CN112258479B - T0 detection method and device based on image characteristics and storage medium - Google Patents
T0 detection method and device based on image characteristics and storage medium Download PDFInfo
- Publication number
- CN112258479B CN112258479B CN202011141921.1A CN202011141921A CN112258479B CN 112258479 B CN112258479 B CN 112258479B CN 202011141921 A CN202011141921 A CN 202011141921A CN 112258479 B CN112258479 B CN 112258479B
- Authority
- CN
- China
- Prior art keywords
- image
- target
- detection
- video image
- action
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 149
- 238000012545 processing Methods 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000011895 specific detection Methods 0.000 claims abstract description 16
- 230000008859 change Effects 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 11
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 9
- 230000009471 action Effects 0.000 claims description 60
- 238000001914 filtration Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 6
- 238000007599 discharging Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000011161 development Methods 0.000 abstract description 7
- 230000002411 adverse Effects 0.000 abstract description 5
- 230000000295 complement effect Effects 0.000 abstract description 4
- 230000005540 biological transmission Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 3
- 238000013139 quantization Methods 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 235000002566 Capsicum Nutrition 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 238000011410 subtraction method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application provides a T0 detection method, a device and a storage medium based on image characteristics, wherein the method comprises the following steps: synthesizing a source video image of a detection target obtained in real time with a standard time stamp to obtain a target video image; cutting the specific detection area of the target video image to obtain a cut video image; performing differential processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0; acquiring T0 information of the detection target according to the standard time stamp on the target frame image; therefore, the application solves the problem that the existing technology has errors in the detection method of the flight test product T0 due to manual observation, judgment and complement, effectively improves the automation level and reliability of the detection system, and reduces the adverse effect of the development change of the product model on the T0 signal.
Description
Technical Field
The application relates to the technical field of measurement and control, in particular to a T0 detection method and device based on image characteristics and a storage medium.
Background
In the ranges of missile tests, aerospace launching and the like, the actions of ignition, ejection, take-off and the like of the flight test products are very key time sequence actions, and are important event reference points of other flight time sequence actions; the take-off signal is a signal for identifying an action event by detecting the action of a test product in a key time sequence, is only a real-time electric signal with voltage change, is required to be converted into a time data signal for testing, transmitting, measuring, controlling and post analysis processing of the test product, is called a take-off zero signal (T0 information for short), and is sent to each user equipment according to a specified coding format and transmission protocol; the equipment for converting the take-off signal into standard Beijing time information is called a signal console for transmitting take-off zero time, and is called a T0 console for short.
The traditional flight test product mainly depends on a take-off switch provided by a transmitting platform to perform an opening or closing action to generate an active or passive take-off pulse signal, the active or passive take-off pulse signal is transmitted to a T0 control console through a transmission line, after the T0 control console receives the take-off pulse signal, the rising or falling edge of the take-off pulse signal is taken, so that the state of an internal trigger of the take-off pulse signal is turned over, the standard time at the current moment is read, and T0 information is generated; therefore, the traditional real-time detection method for the transmitting moment is that a single-point physical detection switch performs real-time measurement, and the transmission is carried out by a main wire cable and a standby wire cable, and manual observation and judgment are assisted, so that the real-time reissue is performed. The detection method has the defects that the solidification of physical components is detected, the requirements of novel products such as non-contact products and multi-contact products are difficult to meet, the reaction time of people in the reissue process is limited, the influence of environmental factors is caused, and the like, and the requirements of T0 real-time detection along with the development of the types and the kinds of the products cannot be effectively met.
Therefore, the detection method of the prior art on the flight test product T0 has the problem of errors due to manual observation, judgment and reimbursement, and can not effectively meet the requirement of real-time detection of the T0 along with the development of the model and the type of the product.
Disclosure of Invention
Aiming at the defects in the prior art, the T0 detection method, the device and the storage medium based on the image characteristics solve the problem that errors exist in the detection method of the flight test product T0 due to manual observation, judgment and complement in the prior art, effectively improve the automation level and reliability of a detection system, and reduce the adverse effect of development change of the product model on a T0 signal.
