CN116627916B - Automatic test method and system for multi-path camera data acquisition and data backflow - Google Patents
Automatic test method and system for multi-path camera data acquisition and data backflow Download PDFInfo
- Publication number
- CN116627916B CN116627916B CN202310912613.1A CN202310912613A CN116627916B CN 116627916 B CN116627916 B CN 116627916B CN 202310912613 A CN202310912613 A CN 202310912613A CN 116627916 B CN116627916 B CN 116627916B
- Authority
- CN
- China
- Prior art keywords
- image
- images
- data
- living body
- acquired
- 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
- 238000010998 test method Methods 0.000 title claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 96
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 14
- 238000004806 packaging method and process Methods 0.000 claims description 6
- 101100459256 Cyprinus carpio myca gene Proteins 0.000 claims description 5
- 241001522296 Erithacus rubecula Species 0.000 claims description 5
- 238000001727 in vivo Methods 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 7
- 230000007547 defect Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 101100459261 Cyprinus carpio mycb gene Proteins 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
- G06F16/164—File meta data generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/14—Details of searching files based on file metadata
- G06F16/148—File search processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/172—Caching, prefetching or hoarding of files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Library & Information Science (AREA)
- Studio Devices (AREA)
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an automatic test method and system for data acquisition and data backflow of a multi-path camera, which comprises two parts, an embedded device and a PC end. The invention also supports the simultaneous acquisition of the data of the multiple cameras, saves the correlation among the images from different cameras, is used for acquiring the images corresponding to the multiple cameras at the same time, and supports the data acquisition and the data backflow requirement of the living body detection algorithm. The invention is based on the PYTHON tool, realizes the functional requirements for large data volume acquisition and backflow, improves the automatic test level, and improves the development and test efficiency.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an automatic test method and system for multi-path camera data acquisition and data backflow based on an embedded system.
Background
The embedded device is an intelligent door lock, wherein an important component is an intelligent module, and important functional modules in the intelligent module are functional modules such as face detection, face recognition and/or living body detection.
The training of the algorithm model is generally completed on a personal computer or a GPU, and the algorithm model is generated and then applied to the embedded system. In addition, two or more cameras with the same time are required to acquire images corresponding to the living body algorithm.
In general, face pictures used by a training algorithm need to be acquired from a camera of an embedded system, so that the consistency of an algorithm model and an actual application scene can be ensured as much as possible, and the detection and recognition effects are better.
In addition, in practical application, the face data needs to be fed back to the intelligent algorithm for counting the detection effect or the identification effect of the algorithm model or for locating whether the algorithm model has holes or not.
The current collection of data is typically by saving camera video data to a file. The video format is typically MJEPG or H264, etc. The acquisition method has the following defects: 1. after compression, the acquired data are distorted to different degrees. 2. The acquired data typically requires further classification or recalibration. 3. Two or more paths of camera data at the same time cannot be stored at the same time, and the data acquisition requirements of algorithms such as living body detection cannot be met.
Currently, a special device (such as HDMI to AHD) is generally used to convert the collected video into a virtual camera. The defects are: 1. additional costs are required for the dedicated equipment. 2. The video-compressed data is distorted. 3. Embedded devices without camera interfaces (e.g., smart door lock modules) cannot be used. 4. The data backflow requirement of the living body detection algorithm cannot be met.
In addition, there is a backward data mode of transmitting video data or picture data through a network port, but the mode can be realized only by depending on the existence of the network port or WIFI of the embedded device. For embedded equipment without a network port (such as an intelligent door lock module), the embedded equipment cannot be used.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides an automatic test method for multi-path camera data acquisition and data backflow based on an embedded system, which has low requirements on equipment, does not depend on a network port and a video interface, supports multi-path camera data acquisition, and meets the data acquisition and data backflow requirements of a living body detection algorithm.
