[0050] Freeze the brightness change gradient of each abnormal position;

[0051] Based on the brightness change gradient of each abnormal position, the corresponding pinhole camera detection table is matched, and the matching coefficient of each abnormal position is located.

[0052] Optionally, the method of defining the final position of the pinhole camera according to the detection of the brightness change gradient of each abnormal position further includes:

[0053] Defining the best abnormal position according to the comparison of matching coefficients of various abnormal positions;

[0054] Trigger pinhole detection and brightness detection based on the best abnormal position, and define the judgment parameters of the pinhole camera based on the pinhole detection and brightness detection;

[0055] If the judgment parameter of the pinhole camera is greater than the preset parameter threshold, the best abnormal position is defined as the final position of the pinhole camera.

[0056] Optionally, the collaborative detection method based on the motion platform and lighting further includes:

[0057] Freeze the best abnormal position;

[0058] Match the brightness in each time frame based on the best anomaly position and define the brightness change amount;

[0059] Monitor the best abnormal position in real time and define the displacement change amount under the illumination state of the best abnormal position;

[0060] The final position of the pinhole camera is determined based on the brightness change and displacement change.

[0061] In addition, an embodiment of the present invention further provides a collaborative detection system based on a motion platform and lighting, and the collaborative detection system based on a motion platform and lighting includes:

[0062] A first image module is used to carry a laser emitting device and a camera on a motion platform, and the camera takes pictures of a scene without lighting as the motion platform moves dynamically to collect a first scene image set; at this time, the laser emitting device and the camera are in a collaborative mode;

[0063] The second picture module is used to trigger the change of the lighting state based on the completion of the collection of the first scene picture set, and define the lighting state of the scene, start the laser emission device to achieve fill light, and at the same time, the camera shoots the scene of the lighting state as the motion platform moves dynamically to collect the second scene picture set;

[0064] A picture sequence module, used for associating the second scene picture set with the first scene picture set, and defining a frame difference picture sequence based on picture comparison of the same time frame;

[0065] The abnormal position module is used to define the value of each pixel in the frame difference picture sequence, mark the abnormal features according to the value of each pixel, and define the abnormal position where the abnormal features are located;

[0066] A brightness module, used to freeze the abnormal position where the abnormal feature is located, and define a brightness change gradient based on the brightness contrast of the abnormal position in the second scene picture set;

[0067] The detection module is used to define the final position of the pinhole camera based on the detection of the brightness change gradient of each abnormal position.

[0068] In an embodiment of the present invention, through the method in the embodiment of the present invention, a laser emitting device and a camera are carried on a motion platform, and the laser emitting device and the camera are in a collaborative mode. Image control is performed based on the illumination state and the non-illumination state of the scene by the laser emitting device and the camera. At this time, a second scene image set and a first scene image set are constructed, and a frame difference image sequence is defined based on image comparison of the same time frame; each pixel value of the frame difference image sequence is defined, and abnormal features are marked according to each pixel value and abnormal positions where the abnormal features are located are defined, the abnormal positions where the abnormal features are located are frozen, and a brightness change gradient is defined based on the brightness comparison of the abnormal positions in the second scene image set; the final position of the pinhole camera is defined based on the detection of the brightness change gradient of each abnormal position, thereby controlling the final position of the pinhole camera based on multiple dimensions, and achieving a better detection effect of a high-precision pinhole camera based on a single light source, reducing the interference of other parameters, and effectively reducing the false alarm rate of the pinhole camera in this scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1is a schematic flow chart of a collaborative detection method based on a motion platform and lighting in an embodiment of the present invention;

[0071] Figure 2 is a flow chart of S11 in the collaborative detection method based on a motion platform and lighting in an embodiment of the present invention;

[0072] Figure 3 is a flow chart of S12 in the collaborative detection method based on a motion platform and lighting in an embodiment of the present invention;

[0073] Figure 4 is a flow chart of S13 in the collaborative detection method based on a motion platform and lighting in an embodiment of the present invention;

[0074] Figure 5 is a flow chart of S14 in the collaborative detection method based on a motion platform and lighting in an embodiment of the present invention;