In a first aspect, the present application provides a method for detecting T0 based on image features, the method comprising: synthesizing a source video image of a detection target obtained in real time with a standard time stamp to obtain a target video image; cutting the specific detection area of the target video image to obtain a cut video image; performing differential processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0; and acquiring the T0 information of the detection target according to the standard time stamp on the target frame image.
Optionally, performing differential processing on the cropped video image according to a preset rule to obtain a target frame image of the detection target at T0, and further including: performing differential processing on the cut video image to obtain a differential image of the moving object; performing cascade low-frequency filtering on the differential image of the moving object to obtain a filtered image sequence; and continuously judging the filtering image sequence to obtain a target frame image of the detection target at T0.
Optionally, performing continuous decision on the filtered image sequence to obtain a target frame image of the detection target at T0, including: acquiring the gray value of each frame of image in the filter image sequence; acquiring a difference value of gray values of a current frame image and an adjacent previous frame image; and when the difference value is greater than or equal to a preset threshold value, the current frame image is a target frame image of the detection target at T0.
Optionally, before acquiring the gray value of each frame of image in the target image sequence, the method further includes: and carrying out corner detection on the target image sequence according to a corner detection algorithm.
Optionally, the formula expression of the corner detection algorithm is:
where E (u, v) is the gray level change resulting from the window function movement (u, v), w (x, y) is the window function, I (x, y) is the image gray level, and I (x+u, y+v) is the translated image gray level.
Optionally, before performing differential processing on the cropped video image according to a preset rule to obtain a target frame image of the detection target at T0, the method further includes: and acquiring key actions of the detection target at T0, wherein the key actions comprise an ignition action, an ejection action, a cylinder discharging action and a take-off action.
Optionally, performing differential processing on the cropped video image according to a preset rule to obtain a target frame image of the detection target at T0, where the differential processing includes: when the key action is an ignition action, performing differential processing on the cut video image according to an inter-frame differential algorithm to obtain a target frame image of the detection target at T0; and when the key action is the ejection action, the barrel discharging action or the take-off action, performing differential processing on the cut video image according to an accumulated differential algorithm to obtain a target frame image of the detection target at T0.
In a second aspect, the present application provides an image feature-based T0 detection apparatus, the apparatus comprising: the target video image acquisition module is used for synthesizing the source video image of the detection target acquired in real time with the standard time stamp to obtain a target video image; the clipping module is used for clipping the specific detection area of the target video image to obtain a clipping video image; the difference processing module is used for carrying out difference processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0; and the transmitting moment acquisition module is used for acquiring the T0 information of the detection target according to the standard time stamp on the target frame image.
Optionally, the differential processing module further includes: the image difference processing module is used for carrying out difference processing on the cut video image to obtain a difference image of the moving object; the cascade filtering module is used for carrying out cascade low-frequency filtering on the differential image of the moving object to obtain a filtering image sequence; and the continuous judgment module is used for continuously judging the filtering image sequence to acquire a target frame image of the detection target at T0.
In a third aspect, the present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of: synthesizing a source video image of a detection target obtained in real time with a standard time stamp to obtain a target video image; cutting the specific detection area of the target video image to obtain a cut video image; performing differential processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0; and acquiring the T0 information of the detection target according to the standard time stamp on the target frame image.
The technical principle of the application is as follows:
according to the application, the standard time stamp synthesis is carried out on the source video image of the detection target, so that each frame of image in the obtained target video image has corresponding standard time information; in order to reduce detection quantity and improve detection efficiency, a specific detection area is cut on a target video image to obtain a cut video image, then a target frame image generating the key action is obtained by detecting a moving target and detecting the key action on the cut video image, and T0 information of the detection target is obtained according to standard timestamp information on the target frame image.
Compared with the prior art, the application has the following beneficial effects:
the application is a technology for detecting the emission key action of a product by utilizing key target micro-motion characteristics and automatically generating T0 information by carrying out real-time acquisition processing on digital images of single-path or multi-path emission live images. The automatic generation of the T0 information can be realized, the time delay error is reduced, the automation level and the reliability of a detection system can be effectively improved, and the adverse effect of development change of the product model on the signal generation at the transmitting moment is reduced.