In order to solve the above-mentioned purpose, the invention adopts the technical scheme:
an automatic test method for multi-path camera data acquisition and data backflow comprises the following steps:
capturing an original image in a camera module of the embedded device;
the meta-attribute of the images is saved, wherein the images acquired by the multiple cameras at the same time have the same image ID value and are used for judging the correlation among the images;
performing face detection, and storing a face detection result as image attribute information;
obtaining multiple paths of images at the same time, executing living body detection, and storing living body detection results as image attribute information;
performing face recognition, and storing a face recognition result as image attribute information;
storing the image as a file, and packaging the image attribute information as a regular image file name, so that the PC end can analyze the corresponding image attribute information from the file name;
the USB interface of the embedded equipment is connected by using a data line, the equipment end and the PC end are connected, and a user operates the embedded equipment at the PC end through the ADB;
during data acquisition, the PC end polls whether acquired images exist or not in a round-robin mode, an image list is acquired through the ADB, and the acquired images are downloaded to the PC end through the ADB in sequence;
the PC end stores the downloaded image data into a designated folder;
when data is backward flowed, the PC end acquires an image list from the acquired data set, and sequentially uploads the images to the equipment end through the ADB;
after the data uploading is completed, the PC end issues corresponding detection or identification commands through the ADB, waits for completion and inquires the result;
the equipment end executes the detection or identification command and reports the result;
after receiving the reported result, the PC end stores the image and the corresponding result in an excel report, and counts the success or failure probability;
the command is sent, the result is inquired, and the command for uploading and downloading the image is executed based on PYTHON.
Further, the process of the embedded device for collecting the face data through recognition specifically comprises the following steps:
step A, capturing YUV data of cameras 1 to N, and comparing time stamps to ensure that multiple paths of images are captured at the same time for living body detection;
step B, performing face detection to obtain a face detection result; step C, the face detection is successful, otherwise, the step A is entered;
step C, performing living body detection to obtain a living body detection result; step D is successfully carried out in the living body detection, otherwise, step A is carried out;
step D, performing face recognition to obtain a face recognition result; step E is successfully carried out on face recognition, otherwise, step A is carried out;
and E, saving the image and all the image attributes to the file.
Further, the specific process of the PC side for collecting the image data from the embedded device comprises the following steps:
step a, the PC end issues a start identification command through the ADB SHELL;
step b, inquiring whether the embedded equipment successfully collects the identified images in a round robin manner, and acquiring an image list which is successfully collected;
step c, sending an image uploading command through the ADB, uploading the acquired image, storing the image to a designated folder, and if the folder does not exist, newly creating the folder;
step d, judging whether the number of the acquired images is larger than a threshold value, if so, entering a step e, otherwise, entering a step b;
and e, ending.
Further, when the multi-path camera performs data acquisition, N paths of images corresponding to the input to the living body algorithm are respectively identified as cam1_ idM to camn_ idM, wherein cam1 is image data captured from the camera 1, camN is image data captured from the camera N, and idM is represented as an image acquired at the same time point; when data is backward-filled, images acquired at the same time point are selected from the acquired data of N cameras and uploaded to the equipment end, an ID value is analyzed from a file name by using PYTHON, namely, an image with the ID value of M is analyzed from the camera 1, an image with the ID of M is analyzed from the camera N, the analyzed N images are image sets acquired at the same time, the image sets are uploaded to the equipment end by using ADB, and algorithm detection is executed.
The invention further aims to overcome the defects of the prior art, and provides an automatic test system for multi-path camera data acquisition and data backflow based on an embedded system, which has low requirements on equipment, does not depend on a network port and a video interface, supports multi-path camera data acquisition, and meets the data acquisition and data backflow requirements of a living body detection algorithm.
In order to solve the above-mentioned purpose, the invention adopts the technical scheme:
an automatic test system for multi-path camera data acquisition and data backflow comprises a plurality of cameras, embedded equipment and a PC end;
the cameras are used for collecting original images;
the embedded equipment is used for receiving original images of a plurality of cameras and storing the meta-attribute of the images, wherein the images acquired by the plurality of cameras at the same time have the same image ID value and are used for judging the correlation among the images; the embedded device is used for executing face detection and storing a face detection result; performing living body detection, and saving a score of the living body detection as image attribute information; performing face recognition, and storing a face recognition result as image attribute information; storing the image as a file, and packaging the image attribute information as a regular image file name, so that the PC end analyzes the corresponding image attribute information from the file name; the embedded equipment is also used for executing a detection or identification command sent by the PC end and reporting the result;
the PC end is connected with a USB interface of the embedded equipment by using a data line, the embedded equipment is operated on the basis of PYTHON by the ADB, and during data acquisition, whether acquired images exist or not is searched in a round-robin mode, an image list is acquired, the images are sequentially downloaded to the PC end, and the PC end stores the downloaded image data in a specified folder; when data is backward flowed, the PC end acquires an image list from the collected data set and sequentially uploads the images to the embedded equipment; after the data uploading is completed, the PC end issues corresponding detection or identification commands through the ADB, waits for completion and inquires the result; after receiving the report result of the embedded device, the PC end stores the image and the corresponding result in an excel report, and counts the success or failure probability.