[0075] Figure 6 is a flow chart of S15 in the collaborative detection method based on a motion platform and lighting in an embodiment of the present invention;

[0076] Figure 7 is a flow chart of S16 in the collaborative detection method based on a motion platform and lighting in an embodiment of the present invention;

[0077] Figure 8 Schematic diagram of the structure of a cooperative detection system based on a motion platform and lighting in an embodiment of the present invention;

[0078] Fig. 9 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0079] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0080] Example

[0081] See also Figures 1 to 8 , a collaborative detection method based on a motion platform and lighting, applied to the collaborative detection scene of a pinhole camera; the collaborative detection method based on a motion platform and lighting includes:

[0082] See also Figure 2S11: The motion platform carries a laser emitting device and a camera, and the camera shoots a scene without lighting as the motion platform moves dynamically to collect a first scene picture set; at this time, the laser emitting device and the camera are in a collaborative mode;

[0083] In the specific implementation process of the present invention, the specific steps may be:

[0084] S111: Carrying a laser emitting device and a camera on a motion platform, and locating a position of the laser emitting device and a position of the camera;

[0085] S112: collecting regional parameters of the bearing surface of the motion platform, adjusting the position of the laser emitting device and the position of the camera according to the regional parameters of the bearing surface and the scene type, and defining a collaborative mode according to the position of the laser emitting device and the position of the camera. At this time, the laser emitting device and the camera are in the collaborative mode, and the illumination node of the laser emitting device and the shooting node of the camera are adjusted in the collaborative mode;

[0086] S113: After the position of the laser emitting device and the position of the camera are adjusted, the environmental parameters in the scene are collected, and the state of the scene is defined according to the environmental parameters in the scene; the state of the scene includes a non-illuminated state and an illuminated state;

[0087] S114: If the scene is in a non-illuminated state, the camera shoots the scene in the non-illuminated state as the motion platform moves dynamically, so as to collect a plurality of non-illuminated environment pictures of the scene;

[0088] S115: Match corresponding shooting times based on a plurality of unlit environment pictures of the scene, and construct a first scene picture set.

[0089] In an embodiment of the present invention, a laser emitting device and a camera are carried on a motion platform, and the motion platform drives the laser emitting device and the camera to move dynamically. At this time, the position of the laser emitting device and the camera are located, and the position of the laser emitting device and the camera is controlled, so as to reasonably arrange the position of the laser emitting device and the camera.

[0090] Among them, the area parameters of the bearing surface of the motion platform are collected, the position of the laser emitting device and the position of the camera are regulated according to the area parameters of the bearing surface and the scene type, and a collaborative mode is defined according to the position of the laser emitting device and the position of the camera, so that the laser emitting device and the camera can work collaboratively according to the collaborative mode. At this time, the laser emitting device and the camera are in the collaborative mode, and the illumination node of the laser emitting device and the shooting node of the camera are regulated in the collaborative mode.

[0091] Furthermore, after the position of the laser emitting device and the position of the camera are adjusted, the environmental parameters in the scene are collected, and the state of the scene is defined according to the environmental parameters in the scene to facilitate lighting control of the scene, thereby realizing state control of the scene. At this time, the state of the scene includes an unlit state and a lit state.

[0092] At this time, if the scene is in an unlit state, the camera will shoot the unlit scene as the motion platform moves dynamically to collect multiple unlit environment pictures of the scene; based on the multiple unlit environment pictures of the scene, the corresponding shooting time is matched, and a first scene picture set is constructed, so as to control the unlit state of the scene according to the first scene picture set, thereby further controlling the first scene picture set.

[0093] See also Figure 3 , S12: triggering a change in the lighting state based on the completion of the collection of the first scene picture set, defining the lighting state of the scene, starting the laser emission device to achieve fill light, and at the same time, the camera shoots the scene of the lighting state as the motion platform moves dynamically to collect the second scene picture set;

[0094] In the specific implementation process of the present invention, the specific steps may be:

[0095] S121: monitoring the collection progress of the first scene picture set in real time, and defining the time when the collection of the first scene picture set is completed;

[0096] S122: triggering a lighting component of the scene based on the moment when the collection of the first scene picture set is completed, and outputting light to the environment according to the lighting component;