Drawings
Fig. 1 is a schematic flow chart of a T0 detection method based on image features according to an embodiment of the present application;
specific steps of step S103 in fig. 2 and fig. 1;
FIG. 3 is a block flow diagram of another method for detecting T0 based on image features according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a T0 detection device based on image features according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a T0 detection system based on image features according to an embodiment of the present application;
fig. 6 is a schematic flow chart of a T0 detection system based on image features according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Fig. 1 is a schematic flow chart of a T0 detection method based on image features according to an embodiment of the present application; as shown in fig. 1, the method for detecting T0 based on image features specifically includes the following steps:
step S101, synthesizing a source video image of a detection target obtained in real time with a standard time stamp to obtain a target video image.
Specifically, standard time stamp synthesis is performed on the source video images, so that each frame of image in the target video images has corresponding time information.
Step S102, cutting specific detection areas of the target video image to obtain a cut video image.
Specifically, the specific detection area is an interested area, the specific detection area is obtained through user definition selection during initialization, and when the same source video image is subsequently subjected to cutting through the pre-stored specific detection area, the target video image is cut, and the cut video image is obtained.
And step S103, carrying out differential processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0.
Further, before performing differential processing on the cropped video image according to a preset rule to obtain a target frame image of the detection target at T0, the method further includes: and acquiring key actions of the detection target at T0, wherein the key actions comprise an ignition action, an ejection action, a cylinder discharging action and a take-off action.
Performing differential processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0, wherein the differential processing comprises the following steps: when the key action is an ignition action, performing differential processing on the cut video image according to an inter-frame differential algorithm to obtain a target frame image of the detection target at T0; and when the key action is the ejection action, the barrel discharging action or the take-off action, performing differential processing on the cut video image according to an accumulated differential algorithm to obtain a target frame image of the detection target at T0.
It should be noted that according to the emission characteristics of the detection target, the method can be divided into two categories, namely, thermal emission and cold emission, wherein the key actions of the thermal emission mainly comprise ignition and take-off, and the key actions of the cold emission mainly comprise ejection and barrel ejection; the rocket assembly for the ejection action and the thermal firing of the cold-shooting warhead has the characteristic of continuous micro-motion; in addition, according to priori knowledge, during thermal emission, the first moving target is flame sprayed by ignition at the part of the rocket engine, and only the detection part of key actions and the characteristics thereof are required to be correctly selected by a detection area and a characteristic algorithm. The moving object detection algorithm under the static background mainly comprises the following steps: inter-frame difference method, cumulative difference method, optical flow method, background subtraction method, etc. The inter-frame difference method is mainly used for detecting the change between two adjacent frames of images, directly comparing the difference of gray values of pixels corresponding to the two frames of images, and then extracting a moving target in a sequence image through a threshold value, and has the characteristics of no background accumulation and simple algorithm. The cumulative difference method detects small displacement or slow moving objects by analyzing the change of continuous images, and is suitable for detecting three key actions of ejection, barrel discharge and take-off. The inter-frame difference method is divided into a first-order difference and a second-order difference, and the main difference is that the detection sensitivity is different, so that the method is suitable for detecting the ignition key action. The inter-frame second order difference algorithm is selected in consideration of the requirements that the detected dynamic range is to be adapted to the working scenes of different cameras (high definition/standard definition, interlaced/progressive scanning), different angles (front, side, back), different distances (far, middle, near), different backgrounds (daytime, night).
Step S104, obtaining the T0 information of the detection target according to the standard time stamp on the target frame image.
The technical principle of the application is as follows:
according to the application, the standard time stamp synthesis is carried out on the source video image of the detection target, so that each frame of image in the obtained target video image has corresponding standard time information; in order to reduce detection quantity and improve detection efficiency, a specific detection area is cut on a target video image to obtain a cut video image, then a target frame image generating the key action is obtained by detecting a moving target and detecting the key action on the cut video image, and T0 information of the detection target is obtained according to standard timestamp information on the target frame image.