Further, the process of the embedded device for collecting the face data through recognition specifically comprises the following steps:
step A, capturing YUV data of cameras 1 to N, and comparing time stamps to ensure that multiple paths of images are captured at the same time for living body detection;
step B, performing face detection to obtain a face detection result; step C, the face detection is successful, otherwise, the step A is entered;
step C, performing living body detection to obtain a living body detection result; step D is successfully carried out in the living body detection, otherwise, step A is carried out;
step D, performing face recognition to obtain a face recognition result; step E is successfully carried out on face recognition, otherwise, step A is carried out;
and E, saving the image and all the image attributes to the file.
Further, the specific process of the PC side for collecting the image data from the embedded device comprises the following steps:
step a, the PC end issues a start identification command through the ADB SHELL;
step b, inquiring whether the embedded equipment successfully collects the identified images in a round robin manner, and acquiring an image list which is successfully collected;
step c, sending an image uploading command through the ADB, uploading the acquired image, storing the image to a designated folder, and if the folder does not exist, newly creating the folder;
step d, judging whether the number of the acquired images is larger than a threshold value, if so, entering a step e, otherwise, entering a step b;
and e, ending.
Further, when the multi-path camera of the embedded device performs data acquisition, N paths of images corresponding to the input to the living body algorithm are respectively identified as cam1_ idM to camn_ idM, wherein cam1 is image data captured from the camera 1, camN is image data captured from the camera N, and idM is represented as an image acquired at the same time point; when data is backward-filled, images acquired at the same time point are selected from the acquired data of N cameras and uploaded to the equipment end, an ID value is analyzed from a file name by using PYTHON, namely, an image with the ID value of M is analyzed from the camera 1, an image with the ID of M is analyzed from the camera N, the analyzed N images are image sets acquired at the same time, the image sets are uploaded to the equipment end by using ADB, and algorithm detection is executed.
After the scheme is adopted, the automatic test method and the system for the data acquisition and the data backflow of the multipath camera support the acquisition of lossless or lossy images on the embedded equipment with the USB interface, and support various image formats such as YUV data format (data lossless), MJPEG format, JPEG format and the like. Preserving the meta-properties of the image, such as image resolution, image format, image source or use information, is supported. Image data collected by backward flowing through the USB interface is supported, and the image data are used for intelligent algorithm function processing modules such as face detection or recognition and the like to realize statistical analysis, scene reproduction and the like. The invention also supports the simultaneous acquisition of the data of the multiple cameras, saves the correlation among the images from different cameras, is used for acquiring the images corresponding to the multiple cameras at the same time, and supports the data acquisition and the data backflow requirements of the living body detection algorithm. In addition, the invention is based on the PYTHON tool, so that the functional requirements for large data volume acquisition and backflow are realized, the automatic test level is further improved, and the development and test efficiency is improved.
Compared with the prior art, the invention has low requirements on equipment, does not depend on a network port or a video interface, and only needs to be provided with a USB interface; the method supports multiple data formats such as lossless and lossy, and the like, and meets different development and test requirements more flexibly; the automatic test is supported, the implementation cost is reduced, the time cost is saved, and more scheme selection flexibility is provided; the data acquisition of the multi-path cameras is supported, and the requirements of data acquisition and data backflow of a living body detection algorithm are met.
Drawings
FIG. 1 is a schematic diagram of the framework of the system of the present invention.
FIG. 2 is a schematic view of a partial flow chart of the present invention.
Detailed Description
In order to further explain the technical scheme of the invention, the invention is explained in detail by specific examples.
The general idea of the automatic test method for multi-path camera data acquisition and data backflow is that a large number of face images are required to be acquired in embedded equipment such as an intelligent door lock and used for training intelligent algorithms such as face detection and face recognition algorithms and the like.
In general, face pictures used by a training algorithm need to be acquired from a camera of an embedded system, so that the consistency of an algorithm model and an actual application scene can be ensured as much as possible, and the detection and recognition effects are better.