[0097] S123: Collecting the spatial layout style of the scene, and associating the spatial layout style and spatial area of ​​the scene;

[0098] S124: matching the lighting mode of the lighting fixture according to the spatial layout style and the spatial area;

[0099] S125: defining the lighting state of the scene based on the lighting mode of the lighting component, and starting the laser emitting device to achieve fill light;

[0100] S126: If the scene is in an illuminated state, the camera shoots the scene in the illuminated state as the motion platform moves dynamically, so as to collect a plurality of environmental images of the illumination of the scene;

[0101] S127: Match corresponding shooting times based on a plurality of environmental pictures of the lighting of the scene, and construct a second scene picture set.

[0102] In an embodiment of the present invention, the collection progress of the first scene picture set is monitored in real time, and the moment when the collection of the first scene picture set is completed is defined, so as to automatically trigger the state change of the scene, thereby triggering the lighting components of the scene based on the moment when the collection of the first scene picture set is completed, and outputting light to the environment according to the lighting components, so as to change the state of the scene to the lighting state, and manage the lighting state, thereby realizing automatic change of the scene between the non-lighting state and the lighting state.

[0103] At this time, the spatial layout style of the scene is collected, and the spatial layout style and spatial area of ​​the scene are associated; the light-emitting mode of the lighting fixture is matched according to the spatial layout style and spatial area, so as to facilitate the management of the light-emitting mode of the lighting fixture, and then control the working power of the lighting fixture, so as to facilitate reasonable lighting for the scene.

[0104] Furthermore, the lighting state of the scene is defined based on the light emission mode of the lighting component, and the laser emitting device is started to realize fill light, so that the laser emitting device is fully utilized so as to facilitate the use of the laser emitting device for fill light.

[0105] Therefore, if the scene is in a lighting state, the camera will shoot the scene in the lighting state as the motion platform moves dynamically to collect multiple lighting environment pictures of the scene; based on the multiple lighting environment pictures of the scene, the corresponding shooting time is matched, and a second scene picture set is constructed, so as to control the lighting state of the scene according to the second scene picture set, thereby further controlling the second scene picture set.

[0106] See also Figure 4 , S13: Associating the second scene picture set and the first scene picture set, and defining a frame difference picture sequence based on picture comparison of the same time frame;

[0107] In the specific implementation process of the present invention, the specific steps may be:

[0108] S131: Freeze the second scene picture set and the first scene picture set, and perform dynamic matching of time frames based on the second scene picture set and the first scene picture set;

[0109] S132: Associating the second scene picture set with the first scene picture set, and defining a correlation coefficient between the second scene picture set and the first scene picture set;

[0110] S133: defining a correlation level according to a correlation coefficient between the second scene picture set and the first scene picture set;

[0111] S134: Under the correlation level, collect multiple time frames;

[0112] S135: Filtering the best top three time frames based on multiple time frames and correlation coefficients;

[0113] S136: triggering picture comparison between the second scene picture set and the first scene picture set based on the same time frame in the best first three time frames;

[0114] S137: defining a frame difference picture sequence according to a picture comparison between the second scene picture set and the first scene picture set, so as to output three frame difference picture sequences;

[0115] S138: Defining an optimal frame difference picture sequence based on comparison of three frame difference picture sequences.

[0116] In an embodiment of the present invention, the second scene picture set and the first scene picture set are frozen, and dynamic matching of time frames is performed based on the second scene picture set and the first scene picture set; the second scene picture set and the first scene picture set are associated, and a correlation coefficient between the second scene picture set and the first scene picture set is defined, so as to define a correlation level according to the correlation coefficient between the second scene picture set and the first scene picture set, thereby presenting the degree of correlation between the second scene picture set and the first scene picture set through the correlation level.

[0117] At this time, at this correlation level, multiple time frames are collected; the best top three time frames are screened based on the multiple time frames and the correlation coefficients, so as to facilitate targeted management and control of the best top three time frames, and achieve preliminary screening.