Compared with the prior art, the application has the following beneficial effects:
the application is a technology for detecting the emission key action of a product by utilizing key target micro-motion characteristics and automatically generating T0 information by carrying out real-time acquisition processing on digital images of single-path or multi-path emission live images. The automatic generation of the T0 information can be realized, the time delay error is reduced, the automation level and the reliability of a detection system can be effectively improved, and the adverse effect of development change of the product model on the signal generation at the transmitting moment is reduced.
As shown in fig. 2, in the specific step of step S103 in fig. 1, step S103 performs differential processing on the cropped video image according to a preset rule to obtain a target frame image of the detection target at T0, and specifically includes the following steps:
step S201, performing differential processing on the cropped video image to obtain a differential image of the moving object.
Step S202, cascade low-frequency filtering is carried out on the differential image of the moving object, and a filtered image sequence is obtained.
Step S203, acquiring a gray value of each frame of image in the filtered image sequence.
Step S204, the difference value of gray values of the current frame image and the adjacent previous frame image is obtained.
In step S205, when the difference is greater than or equal to a preset threshold, the current frame image is the target frame image of the detection target at T0.
It should be noted that, the cascade low-frequency filtering in this embodiment includes cascade low-frequency filtering using a median filter and a wiener filter, eliminating the effects of salt and pepper noise, white noise and quantization noise, and performing most of noise elimination by the median filter and the local characteristic form secondary cascade filter.
In this embodiment, the moving object detection, that is, the processing method of performing the second-order difference or the first-order accumulated difference between frames on the moving object under the static or slowly changing emission background in the specific detection area of the fixed camera (performing the image interactive clipping on the detection area of interest), detects the moving object. The local feature detection is a detection method for further confirming the detected moving target according to the specific local feature of the moving target. The method mainly comprises cascade low-frequency filtering, morphological filtering and continuous judgment, and has the main effects of performing ou classification on noise and useful signals and ensuring the accuracy and reliability of detection results; the detection of the ignition action has the advantages that the gray level extremum of the differential image is larger, the gray level extremum of other noises except impact noises is limited, and the statistical threshold value processing can be uniformly carried out; cancellation of impact noise: firstly, adopting a median filter and a wiener filter to carry out cascading low-frequency filtering to eliminate the influence of salt and pepper noise, white noise and quantization noise; and secondly, by utilizing the continuous characteristic of the ignition action signal, the characteristic that most of impact noise subjected to cascaded low-frequency filtering is discontinuous is filtered through continuous judgment. And the detection of the ejection action has small gray extreme value of the differential image and even smaller noise. The vast majority of noise elimination is accomplished through a median filter and a local characteristic form secondary cascade filter, and then the Ou of useful signals is accomplished through continuous judgment. The local characteristic form secondary cascade filtering is completed by performing two continuous corrosion operations (equivalent to form filtering) on the differential image by using two different oblique lines (a certain length and an angle) probes which are in the useful differential image and are not in noise.
In one embodiment of the present application, before acquiring the gray value of each frame of image in the target image sequence, the method further includes:
and carrying out corner detection on the target image sequence according to a corner detection algorithm.
The formula expression of the corner detection algorithm is as follows:
where E (u, v) is the gray level change resulting from the window function movement (u, v), w (x, y) is the window function, I (x, y) is the image gray level, and I (x+u, y+v) is the translated image gray level.
The application adopts image detection algorithm to detect the transmitting time in real time based on the image characteristics, and the algorithm adopts local characteristic detection, namely a detection method for further confirming the detected moving target according to the special local characteristics of the moving target. The method mainly comprises cascade low-frequency filtering, morphological filtering and continuous judgment, and has the main effects of identifying local characteristics of noise and useful signals, and ensuring the accuracy and reliability of detection results. In addition, the algorithm core is the optimal design of the autonomous detection algorithm, and the angular point position change generated by the target inching during ejection is utilized for accurate detection. For the case of a certain image scale, a typical corner detection algorithm is Harris corner detection, which replaces a binary window function with a gaussian function, and the closer to the center point, the greater the weight of the pixel is, so as to reduce the influence of noise.