The intelligent device such as a door lock module generally has a USB interface and supports an ADB function. The USB channel has the characteristics of high bandwidth and high speed. Therefore, the image from the camera is downloaded by the USB channel, the downloading of bare data or encoded data can be flexibly selected, and the data with different formats can be acquired according to different requirements.
In order to verify the face recognition effect in the intelligent door lock, the passing or failure probability of detection needs to be counted for a specific big data test set, and the passing or failure probability of recognition needs to be counted and recognized for the big data test set. It is necessary to save in particular which image failed or succeeded.
Therefore, the invention utilizes the PYHON tool to automatically upload and download the pictures aiming at the big data test set, performs face detection or recognition, and then stores the score and the corresponding image of the face detection or recognition into a report. And counting the failure or success proportion according to a specific threshold value, judging whether the algorithm effect meets the requirement or not, or whether the algorithm is used for positioning the defect or not, and assisting in positioning the defect.
In addition, the living body detection algorithm requires, as input data, multiplexed camera data from the same time. Therefore, correlation among multiple paths of camera data needs to be saved to meet the requirement of synchronization of image data.
Based on the above ideas, as shown in fig. 1 and fig. 2, the invention discloses an automatic test method for data acquisition and data backflow of a multi-path camera, which comprises two parts, wherein one part is a device-side program, the other part is an embedded system, and the other part is a PC-side device, and executes a PYTHON program. The method comprises the following steps:
capturing an original image in a camera module of the embedded device; the image format is generally YUV or RGB format, the original format image can be directly collected, the consistency of the algorithm model and the actual application scene is ensured as much as possible, and the detection and recognition effects are better; the image may also be compressed in a compressed format such as MJPEG, etc., considering that the original data format will occupy more storage and bandwidth.
The meta-properties of the image, such as resolution, time stamp, image ID value, etc., are saved. The images acquired by the multiple cameras at the same time have the same image ID value and are used for judging the correlation among the images.
Face detection is performed, and face detection results, such as face coordinates and face detection scores, are saved as image attribute information.
Multiple images at the same time are obtained, living body detection is performed, and the score of the living body detection is saved as image attribute information.
Face recognition is performed, such as the highest score and the name of the person, and the face recognition result is saved as image attribute information.
And storing the image as a file, and packaging the image attribute information as a regular image file name, so that the PC end can analyze the corresponding image attribute information from the file name.
The USB interface of the embedded equipment is connected by using a data line, the equipment end and the PC end are connected, and a user operates the embedded equipment at the PC end through the ADB, such as SHELL operation, file transmission operation and the like.
During data acquisition, the PC end polls whether acquired images exist or not in a round-robin mode, an image list is acquired through the ADB, and the acquired images are downloaded to the PC end through the ADB in sequence;
the PC end stores the downloaded image data into a designated folder; the name of the folder comprises a camera ID, acquisition starting time, acquisition scene and other information.
When data is backward flowed, the PC end acquires an image list from the acquired data set, and sequentially uploads the images to the equipment end through the ADB;
after the data uploading is completed, the PC end issues corresponding detection or identification commands through the ADB, waits for completion and inquires the result;
the equipment end executes the detection or identification command and reports the result;
after receiving the reported result, the PC end stores the image and the corresponding result in an excel report, and counts the success or failure probability;
the command is sent, the result is inquired, and the image uploading and downloading command is executed based on PYTHON, so that the functions of automatic data acquisition and data backflow based on a large data set are realized.
In performing the living body detection, the PC side takes as input a plurality of images having the same image ID value by judging that the images are in the same scene.
As shown in fig. 2, the process of collecting face data through recognition by the embedded device of the present invention specifically includes the following steps:
step A, capturing YUV data of cameras 1 to N, and comparing time stamps to ensure that multiple paths of images are captured at the same time for living body detection; if the data volume needs to be compressed, the YUV image can be coded into MJPEG, and the MJPEG image can be a lossy image;
step B, performing face detection to obtain a face detection result; step C, the face detection is successful, otherwise, the step A is entered;
step C, performing living body detection to obtain a living body detection result; step D is successfully carried out in the living body detection, otherwise, step A is carried out;
step D, performing face recognition to obtain a face recognition result; step E is successfully carried out on face recognition, otherwise, step A is carried out;
step E, save image and all image attributes to file, in embedded device, if there is no SD device, it can also consider using memory file system (RAMFS), which is a memory-based file system, working completely in RAM. It is a virtual file system that can be created dynamically in memory at run-time without using space on the hard disk.