[0118] Therefore, in the best first three time frames, the picture comparison between the second scene picture set and the first scene picture set is triggered based on the same time frame; a frame difference picture sequence is defined according to the picture comparison between the second scene picture set and the first scene picture set to output three frame difference picture sequences; an optimal frame difference picture sequence is defined based on the comparison of the three frame difference picture sequences. At this time, the picture differences between the second scene picture set and the first scene picture set are presented according to the optimal frame difference picture sequence, so as to facilitate anomaly detection by utilizing the picture differences between the second scene picture set and the first scene picture set, thereby performing positioning detection on the pinhole camera and ensuring the detection effect of the pinhole camera.

[0119] See also Figure 5 , S14: defining the pixel values ​​of the frame difference picture sequence, marking abnormal features according to the pixel values, and defining the abnormal positions where the abnormal features are located;

[0120] In the specific implementation process of the present invention, the specific steps may be:

[0121] S141: freeze the best frame difference picture sequence;

[0122] S142: defining a value of each pixel based on the best frame difference picture sequence;

[0123] S143: defining a pixel value difference based on a comparison between the pixel values, and defining a marked abnormal part according to each pixel value difference;

[0124] S144: performing targeted abnormal processing based on the abnormal part to construct corresponding abnormal features;

[0125] S145: Freeze the abnormal feature, and define the abnormal position where the abnormal feature is located according to the abnormal feature and the three-dimensional space of the scene.

[0126] In the specific implementation process of the present invention, the best frame difference picture sequence is frozen; the value of each pixel is defined based on the best frame difference picture sequence; the pixel value difference is defined based on the comparison between the pixel values, and the abnormal part is marked according to the definition of each pixel value difference, so as to control the abnormal part and perform targeted processing on the abnormal part.

[0127] At this time, targeted abnormal processing is performed based on the abnormal part to construct the corresponding abnormal features; the abnormal features are frozen, and the abnormal positions of the abnormal features are defined according to the abnormal features and the three-dimensional space of the scene, so as to further control the position of the pinhole camera according to the abnormal positions of the abnormal features, thereby improving the accuracy of the position of the pinhole camera.

[0128] See also Figure 6 , S15: freeze the abnormal position where the abnormal feature is located, and define a brightness change gradient based on the brightness contrast of the abnormal position in the second scene picture set;

[0129] In the specific implementation process of the present invention, the specific steps may be:

[0130] S151: freeze the abnormal position where the abnormal feature is located;

[0131] S152: triggering position detection based on the abnormal position where the abnormal feature is located;

[0132] S153: In the position detection, a plurality of surrounding environment areas are defined according to the abnormal position where the abnormal feature is located;

[0133] S154: defining a regional brightness of each region according to a regional contrast between a plurality of surrounding environment regions;

[0134] S155: triggering a fill light mode of the laser emitting device according to a comparison between the regional brightness of each area, so as to ensure correspondence between the regional brightness of each area and the brightness of the abnormal position where the abnormal feature is located;

[0135] S156: In the second scene picture set, define corresponding multiple brightnesses based on the abnormal position where the abnormal feature is located and each time frame;

[0136] S157: performing comparison according to the multiple brightnesses and defining the brightness difference between two adjacent brightnesses. At this time, multiple brightness differences are collected and a brightness change gradient is defined.

[0137] In the specific implementation process of the present invention, the abnormal position where the abnormal feature is located is frozen so as to trigger position detection based on the abnormal position where the abnormal feature is located, thereby performing brightness detection for position detection and controlling the surrounding environment area of ​​the abnormal position where the abnormal feature is located.

[0138] Therefore, in this position detection, multiple surrounding environment areas are defined according to the abnormal position where the abnormal feature is located; the regional brightness of each area is defined according to the regional comparison between the multiple surrounding environment areas, thereby defining the regional brightness of each area, and then controlling the brightness of the surrounding environment of the abnormal position where the abnormal feature is located.

[0139] Therefore, the fill light mode of the laser emitting device is triggered according to the contrast between the regional brightness of each area to ensure the correspondence between the regional brightness of each area and the brightness of the abnormal position where the abnormal feature is located; at the same time, in the second scene picture set, multiple corresponding brightnesses are defined based on the abnormal position where the abnormal feature is located and each time frame; comparison is performed based on the multiple brightnesses, and the brightness difference between two adjacent brightnesses is defined. At this time, multiple brightness differences are collected, and a brightness change gradient is defined, and then the position with a large brightness change is presented through the processing of the brightness change gradient, thereby controlling the position of the pinhole camera.