Fig. 3 is a flow chart of another image feature-based T0 detection method according to an embodiment of the present application, where, as shown in fig. 3, the image feature-based T0 detection method provided in this embodiment stores standard time and collected video images into an image and a corresponding time array buffer, and then performs first-order difference, median filtering, wiener filtering, edge detection, corner detection and decision on the image in the buffer to obtain corresponding T0 information; the application adopts a mixed programming mode to realize, uses Matlab language to write a core recognition algorithm of image detection T0, uses Visual C++ language to build an overall framework of application software, and calls a C++ dynamic library converted by the core recognition algorithm based on the Matlab language, wherein the C++ dynamic library comprises image acquisition, time-frequency acquisition, image preprocessing, image caching, detection T0 algorithm library, algorithm evaluation, construction data, network configuration, T0 transmission, detection driving, image preview, cutting and the like.
Fig. 4 is a schematic structural diagram of a T0 detection device based on image features according to an embodiment of the present application; as shown in fig. 4, the image feature-based T0 detection apparatus provided in the embodiment of the present application specifically includes:
the target video image obtaining module 310 is configured to synthesize a source video image of a detection target obtained in real time with a standard timestamp to obtain a target video image;
the cropping module 320 is configured to crop the target video image in a specific detection area to obtain a cropped video image;
the difference processing module 330 is configured to perform difference processing on the cropped video image according to a preset rule, so as to obtain a target frame image of the detection target at T0;
and the transmitting time acquisition module 340 is configured to acquire T0 information of the detection target according to a standard timestamp on the target frame image.
In an embodiment of the present application, the differential processing module 330 further includes: the image difference processing module is used for carrying out difference processing on the cut video image to obtain a difference image of the moving object; the cascade filtering module is used for carrying out cascade low-frequency filtering on the differential image of the moving object to obtain a filtering image sequence; the continuous judgment module is used for continuously judging the filtering image sequence to acquire a target frame image of the detection target at T0
Fig. 5 is a schematic structural diagram of an image feature-based T0 detection system provided by the embodiment of the present application, fig. 6 is a schematic flow diagram of an image feature-based T0 detection system provided by the embodiment of the present application, and as can be seen from fig. 5 and 6, the image feature-based T0 detection system provided by the embodiment of the present application specifically includes a high-definition camera, a video acquisition card and a graphics workstation, where an SDI/HDMA interface and a 1 m low-loss coaxial cable (75Ω) direct connection mode are adopted between the high-definition camera and the video acquisition card (box), and a PCI EXPRESs or USB3.0 high-speed interface is adopted between the video acquisition card (box) and the graphics workstation, and the video acquisition card (box) performs hardware automatic detection and independent sampling on an input image, so that quality and low delay of image transmission and acquisition are ensured, resources of the graphics workstation are not occupied (or occupied or less), and image detection work of the graphics workstation is not affected.
The T0 detection system based on the image characteristics comprises wire and cable connection, image source acquisition, equipment startup and detection software. The wire cable connection comprises an antenna erection, a power line connection and a network cable connection, a GPS/BD dual-mode antenna is erected, the situation that the antenna is shielded is avoided, and an antenna interface is connected to a corresponding interface of a code card when the workstation is connected; connecting a workstation network card interface to a measurement and control system access switch by using a network cable; the device power lines are all connected to the mains switch. The image source is obtained, a camera can be obtained or erected from an existing image system, interfaces such as an SDI (serial digital interface), an HDMI (high definition multimedia interface) and the like are provided, high definition images are supported, and each image is connected to a corresponding interface (supporting 8 paths of image sources) of the workstation high definition image acquisition card by using one SDI/HDMI video line.
And after the graphic workstation is started, opening image detection application software, starting automatic detection, and displaying information such as a task code number, beijing time, predicted ignition time, countdown and the like on the upper part. The middle left side displays a preview image of the live image. The upper left corner of the right side of the middle part displays a real-time clipping image; the lower left corner is used for configuring network settings, including a source port number, a destination port number, a local IP address and a destination IP address; the upper right corner displays data information, including information such as T0 time, T0 source code, information source, information sink and the like; the right middle part displays and evaluates detection performance, including information such as detection T0 moment, algorithm time delay, transmission time delay and the like; the lower right part is used for mode setting, including modes of detecting T0 time, sending and the like; the right lower part is also provided with control buttons including control buttons for starting detection, sending T0, exiting and the like. The lowest part of the whole interface is used for displaying the source code for transmitting the T0 information.