And packaging all the information such as the identification score, the image attribute and the like in a file, and customizing specific rules. The method mainly comprises the following attribute information:
the specific process of the PC side for collecting the image data from the embedded equipment comprises the following steps:
step a, the PC end issues a start identification command through the ADB SHELL;
step b, inquiring whether the embedded equipment successfully collects the identified images in a round robin manner, and acquiring an image list which is successfully collected;
step c, sending an image uploading command through the ADB, uploading the acquired image, storing the image to a designated folder, and if the folder does not exist, newly creating the folder;
step d, judging whether the number of the acquired images is larger than a threshold value, if so, entering a step e, otherwise, entering a step b;
and e, ending.
The multi-path camera data correlation processing adopts the same ID value to judge the image correlation, has simple realization method and flexibility, and is also applicable to the situation of irrelevant image data. In more detail, at the time of data acquisition, two paths of images corresponding to the input to the living algorithm are respectively identified as cam1_id100 and cam2_id100, where cam1 is image data captured from the camera 1 and cam2 is image data captured from the camera 2. id100 represents an image acquired at the same point in time. When the data is backward filled, the images acquired at the same time point are selected from the acquired data of the two cameras and uploaded to the equipment end. At this time, the ID value is resolved from the file name by using PYTHON, for example, the ID value is resolved to be 100 from the camera 1, the image with the ID of 100 is resolved from the camera 2, such two images are image pairs acquired at the same time, the image pairs are uploaded to the equipment end by using ADB, and algorithm detection is performed, so that scene reproduction is realized. The method is convenient to be applied to the scenes such as algorithm problem positioning, registration recognition and the like.
As shown in fig. 1, the invention also discloses an automatic test system for multi-path camera data acquisition and data backflow based on the embedded system, which comprises a plurality of cameras 1, embedded equipment 2 and a PC end 3;
the cameras 1 are used for collecting original images;
the embedded device 2 is configured to receive original images of a plurality of cameras and store meta-attributes of the images, where images acquired by the plurality of cameras at the same time have the same image ID value, and determine correlation between the images; the embedded device 2 is further configured to perform face detection and store a face detection result; performing living body detection, and saving a score of the living body detection as image attribute information; performing face recognition, and storing a face recognition result as image attribute information; the image is stored as a file, and the image attribute information is packaged as a regular image file name, so that the PC end can analyze the corresponding image attribute information from the file name; the embedded device 2 is also used for executing a detection or identification command sent by the PC end and reporting the result;
the PC end is connected with a USB interface of the embedded equipment by using a data line, the embedded equipment is operated on the basis of PYTHON by the ADB, when data is acquired, whether an acquired image exists or not is searched in a round-robin mode, an image list is acquired by the ADB, the image list is sequentially downloaded to the PC end by the ADB, the downloaded image data is stored in a designated folder by the PC end, wherein the name of the folder comprises a camera ID, acquisition starting time, acquisition scene and other information; when data is backward flowed, the PC end acquires an image list from the acquired data set, and sequentially uploads the images to the embedded equipment through the ADB; after the data uploading is completed, the PC end issues corresponding detection or identification commands through the ADB, waits for completion and inquires the result; after receiving the report result of the embedded device, the PC end stores the image and the corresponding result in an excel report, and counts the success or failure probability.
The above examples and illustrations are not intended to limit the form or form of the present invention, and any suitable variations or modifications thereof by those skilled in the art should be regarded as not departing from the scope of the invention.