[0140] See also Figure 7 and 8 , S16: defining the final position of the pinhole camera according to the detection of the brightness change gradient of each abnormal position;

[0141] In the specific implementation process of the present invention, the specific steps may be:

[0142] S161: freeze the brightness change gradient of each abnormal position;

[0143] S162: matching the corresponding pinhole camera detection table based on the brightness change gradient of each abnormal position, and locating the matching coefficient of each abnormal position;

[0144] S163: defining the best abnormal position according to the comparison of the matching coefficients of the various abnormal positions;

[0145] S164: triggering pinhole detection and brightness detection based on the best abnormal position, and defining judgment parameters of the pinhole camera according to the pinhole detection and brightness detection;

[0146] S165: If the judgment parameter of the pinhole camera is greater than the preset parameter threshold, the best abnormal position is defined as the final position of the pinhole camera.

[0147] Among them, the brightness change gradient of each abnormal position is frozen; the detection table of the corresponding pinhole camera is matched based on the brightness change gradient of each abnormal position, and the matching coefficient of each abnormal position is located; and the best abnormal position is defined according to the comparison of the matching coefficients of each abnormal position.

[0148] Therefore, pinhole detection and brightness detection are triggered based on the optimal abnormal position, and the judgment parameters of the pinhole camera are defined according to the pinhole detection and brightness detection; if the judgment parameters of the pinhole camera are greater than the preset parameter threshold, the optimal abnormal position is defined as the final position of the pinhole camera, thereby clarifying the final position of the pinhole camera and ensuring the detection effect of the pinhole camera.

[0149] The collaborative detection method based on the motion platform and lighting also includes: freezing the best abnormal position; matching the brightness in each time frame based on the best abnormal position and defining the brightness change; real-time monitoring of the best abnormal position and defining the displacement change under the lighting condition of the best abnormal position; and determining the final position of the pinhole camera based on the brightness change and the displacement change.

[0150] At this time, the brightness change gradient is defined based on the brightness contrast of the abnormal position in the second scene picture set; the final position of the pinhole camera is defined according to the detection of the brightness change gradient of each abnormal position, so that the final position of the pinhole camera is controlled based on multiple dimensions, and a better high-precision pinhole camera detection effect is achieved on the basis of a single light source, which reduces the interference of other parameters and effectively reduces the false alarm rate of the pinhole camera in this scene.

[0151] Specifically, step 1: First, mark the light and dark images obtained by the camera as A and B respectively. Step 2: For each pair of light and dark images at the same time, obtain the frame difference image sequence U of the camera in the light and dark conditions. Step 3: For the image sequence A, according to the change of the time dimension, calculate the image rotation matrix of each pair of the latter moment relative to the previous moment, and obtain the matrix sequence V.

[0152] Step 4: Compare the pixel values ​​in the image sequence U with the set threshold. The bright spots above the threshold are the possible pinhole camera positions. Then, based on the illuminated image corresponding to the first moment, a spatial coordinate system is established to determine the spatial position of the bright spot. The bright spots at subsequent moments can be normalized to the same spatial coordinate system through spatial transformation matrices including rotation matrices.

[0153] Step 5: Calculate the relative displacement and brightness gradient based on the spatial position of the bright spot at each moment calculated in step 4. Refer to the spatial displacement value and gradient size, use threshold filtering to achieve position filtering, and finally output the pinhole camera detection result.

[0154] In an embodiment of the present invention, through the method in the embodiment of the present invention, a laser emitting device and a camera are carried on a motion platform, and the laser emitting device and the camera are in a collaborative mode. Based on the laser emitting device and the camera, image control is performed on the illumination state and the non-illumination state of the scene. At this time, a second scene image set and a first scene image set are constructed, and a frame difference image sequence is defined based on the image comparison of the same time frame; each pixel value of the frame difference image sequence is defined, and abnormal features are marked according to each pixel value and the abnormal position where the abnormal features are located is defined, the abnormal position where the abnormal features are located is frozen, and a brightness change gradient is defined based on the brightness comparison of the abnormal position in the second scene image set; the final position of the pinhole camera is defined according to the detection of the brightness change gradient of each abnormal position, so that the final position of the pinhole camera is controlled based on multiple dimensions, and a better high-precision pinhole camera detection effect is achieved on the basis of a single light source, the interference of other parameters is reduced, and the false alarm rate of the scene for the pinhole camera is effectively reduced. At the same time, the image processing method of the continuous motion scene light and dark image sequence is used to realize the recognition and detection of high-precision pinhole cameras.