The application adopts hardware integration and autonomous research and development of application software, adopts autonomous research and development image detection algorithm based on differential noise reduction and abstract quantization characteristic extraction technology, and has the technology and device for identifying the hot emission, cold emission, single emission, multiple emission and multiple emission micro-motion characteristics of a flying product and automatically generating the combination of software and hardware transmitted according to a stipulated protocol at the moment of emission; in addition, the application integrates a high-precision time code card and high-definition image acquisition equipment by using a PCI EXPRES or USB3.0 high-speed interface, the Beidou/GPS synchronization precision is better than 100ns, and the image acquisition quality is better than that of high-definition images.
The application adopts a mixed programming mode to realize, uses Matlab language to write a core recognition algorithm of image detection T0, uses Visual C++ language to build an integral framework of application software, and calls a C++ dynamic library converted by the core recognition algorithm based on the Matlab language. The method comprises image acquisition, time-frequency acquisition, image preprocessing, image caching, detection of a T0 algorithm library, algorithm evaluation, data construction, network configuration, T0 transmission, detection driving, image preview, cutting and the like.
In summary, the image feature-based T0 detection system provided by the application has the following advantages:
1. based on the image micro-motion characteristics of the key part of the launching moment of the flying product, the application adopts a real-time image processing and detecting technology, and a set of detecting device can realize remote or local measurement of the launching moment of various types of flying products in real time and send the real-time measurement to a related system. The technology and the device realize automatic detection, can be used as a backup of the traditional detection means, and improve the task reliability.
2. According to the application, image real-time detection software is independently designed and developed by integrating high-definition image acquisition equipment, a GPS/BD high-precision time code card and a high-performance workstation, so that the detection of the transmitting moment is realized and the transmitting moment is sent to a data center according to a stipulated protocol.
3. The application develops the classification research of the image detection targets, and completes the simulation of a first-order difference and second-order difference moving target detection algorithm and MATLAB software based on the gray level change of the images; the system designs a demonstration model machine, completes the design and programming work of image detection T0 software, improves and successfully applies edge difference and corner detection algorithm based on moving object image characteristics, optimizes the design of system video capturing and display multithreading, video format conversion, detection time delay, interface and the like, comprehensively applies the technologies of image detection area dynamic clipping, YUV/GRARY format conversion, smooth interface data and the like, and solves the technical problem of software interface matching between video capturing and image detection.
4. The application researches and applies the T0 signal generation technology based on image processing, and can effectively improve the automation working level and the system reliability of the artificial complementary T0 signal as an effective complementary technical means of a T0 control console, and reduce the adverse effect of development change of the product model on the T0 signal.
In another embodiment of the application, a computer device is provided comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of: synthesizing a source video image of a detection target obtained in real time with a standard time stamp to obtain a target video image; cutting the specific detection area of the target video image to obtain a cut video image; performing differential processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0; and acquiring the T0 information of the detection target according to the standard time stamp on the target frame image.
In yet another embodiment of the present application, a computer readable storage medium is provided having stored thereon a computer program which when executed by a processor performs the steps of: synthesizing a source video image of a detection target obtained in real time with a standard time stamp to obtain a target video image; cutting the specific detection area of the target video image to obtain a cut video image; performing differential processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0; and acquiring the T0 information of the detection target according to the standard time stamp on the target frame image.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Claims (7)
1. A method for detecting T0 based on image features, the method comprising:
synthesizing a source video image of a detection target obtained in real time with a standard time stamp to obtain a target video image;
cutting the specific detection area of the target video image to obtain a cut video image;
performing differential processing on the cut video image to obtain a differential image of the moving object;
performing cascade low-frequency filtering on the differential image of the moving object to obtain a filtered image sequence;
acquiring the gray value of each frame of image in the filter image sequence;
acquiring a difference value of gray values of a current frame image and an adjacent previous frame image;
when the difference value is greater than or equal to a preset threshold value, the current frame image is a target frame image of the detection target at T0;
acquiring T0 information of the detection target according to the standard time stamp on the target frame image;
wherein T0 is a take-off zero signal of a flight test product.