Claims (4)
1. The automatic test method for the data acquisition and the data backflow of the multipath camera is characterized by comprising the following steps of:
step S1: capturing YUV data of cameras 1 to N in a camera module of the embedded equipment, wherein images acquired by multiple cameras at the same time have the same image ID value, and are used for judging correlation among the images, comparing time stamps, and ensuring that the images are captured at the same time and are used for living body detection; the N paths of images which are correspondingly input to the living body algorithm are respectively identified as cam1_ idM to camN_ idM, wherein cam1 is image data captured from the camera 1, camN is image data captured from the camera N, and idM is represented as an image acquired at the same time point; preserving the meta-attribute of the image;
step S2: performing face detection to obtain a face detection result, storing the face detection result as image attribute information, and if the face detection is successful, performing living body detection to obtain a living body detection result, otherwise, performing YUV data of capturing cameras 1 to N, comparing time stamps to ensure that the images are captured at the same time and are used for living body detection;
step S3: acquiring multiple paths of images at the same time, executing living body detection, acquiring a living body detection result, storing a score of the living body detection as image attribute information, performing face recognition successfully when the living body detection is successful, and acquiring the face recognition result, otherwise, performing YUV data of capturing cameras 1 to N, comparing time stamps, and ensuring the multiple paths of images captured at the same time for the living body detection;
step S4: executing face recognition, obtaining a face recognition result, storing the face recognition result as image attribute information, and if the face recognition is successful, entering a step of storing images and all image attributes into a file, otherwise, entering YUV data of capturing cameras 1 to N, comparing time stamps, and ensuring that the images are captured at the same time and are used for in-vivo detection;
step S5: storing the image and all the image attribute information into a file, and packaging the image attribute information into a regular image file name, so that the PC end analyzes the corresponding image attribute information from the image file name;
step S6: the USB interface of the embedded equipment is connected by using a data line, the embedded equipment is connected with the PC end, and a user operates the embedded equipment at the PC end through the ADB;
step S7: when image data are collected, the PC end polls whether the collected images exist in the embedded equipment in a round-robin mode, an image list is obtained through the ADB, and the image list is downloaded to the PC end through the ADB in sequence;
step S8: the PC end stores the downloaded image data into a designated folder;
step S9: when data is backward-filled, the PC end selects images acquired at the same time point from the acquired data of N cameras, uploads the images to the embedded equipment, analyzes an ID value from an image file name by using PYTHON, namely analyzes an image with the ID value of M from the camera 1, analyzes the image with the ID of M from the camera N, analyzes the N images to be an image set acquired at the same time, uploads the image set to the embedded equipment by using ADB, and executes algorithm detection;
step S10: after the image uploading is finished, the PC end issues a corresponding detection or identification command through the ADB, waits for finishing and inquiring the result;
step S11: the embedded equipment executes the detection or identification command and reports the result;
step S12: after receiving the reported result, the PC end stores the image and the corresponding result in an excel report, and counts the success or failure probability;
the command is sent, the result is inquired, and the command for uploading and downloading the image is executed based on PYTHON.
2. The automatic test method for multi-path camera data acquisition and data backflow as claimed in claim 1, wherein the process of acquiring image data from the embedded device by the PC terminal comprises the following steps:
step a, the PC end issues a start identification command through the ADB SHELL;
step b, inquiring whether the embedded equipment successfully collects the identified images in a round robin manner, and acquiring an image list which is successfully collected;
step c, sending an image uploading command through the ADB, uploading the acquired image, storing the image to a designated folder, and if the folder does not exist, newly creating the folder;
step d, judging whether the number of the acquired images is larger than a threshold value, if so, entering a step e, otherwise, entering a step b;
and e, ending.
3. An automatic test system for multi-path camera data acquisition and data backflow, comprising: a plurality of cameras, embedded equipment and a PC end;
the cameras are used for collecting original images;
the embedded device captures YUV data of cameras 1 to N, images acquired by the cameras 1 to N at the same time have the same image ID value, the images are used for judging correlation among the images, and time stamps are compared to ensure that multiple paths of images are captured at the same time and used for living body detection; the N paths of images which are correspondingly input to the living body algorithm are respectively identified as cam1_ idM to camN_ idM, wherein cam1 is image data captured from the camera 1, camN is image data captured from the camera N, and idM is represented as an image acquired at the same time point; preserving the meta-attribute of the image; the embedded device is used for performing face detection to obtain a face detection result, storing the face detection result as image attribute information, obtaining multiple paths of images at the same time, performing living body detection to obtain a living body detection result, storing a score of the living body detection as the image attribute information, performing face recognition to obtain a face recognition result, and storing the face recognition result as the image attribute information; storing the image and all the image attribute information into a file, and packaging the image attribute information into a regular image file name so that the PC end analyzes the corresponding image attribute information from the image file name; the embedded equipment is also used for executing a detection or identification command sent by the PC end and reporting the result;
the PC end is connected with a USB interface of the embedded equipment by using a data line, the embedded equipment is operated on the basis of PYTHON by the ADB, when image data are collected, whether the collected images exist in the embedded equipment or not is searched in a round-robin mode, an image list is obtained, the images are sequentially downloaded to the PC end, and the downloaded image data are stored in a designated folder by the PC end; when data is backward-filled, images acquired at the same time point are selected from the acquired data of N cameras and uploaded to the embedded equipment, an ID value is analyzed from an image file name by using PYTHON, namely, an image with the ID value of M is analyzed from the camera 1, an image with the ID of M is analyzed from the camera N, the analyzed N images are image sets acquired at the same time, the image sets are uploaded to the embedded equipment by using ADB, and algorithm detection is executed; after the image uploading is finished, the PC end issues a corresponding detection or identification command through the ADB, waits for finishing and inquiring the result; after receiving the report result of the embedded device, the PC end stores the image and the corresponding result in an excel report, and counts the success or failure probability.