[0155] The method proposed in the present invention benefits from the fact that the system can make full use of the characteristic that the reflectivity of the cat's eye target decays sharply when the incident light deflection angle is large, so it can obtain accuracy that is difficult to achieve with other methods. Since the present invention introduces a scene image sequence in a moving state, smooth high-reflective targets are easy to filter out because the highlights are continuously moving. The method proposed in the present invention can effectively reduce the false alarm rate. At the same time, the solution proposed in the present invention only requires a camera, a laser light source and corresponding optical and mechanical components, and its performance can surpass that of a multi-light source system, reducing system cost and complexity.

[0156] The present invention proposes a scene light and dark image sequence processing method based on a motion platform, which makes full use of the smoothness of high-reflection objects. According to the assumption that cat's eye targets are small in size and high-reflection targets are large in size, the smooth moving highlight areas in the space are screened out in the image sequence, while the bright spots with fixed spatial positions and large gradient changes in the time dimension are retained, thereby filtering out high-reflection interference and effectively reducing the false alarm rate of the system.

[0157] Example

[0158] See also Figure 8 , Figure 8 It is a schematic diagram of the structural composition of a collaborative detection system based on a motion platform and lighting in an embodiment of the present invention.

[0159] like Figure 8 As shown, a collaborative detection system based on a motion platform and lighting, the collaborative detection system based on a motion platform and lighting includes:

[0160] The first image module 21 is used to carry the laser emitting device and the camera on the motion platform, and the camera takes pictures of the scene without lighting as the motion platform moves dynamically to collect a first scene image set; at this time, the laser emitting device and the camera are in a collaborative mode;

[0161] The second picture module 22 is used to trigger the change of the lighting state based on the completion of the collection of the first scene picture set, and define the lighting state of the scene, start the laser emission device to achieve fill light, and at the same time, the camera shoots the scene of the lighting state as the motion platform moves dynamically to collect the second scene picture set;

[0162] A picture sequence module 23, configured to associate the second scene picture set with the first scene picture set, and define a frame difference picture sequence based on picture comparison of the same time frame;

[0163] The abnormal position module 24 is used to define the value of each pixel of the frame difference picture sequence, mark the abnormal feature according to the value of each pixel, and define the abnormal position where the abnormal feature is located;

[0164] A brightness module 25, used to freeze the abnormal position where the abnormal feature is located, and define a brightness change gradient based on the brightness contrast of the abnormal position in the second scene picture set;

[0165] The detection module 26 is used to define the final position of the pinhole camera according to the detection of the brightness change gradient of each abnormal position.

[0166] Example

[0167] See also Fig. 9 , refer to the following Fig. 9The electronic device 40 according to this embodiment of the present invention will be described. Fig. 9 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0168] like Fig. 9 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0169] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0170] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0171] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0172] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0173] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 44. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 45. Fig. 9 As shown, the network adapter 45 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Fig. 9Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup planning systems.

[0174] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0175] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0176] In addition, the collaborative detection method and system based on motion platform and lighting provided in the embodiments of the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A collaborative detection method based on a motion platform and lighting, characterized in that: Applied to collaborative detection scenarios of pinhole cameras; The collaborative detection method based on the motion platform and lighting comprises: The motion platform carries a laser emitting device and a camera, and the camera shoots a scene without lighting as the motion platform moves dynamically to collect a first scene picture set; at this time, the laser emitting device and the camera are in a collaborative mode; The change of the lighting state is triggered based on the completion of the collection of the first scene picture set, and the lighting state of the scene is defined, and the laser emission device is started to achieve fill light. At the same time, the camera shoots the scene of the lighting state as the motion platform moves dynamically to collect the second scene picture set; Associating the second scene picture set and the first scene picture set, and defining a frame difference picture sequence based on picture comparison of the same time frame; Defining the pixel values ​​of the frame difference image sequence, marking abnormal features according to the pixel values, and defining the abnormal positions where the abnormal features are located; Freeze the abnormal position where the abnormal feature is located, and define a brightness change gradient based on the brightness contrast of the abnormal position in the second scene picture set; The final position of the pinhole camera is defined based on the detection of the brightness change gradient at each abnormal position.

2. The collaborative detection method based on motion platform and lighting according to claim 1 is characterized in that: The motion platform carries a laser emitting device and a camera, and the camera shoots a scene without lighting as the motion platform moves dynamically to collect a first scene picture set; At this point, the laser emitting device and the camera are in collaborative mode, including: Carrying a laser emitting device and a camera on a motion platform, and locating the positions of the laser emitting device and the camera; Collect regional parameters of the bearing surface of the motion platform, adjust the position of the laser emitting device and the position of the camera according to the regional parameters of the bearing surface and the scene type, and define a collaborative mode according to the position of the laser emitting device and the position of the camera. At this time, the laser emitting device and the camera are in the collaborative mode, and the illumination node of the laser emitting device and the shooting node of the camera are adjusted in the collaborative mode; After the position of the laser emitting device and the position of the camera are adjusted, the environmental parameters in the scene are collected, and the state of the scene is defined according to the environmental parameters in the scene; the state of the scene includes a non-lighting state and a lighting state; If the scene is in an unlit state, the camera shoots the unlit scene as the motion platform moves dynamically, so as to collect a plurality of unlit environment pictures of the scene; Based on a plurality of unlit environment pictures of the scene, corresponding shooting times are matched, and a first scene picture set is constructed.

3. The collaborative detection method based on motion platform and lighting according to claim 2 is characterized in that: The method triggers a change in the lighting state based on the completion of the acquisition of the first scene picture set, defines the lighting state of the scene, starts a laser emission device to achieve fill light, and at the same time, the camera shoots the scene of the lighting state as the motion platform moves dynamically to acquire a second scene picture set, including: Monitor the collection progress of the first scene picture set in real time, and define the time when the collection of the first scene picture set is completed; triggering a lighting component of the scene based on the moment when the collection of the first scene picture set is completed, and outputting light to the environment according to the lighting component; Collect the spatial layout style of the scene, and associate the spatial layout style and spatial area of ​​the scene; Match the lighting pattern of the lighting fixtures according to the spatial layout style and spatial area; The lighting state of the scene is defined based on the lighting mode of the lighting component, and the laser emission device is started to achieve fill light; If the scene is in an illuminated state, the camera shoots the scene in the illuminated state as the motion platform moves dynamically, so as to collect a plurality of environmental pictures of the illumination of the scene; Based on a plurality of environmental pictures of the lighting of the scene, the corresponding shooting times are matched, and a second scene picture set is constructed.

4. The collaborative detection method based on motion platform and lighting according to claim 3 is characterized in that: The associating the second scene picture set and the first scene picture set, and defining a frame difference picture sequence based on picture comparison of the same time frame, includes: Freeze the second scene picture set and the first scene picture set, and dynamically match the time frames based on the second scene picture set and the first scene picture set; Associating the second scene picture set with the first scene picture set, and defining a correlation coefficient between the second scene picture set and the first scene picture set; defining a correlation level according to a correlation coefficient between the second scene picture set and the first scene picture set; At this level of correlation, multiple time frames are acquired; Filter the top three best timeframes based on multiple timeframes and correlation coefficients; In the best first three time frames, triggering a picture comparison between the second scene picture set and the first scene picture set based on the same time frame; Defining a frame difference picture sequence according to picture comparison between the second scene picture set and the first scene picture set to output three frame difference picture sequences; An optimal frame difference picture sequence is defined based on the comparison of three frame difference picture sequences.

5. The collaborative detection method based on motion platform and lighting according to claim 4 is characterized in that: The step of defining the pixel values ​​of the frame difference picture sequence, marking abnormal features according to the pixel values, and defining the abnormal positions where the abnormal features are located includes: Freeze the best frame difference picture sequence; Defining the value of each pixel based on the best frame difference picture sequence; A pixel value difference is defined based on the comparison between the pixel values, and an abnormal part is marked according to each pixel value difference; Perform targeted exception processing based on the abnormal part to construct the corresponding abnormal features; The abnormal features are frozen, and the abnormal positions where the abnormal features are located are defined according to the abnormal features and the three-dimensional space of the scene.

6. The collaborative detection method based on motion platform and lighting according to claim 5 is characterized in that: The abnormal position where the freeze abnormal feature is located, and defining a brightness change gradient based on the brightness contrast of the abnormal position in the second scene picture set, include: Freeze the abnormal position where the abnormal feature is located; Triggering position detection based on the abnormal position where the abnormal feature is located; In the location detection, a plurality of surrounding environment areas are defined according to the abnormal location where the abnormal features are located; Defining regional brightness of each region according to regional contrast between a plurality of surrounding environment regions; The fill light mode of the laser emission device is triggered according to the contrast between the regional brightness of each area, so as to ensure the correspondence between the regional brightness of each area and the brightness of the abnormal position where the abnormal feature is located; In the second scene picture set, a plurality of corresponding brightnesses are defined based on the abnormal position where the abnormal feature is located and each time frame; Comparison is performed based on multiple brightnesses, and a brightness difference between two adjacent brightnesses is defined. At this time, multiple brightness differences are collected, and a brightness change gradient is defined.

7. The collaborative detection method based on motion platform and lighting according to claim 6 is characterized in that: The method of defining the final position of the pinhole camera according to the detection of the brightness change gradient of each abnormal position includes: Freeze the brightness change gradient of each abnormal position; Based on the brightness change gradient of each abnormal position, the corresponding pinhole camera detection table is matched, and the matching coefficient of each abnormal position is located.

8. The collaborative detection method based on motion platform and lighting according to claim 7 is characterized in that: The method of defining the final position of the pinhole camera according to the detection of the brightness change gradient of each abnormal position also includes: Defining the best abnormal position according to the comparison of matching coefficients of various abnormal positions; Trigger pinhole detection and brightness detection based on the best abnormal position, and define the judgment parameters of the pinhole camera based on the pinhole detection and brightness detection; If the judgment parameter of the pinhole camera is greater than the preset parameter threshold, the best abnormal position is defined as the final position of the pinhole camera.

9. The collaborative detection method based on motion platform and lighting according to claim 8, characterized in that: The collaborative detection method based on the motion platform and lighting also includes: Freeze the best abnormal position; Match the brightness in each time frame based on the best anomaly position and define the brightness change amount; Monitor the best abnormal position in real time and define the displacement change amount under the illumination state of the best abnormal position; The final position of the pinhole camera is determined based on the brightness change and displacement change.

10. A collaborative detection system based on a motion platform and lighting, characterized in that: The collaborative detection system based on motion platform and lighting is applied to the collaborative detection method based on motion platform and lighting as claimed in any one of claims 1 to 9, and the collaborative detection system based on motion platform and lighting includes: A first image module is used to carry a laser emitting device and a camera on a motion platform, and the camera takes pictures of a scene without lighting as the motion platform moves dynamically to collect a first scene image set; at this time, the laser emitting device and the camera are in a collaborative mode; The second picture module is used to trigger the change of the lighting state based on the completion of the collection of the first scene picture set, and define the lighting state of the scene, start the laser emission device to achieve fill light, and at the same time, the camera shoots the scene of the lighting state as the motion platform moves dynamically to collect the second scene picture set; A picture sequence module, used for associating the second scene picture set with the first scene picture set, and defining a frame difference picture sequence based on picture comparison of the same time frame; The abnormal position module is used to define the value of each pixel in the frame difference picture sequence, mark the abnormal features according to the value of each pixel, and define the abnormal position where the abnormal features are located; A brightness module, used to freeze the abnormal position where the abnormal feature is located, and define a brightness change gradient based on the brightness contrast of the abnormal position in the second scene picture set; The detection module is used to define the final position of the pinhole camera based on the detection of the brightness change gradient of each abnormal position.

Images