2. The image feature-based T0 detection method of claim 1, wherein prior to obtaining the gray value for each frame of image in the sequence of filtered images, the method further comprises:
and carrying out corner detection on the filtered image sequence according to a corner detection algorithm.
3. The image feature-based T0 detection method according to claim 2, wherein the formula expression of the corner detection algorithm is:
wherein ,is window function move +.>The grey level change produced->Is a window function, +.>Is the gray scale of the image +.>Is the image gray after the translation.
4. The method for detecting T0 based on image features according to claim 2, wherein before performing differential processing on the cropped video image according to a preset rule to obtain a target frame image of the detection target at T0, the method further comprises:
and acquiring key actions of the detection target at T0, wherein the key actions comprise an ignition action, an ejection action, a cylinder discharging action and a take-off action.
5. The method for detecting T0 based on image features as claimed in claim 4, wherein performing differential processing on the cropped video image according to a preset rule to obtain a target frame image of the detection target at T0, comprises:
when the key action is the ignition action, carrying out differential processing on the cut video image according to an inter-frame differential algorithm to obtain a target frame image of the detection target at T0;
and when the key action is the ejection action, the barrel discharging action or the take-off action, performing differential processing on the cut video image according to an accumulated differential algorithm to obtain a target frame image of the detection target at T0.
6. A T0 detection device based on image features, the device comprising:
the target video image acquisition module is used for synthesizing the source video image of the detection target acquired in real time with the standard time stamp to obtain a target video image;
the clipping module is used for clipping the specific detection area of the target video image to obtain a clipping video image;
the difference processing module is used for carrying out difference processing on the cut video image according to a preset rule to obtain a target frame image of the detection target at T0;
the transmitting moment acquisition module is used for acquiring the T0 information of the detection target according to the standard time stamp on the target frame image;
wherein, the differential processing module further comprises: the image difference processing module is used for carrying out difference processing on the cut video image to obtain a difference image of the moving object; the cascade filtering module is used for carrying out cascade low-frequency filtering on the differential image of the moving object to obtain a filtering image sequence; the continuous judgment module is used for continuously judging the filtering image sequence to acquire a target frame image of the detection target at T0;
the continuous judging module is further used for acquiring the gray value of each frame of image in the filtering image sequence; the method is also used for obtaining the difference value of the gray value of the current frame image and the gray value of the adjacent previous frame image; the current frame image is a target frame image of the detection target at T0 when the difference value is larger than or equal to a preset threshold value;
wherein T0 is a take-off zero signal of a flight test product.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011141921.1A CN112258479B (en) | 2020-10-22 | 2020-10-22 | T0 detection method and device based on image characteristics and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011141921.1A CN112258479B (en) | 2020-10-22 | 2020-10-22 | T0 detection method and device based on image characteristics and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112258479A CN112258479A (en) | 2021-01-22 |
| CN112258479B true CN112258479B (en) | 2023-10-27 |
Family
ID=74264950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011141921.1A Active CN112258479B (en) | 2020-10-22 | 2020-10-22 | T0 detection method and device based on image characteristics and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112258479B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822841B (en) * | 2021-01-29 | 2022-05-20 | 深圳信息职业技术学院 | Sewage impurity caking detection method and device and related equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012073891A (en) * | 2010-09-29 | 2012-04-12 | Nohmi Bosai Ltd | Frequency component specification method for smoke detection and smoke detector |