4. The automatic test system for multi-path camera data acquisition and data back-flow as recited in claim 3, wherein the specific process of the PC side acquiring image data from the embedded device comprises the following steps:
step a, the PC end issues a start identification command through the ADB SHELL;
step b, inquiring whether the embedded equipment successfully collects the identified images in a round robin manner, and acquiring an image list which is successfully collected;
step c, sending an image uploading command through the ADB, uploading the acquired image, storing the image to a designated folder, and if the folder does not exist, newly creating the folder;
step d, judging whether the number of the acquired images is larger than a threshold value, if so, entering a step e, otherwise, entering a step b;
and e, ending.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311201285.0A CN117349240A (en) | 2023-07-25 | 2023-07-25 | Multi-path camera data backflow method and system based on embedded equipment |
CN202310912613.1A CN116627916B (en) | 2023-07-25 | 2023-07-25 | Automatic test method and system for multi-path camera data acquisition and data backflow |
CN202311201276.1A CN117349239A (en) | 2023-07-25 | 2023-07-25 | Multi-path camera data acquisition method and system based on embedded equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310912613.1A CN116627916B (en) | 2023-07-25 | 2023-07-25 | Automatic test method and system for multi-path camera data acquisition and data backflow |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311201276.1A Division CN117349239A (en) | 2023-07-25 | 2023-07-25 | Multi-path camera data acquisition method and system based on embedded equipment |
CN202311201285.0A Division CN117349240A (en) | 2023-07-25 | 2023-07-25 | Multi-path camera data backflow method and system based on embedded equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116627916A CN116627916A (en) | 2023-08-22 |
CN116627916B true CN116627916B (en) | 2023-10-13 |
Family
ID=87592463
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311201285.0A Pending CN117349240A (en) | 2023-07-25 | 2023-07-25 | Multi-path camera data backflow method and system based on embedded equipment |
CN202310912613.1A Active CN116627916B (en) | 2023-07-25 | 2023-07-25 | Automatic test method and system for multi-path camera data acquisition and data backflow |
CN202311201276.1A Pending CN117349239A (en) | 2023-07-25 | 2023-07-25 | Multi-path camera data acquisition method and system based on embedded equipment |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311201285.0A Pending CN117349240A (en) | 2023-07-25 | 2023-07-25 | Multi-path camera data backflow method and system based on embedded equipment |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311201276.1A Pending CN117349239A (en) | 2023-07-25 | 2023-07-25 | Multi-path camera data acquisition method and system based on embedded equipment |
Country Status (1)
Country | Link |
---|---|
CN (3) | CN117349240A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120071849A (en) * | 2010-12-23 | 2012-07-03 | 주식회사 이노와이어리스 | Automatical test system and method performance of smart phone using android debug bridge interface |
CN203104575U (en) * | 2013-01-21 | 2013-07-31 | 上海斐讯数据通信技术有限公司 | Mobile terminal automatic test system |
CN112668510A (en) * | 2020-12-31 | 2021-04-16 | 公安部第三研究所 | Method, system, device, processor and storage medium for realizing performance test of three-dimensional face recognition equipment |
CN113660482A (en) * | 2021-07-28 | 2021-11-16 | 上海立可芯半导体科技有限公司 | Automatic testing method and device for AI camera equipment or module |
CN113705389A (en) * | 2021-08-13 | 2021-11-26 | 北京市商汤科技开发有限公司 | Face recognition module testing method and device, storage medium and electronic equipment |
CN114924950A (en) * | 2022-04-24 | 2022-08-19 | 北京旷视科技有限公司 | Test method, electronic device, and computer-readable medium |
CN115422058A (en) * | 2022-09-01 | 2022-12-02 | 京东科技信息技术有限公司 | Method and device for testing face recognition application |
CN115981927A (en) * | 2022-09-06 | 2023-04-18 | 深圳感臻智能股份有限公司 | Device and method for batch testing of USB (universal serial bus) equipment based on windows system |
-
2023
- 2023-07-25 CN CN202311201285.0A patent/CN117349240A/en active Pending
- 2023-07-25 CN CN202310912613.1A patent/CN116627916B/en active Active
- 2023-07-25 CN CN202311201276.1A patent/CN117349239A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120071849A (en) * | 2010-12-23 | 2012-07-03 | 주식회사 이노와이어리스 | Automatical test system and method performance of smart phone using android debug bridge interface |
CN203104575U (en) * | 2013-01-21 | 2013-07-31 | 上海斐讯数据通信技术有限公司 | Mobile terminal automatic test system |
CN112668510A (en) * | 2020-12-31 | 2021-04-16 | 公安部第三研究所 | Method, system, device, processor and storage medium for realizing performance test of three-dimensional face recognition equipment |
CN113660482A (en) * | 2021-07-28 | 2021-11-16 | 上海立可芯半导体科技有限公司 | Automatic testing method and device for AI camera equipment or module |
CN113705389A (en) * | 2021-08-13 | 2021-11-26 | 北京市商汤科技开发有限公司 | Face recognition module testing method and device, storage medium and electronic equipment |
CN114924950A (en) * | 2022-04-24 | 2022-08-19 | 北京旷视科技有限公司 | Test method, electronic device, and computer-readable medium |
CN115422058A (en) * | 2022-09-01 | 2022-12-02 | 京东科技信息技术有限公司 | Method and device for testing face recognition application |
CN115981927A (en) * | 2022-09-06 | 2023-04-18 | 深圳感臻智能股份有限公司 | Device and method for batch testing of USB (universal serial bus) equipment based on windows system |
Also Published As
Publication number | Publication date |
---|---|
CN117349239A (en) | 2024-01-05 |
CN117349240A (en) | 2024-01-05 |
CN116627916A (en) | 2023-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108174185B (en) | Photographing method, device and terminal | |
CN110493595B (en) | Camera detection method and device, storage medium and electronic device | |
CN101840435A (en) | Method and mobile terminal for realizing video preview and retrieval | |
CN111432169B (en) | Video transmission method, device, equipment and system | |
CN111836052B (en) | Image compression method, image compression device, electronic equipment and storage medium | |
CN112995654A (en) | Video playing pause detection method and device, server and readable storage medium | |
CN113627402B (en) | Image identification method and related device | |
CN108712630A (en) | A kind of internet camera system and its implementation based on deep learning | |
CN105243373A (en) | Method for filtering facial images to prevent repeated snapshot, server, intelligent monitoring device and system | |
CN115396705B (en) | Screen operation verification method, platform and system | |
CN107580234B (en) | Photographing method, display end, camera head end and system in wireless live broadcast | |
CN111598176B (en) | Image matching processing method and device | |
CN113011403A (en) | Gesture recognition method, system, medium, and device | |
CN116627916B (en) | Automatic test method and system for multi-path camera data acquisition and data backflow | |
CN111144156B (en) | Image data processing method and related device | |
CN108540817B (en) | Video data processing method, device, server and computer readable storage medium | |
WO2014176746A1 (en) | Method and system for automatically capturing an object using a mobile terminal | |
CN111263113B (en) | Data packet sending method and device and data packet processing method and device | |
CN113127637A (en) | Character restoration method and device, storage medium and electronic device | |
CN116055806A (en) | Mode switching processing method and device of intelligent terminal, terminal and storage medium | |
CN102510427B (en) | Real-time online transmission method for cell phone with low network bandwidth | |
CN114500934A (en) | Monitoring system for realizing automatic transmission of field monitoring images | |
CN114037646A (en) | Intelligent image detection method, system, readable medium and equipment based on Internet of things | |
CN112379856B (en) | Display picture reconstruction device and method | |
CN114448952B (en) | Streaming media data transmission method and device, storage medium 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 |