| WO2012121735A1 (en) * | 2011-03-10 | 2012-09-13 | Tesfor, Llc | Apparatus and method of targeting small weapons |
| CN107967448A (en) * | 2017-11-16 | 2018-04-27 | 江苏理工学院 | Incipient fire smog real-time detection method and system |
| CN108090932A (en) * | 2017-12-21 | 2018-05-29 | 南京理工大学 | Fried Point Target Detection system and method based on FPGA |
| CN108983675A (en) * | 2018-08-16 | 2018-12-11 | 中国人民解放军63620部队 | System and method for generating lift-off zero,take-off zero signal |
| CN109357977A (en) * | 2018-09-29 | 2019-02-19 | 佛山市云米电器科技有限公司 | Smog sub-district domain space based on time connection rechecks method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7710280B2 (en) * | 2006-05-12 | 2010-05-04 | Fossil Power Systems Inc. | Flame detection device and method of detecting flame |
| US10803557B2 (en) * | 2017-12-26 | 2020-10-13 | Xidian University | Non-uniformity correction method for infrared image based on guided filtering and high-pass filtering |
-
2020
- 2020-10-22 CN CN202011141921.1A patent/CN112258479B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012073891A (en) * | 2010-09-29 | 2012-04-12 | Nohmi Bosai Ltd | Frequency component specification method for smoke detection and smoke detector |
| WO2012121735A1 (en) * | 2011-03-10 | 2012-09-13 | Tesfor, Llc | Apparatus and method of targeting small weapons |
| CN107967448A (en) * | 2017-11-16 | 2018-04-27 | 江苏理工学院 | Incipient fire smog real-time detection method and system |
| CN108090932A (en) * | 2017-12-21 | 2018-05-29 | 南京理工大学 | Fried Point Target Detection system and method based on FPGA |
| CN108983675A (en) * | 2018-08-16 | 2018-12-11 | 中国人民解放军63620部队 | System and method for generating lift-off zero,take-off zero signal |
| CN109357977A (en) * | 2018-09-29 | 2019-02-19 | 佛山市云米电器科技有限公司 | Smog sub-district domain space based on time connection rechecks method |
Non-Patent Citations (2)
| Title |
|---|
| Motion Detection Based on Frame Difference Method;Nishu Singla;《Computer Science》;第1-10页 * |
| 基于视频的飞机货舱烟雾识别去干扰方法研究;薛倩;刘婧;孙钦升;;计算机仿真(第06期);第70-75页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112258479A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11961242B2 (en) | Target tracking method, computer device, and storage medium | |
| US8744166B2 (en) | System and method for multiple simultaneous automated defect detection | |
| US11880982B2 (en) | Method and system for performing image segmentation | |
| CN111222395A (en) | Target detection method and device and electronic equipment | |
| CN105930822A (en) | Human face snapshot method and system | |
| CN110826428A (en) | Ship detection method in high-speed SAR image | |
| CN110647836B (en) | Robust single-target tracking method based on deep learning | |
| CN112258479B (en) | T0 detection method and device based on image characteristics and storage medium | |
| CN108629792A (en) | Laser eyepiece detection method and device based on background modeling Yu background difference | |
| Shostko et al. | Optical-electronic system of automatic detection and higt-precise tracking of aerial objects in real-time. | |
| WO2014133611A1 (en) | Material detection in hyperspectral imagery | |
| US8179301B2 (en) | Image processor and image processing method for synthetic aperture radar | |
| CN116843691A (en) | Photovoltaic panel hot spot detection method, storage medium and electronic equipment | |
| CN113253269B (en) | SAR self-focusing method based on image classification | |
| CN110992398A (en) | Image fusion tracking and anti-interference method for laser radar and infrared detection system | |
| US20230169674A1 (en) | Information processing device, information processing method, and information processing program | |
| CN115546736B (en) | River channel sand production monitoring processing method and system based on image acquisition | |
| WO2014056473A2 (en) | Method for image processing and method that can be performed therewith for the automatic detection of objects, observation device and method for high-precision tracking of the course followed by launched rockets over large distances | |
| CN113572983B (en) | Cloud video processing method and system | |
| CN106846292B (en) | A kind of invalid pixel In-flight measurement method | |
| Lin et al. | An object reconstruction algorithm for moving vehicle detection based on three-frame differencing | |
| CN112015231B (en) | Method and system for processing surveillance video partition | |
| Honeycutt et al. | Use of the LunAero open-source hardware platform to enhance the accuracy and precision of traditional nocturnal migration bird counts | |
| CN110895120B (en) | Image processing technology-based ship cannon system precision detection device and detection method | |
| CN112329729A (en) | Small target ship detection method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |