CN110909619A - Recognition method based on intelligent police vehicle-mounted camera front-facing image processing - Google Patents
Recognition method based on intelligent police vehicle-mounted camera front-facing image processing Download PDFInfo
- Publication number
- CN110909619A CN110909619A CN201911039973.5A CN201911039973A CN110909619A CN 110909619 A CN110909619 A CN 110909619A CN 201911039973 A CN201911039973 A CN 201911039973A CN 110909619 A CN110909619 A CN 110909619A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- processing
- camera
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an identification method based on intelligent police vehicle-mounted camera front-facing image processing, which comprises the following steps: s1: acquiring a single-frame image; s2: image processing and identification; s3: processing and transmitting information; s4: and (5) processing by the vehicle-mounted server. According to the invention, a real-time single-frame image is acquired through a lens by a sensor of a camera, and a camera processor performs image processing on the acquired single-frame image before image coding to identify the face and license plate information in the image. And the camera processor sends the identified face and license plate information to the vehicle-mounted comparison server after undergoing reprocessing, and then the vehicle-mounted comparison server carries out comparison algorithm processing on the identified information. Compared with a back-end identification method, the method adopts the front-end image identification, the image identification is carried out before the image video coding, and the image is not subjected to coding compression processing, so that the image identification is clear, and the image identification speed is higher than that of the back-end identification after the video coding and decoding frame-dismantling processing.
Description
Technical Field
The invention belongs to the technical field of police vehicle-mounted cameras, and particularly relates to an identification method based on intelligent police vehicle-mounted camera front-facing image processing.
Background
Police car is a motor vehicle used for emergency services in units such as public security agencies, national security agencies, prison administration agencies, community correction agencies, and people's court, people's inspection yards, and the like.
The vehicle-mounted monitoring of the police car is divided into three major parts, namely a vehicle-mounted monitoring system, a communication circuit and a monitoring platform, when the existing police car vehicle-mounted camera is used, a rear-end recognition method is mostly adopted for face recognition and license plate information recognition, the image recognition speed of the recognition method is low, and the recognition accuracy and the image definition are poor, so that the recognition method based on the front-mounted image processing of the intelligent police car vehicle-mounted camera is provided.
Disclosure of Invention
The invention aims to provide an identification method based on intelligent police vehicle-mounted camera front-facing image processing. And the camera processor sends the identified face and license plate information to the vehicle-mounted comparison server after undergoing reprocessing, and then the vehicle-mounted comparison server carries out comparison algorithm processing on the identified information. Compared with a rear-end identification method, the method adopts the front-end image identification, the image identification is carried out before the image video coding, and the image is not subjected to coding compression processing, so that the image is clear to identify, the image identification speed is higher than that of the rear-end identification after the video coding and decoding frame-splitting processing, and the method has the characteristics of high identification speed, high accuracy and clear identification snapshot image, and solves the problems in the prior art in the background technology.
In order to achieve the purpose, the invention adopts the following technical scheme: an identification method based on intelligent police vehicle-mounted camera front-facing image processing comprises the following steps:
s1: acquiring a single-frame image, namely detecting by using a front-end camera sensor on a vehicle-mounted camera and acquiring a real-time single-frame image through a lens;
s2: image processing and identification, wherein a camera processor performs image processing on an acquired single-frame image before image coding, and identifies face and license plate information in the image;
s3: the camera processor sends the identified face and license plate information to the vehicle-mounted comparison server after undergoing the duplication processing;
s4: and processing by the vehicle-mounted server, processing the identified information by a comparison algorithm by the vehicle-mounted comparison server, and finishing image processing and identification.
Preferably, the vehicle-mounted camera comprises a camera sensor and a camera processor.
Preferably, the camera processor is an ARM processor.
Preferably, the camera processor comprises a face recognition module and a license plate information recognition module.
Preferably, the face recognition module includes face image acquisition and detection, face image preprocessing, face image feature extraction, and matching and recognition.
Preferably, the vehicle-mounted comparison server comprises an information comparison module and an algorithm processing module.
Compared with the prior art, the recognition method based on the intelligent police vehicle-mounted camera front-facing image processing has the following advantages that:
1. according to the invention, a real-time single-frame image is acquired through a lens by a sensor of a camera, and a camera processor performs image processing on the acquired single-frame image before image coding to identify the face and license plate information in the image. And the camera processor sends the identified face and license plate information to the vehicle-mounted comparison server after undergoing reprocessing, and then the vehicle-mounted comparison server carries out comparison algorithm processing on the identified information. Compared with a rear-end identification method, the method adopts the front-end image identification, the image identification is carried out before the image video coding, and the image is not subjected to coding compression processing, so that the image is clear in identification, the image identification speed is higher than that of the rear-end identification after the video coding and decoding frame-breaking processing, and the method has the characteristics of high identification speed, high accuracy and clear identification snapshot image.
Drawings
FIG. 1 is a system diagram of an identification method based on intelligent police vehicle-mounted camera front-facing image processing according to the present invention;
fig. 2 is a flowchart of an identification method based on smart police car-mounted camera front-facing image processing according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The specific embodiments described herein are merely illustrative of the invention and do not delimit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the invention provides an identification method based on intelligent police vehicle-mounted camera front-facing image processing, comprising the following steps:
s1: acquiring a single-frame image, namely detecting by using a front-end camera sensor on a vehicle-mounted camera and acquiring a real-time single-frame image through a lens;
s2: image processing and identification, wherein a camera processor performs image processing on an acquired single-frame image before image coding, and identifies face and license plate information in the image;
s3: the camera processor sends the identified face and license plate information to the vehicle-mounted comparison server after undergoing the duplication processing;
s4: and processing by the vehicle-mounted server, processing the identified information by a comparison algorithm by the vehicle-mounted comparison server, and finishing image processing and identification.
Specifically, the vehicle-mounted camera comprises a camera sensor and a camera processor.
According to the category of photosensitive devices, most of lenses used by cameras in the market are a CCD (charge coupled device) and a CMOS (complementary metal oxide semiconductor), wherein the CCD is a high-end technical component applied to the aspects of camera shooting and image scanning due to higher price, and the CMOS is mostly applied to some low-end video products.
In a product adopting CMOS as a photosensitive component, the effect comparable to that of a CCD camera can be completely achieved by adopting an image light source automatic gain reinforcement technology, an automatic brightness and white balance control technology, a color saturation, a contrast ratio, an edge enhancement technology, a gamma correction technology and other advanced image control technologies. Limited by market conditions, market development and other conditions, the number of manufacturers adopting CCD image sensors for cameras is small, and the main reason is the influence of high cost of the CCD image sensors.
The image sensor utilizes the photoelectric conversion function of the photoelectric device. The light image on the light sensing surface is converted into an electric signal in corresponding proportion to the light image. In contrast to the photosensitive elements of "point" light sources such as photodiodes, phototransistors, etc., image sensors are functional devices that divide the light image on their light-receiving surface into many small cells and convert it into usable electrical signals. Image sensors are classified into photoconductive cameras and solid-state image sensors. Compared with a photoconductive camera tube, the solid-state image sensor has the characteristics of small volume, light weight, high integration level, high resolution, low power consumption, long service life, low price and the like. Therefore, the method is widely applied to various industries.
Specifically, the camera processor is an ARM processor.
ARM is a 32-bit Reduced Instruction Set (RISC) processor architecture, which supports two instruction sets in newer architectures: the ARM instruction set and the Thumb instruction set. The ARM instruction is 32 bits long, and the Thumb instruction is 16 bits long. The Thumb instruction set is a functional subset of the ARM instruction set, but compared with an equivalent ARM code, the Thumb instruction set can save more than 30-40% of storage space, and simultaneously has all the advantages of a 32-bit code.
The RISC architecture should have the following characteristics:
the fixed-length instruction format is adopted, the instructions are integrated and simple, and 2-3 basic addressing modes are provided.
And a single-cycle instruction is used, so that the pipeline operation is convenient to execute.
The registers are used in a large quantity, the data processing instruction only operates the registers, and only the load/store instruction can access the memory, so that the execution efficiency of the instruction is improved.
Besides, the ARM architecture also adopts some special technologies, so that the area of a chip is reduced as much as possible on the premise of ensuring high performance, and the power consumption is reduced:
all instructions can be determined whether to be executed according to the previous execution result, so that the execution efficiency of the instructions is improved.
Data can be transferred in bulk with load/store instructions to improve the efficiency of data transfer.
The logic processing and the shift processing may be done simultaneously in one data processing instruction.
The automatic increase and decrease of the address is used in the loop processing to improve the operation efficiency.
Specifically, the camera processor comprises a face recognition module and a license plate information recognition module.
Specifically, the face recognition module comprises face image acquisition and detection, face image preprocessing, face image feature extraction, matching and recognition.
Face image acquisition and detection
Acquiring a face image: different face images can be collected through the camera lens, and for example, static images, dynamic images, different positions, different expressions and the like can be well collected. When the user is in the shooting range of the acquisition equipment, the acquisition equipment can automatically search and shoot the face image of the user.
Face detection: in practice, face detection is mainly used for preprocessing of face recognition, namely, the position and size of a face are accurately calibrated in an image. The face image contains abundant pattern features, such as histogram features, color features, template features, structural features, Haar features, and the like. The face detection is to extract the useful information and to use the features to realize the face detection.
The mainstream face detection method adopts an Adaboost learning algorithm based on the characteristics, wherein the Adaboost algorithm is a method for classification, and combines weak classification methods to form a new strong classification method.
In the process of face detection, an Adaboost algorithm is used for picking out some rectangular features (weak classifiers) which can represent the face most, the weak classifiers are constructed into a strong classifier according to a weighted voting mode, and then a plurality of strong classifiers obtained by training are connected in series to form a cascade-structured stacked classifier, so that the detection speed of the classifier is effectively improved.
Preprocessing a face image: the image preprocessing for the human face is a process of processing the image based on the human face detection result and finally serving for feature extraction. The original image acquired by the system is limited by various conditions and random interference, so that the original image cannot be directly used, and the original image needs to be subjected to image preprocessing such as gray scale correction, noise filtering and the like in the early stage of image processing. For the face image, the preprocessing process mainly includes light compensation, gray level transformation, histogram equalization, normalization, geometric correction, filtering, sharpening, and the like of the face image.
Extracting the features of the face image: features that can be used by a face recognition system are generally classified into visual features, pixel statistical features, face image transform coefficient features, face image algebraic features, and the like. The face feature extraction is performed on some features of the face. Face feature extraction, also known as face characterization, is a process of feature modeling for a face. The methods for extracting human face features are classified into two main categories: one is a knowledge-based characterization method; the other is a characterization method based on algebraic features or statistical learning.
The knowledge-based characterization method mainly obtains feature data which is helpful for face classification according to shape description of face organs and distance characteristics between the face organs, and feature components of the feature data generally comprise Euclidean distance, curvature, angle and the like between feature points. The human face is composed of parts such as eyes, nose, mouth, and chin, and geometric description of the parts and their structural relationship can be used as important features for recognizing the human face, and these features are called geometric features. The knowledge-based face characterization mainly comprises a geometric feature-based method and a template matching method.
Matching and identifying the face image: and searching and matching the extracted feature data of the face image with a feature template stored in a database, and outputting a result obtained by matching when the similarity exceeds a threshold value by setting the threshold value. The face recognition is to compare the face features to be recognized with the obtained face feature template, and judge the identity information of the face according to the similarity degree. This process is divided into two categories: one is confirmation, which is a process of performing one-to-one image comparison, and the other is recognition, which is a process of performing one-to-many image matching comparison.
Specifically, the vehicle-mounted comparison server comprises an information comparison module and an algorithm processing module.
In summary, the following steps: according to the invention, a real-time single-frame image is acquired through a lens by a sensor of a camera, and a camera processor performs image processing on the acquired single-frame image before image coding to identify the face and license plate information in the image. And the camera processor sends the identified face and license plate information to the vehicle-mounted comparison server after undergoing reprocessing, and then the vehicle-mounted comparison server carries out comparison algorithm processing on the identified information. Compared with a back-end identification method, the method adopts the front-end image identification, the image identification is carried out before the image video coding, and the image is not subjected to coding compression processing, so that the image identification is clear, and the image identification speed is higher than that of the back-end identification after the video coding and decoding frame-dismantling processing.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (6)
1. A recognition method based on intelligent police vehicle-mounted camera front-facing image processing is characterized in that: the method comprises the following steps:
s1: acquiring a single-frame image, namely detecting by using a front-end camera sensor on a vehicle-mounted camera and acquiring a real-time single-frame image through a lens;
s2: image processing and identification, wherein a camera processor performs image processing on an acquired single-frame image before image coding, and identifies face and license plate information in the image;
s3: the camera processor sends the identified face and license plate information to the vehicle-mounted comparison server after undergoing the duplication processing;
s4: and processing by the vehicle-mounted server, processing the identified information by a comparison algorithm by the vehicle-mounted comparison server, and finishing image processing and identification.
2. The identification method based on the front-facing image processing of the intelligent police vehicle-mounted camera is characterized by comprising the following steps of: the vehicle-mounted camera comprises a camera sensor and a camera processor.
3. The intelligent police vehicle-mounted camera pre-image processing-based identification method according to claim 2, characterized in that: the camera processor adopts an ARM processor.
4. The intelligent police vehicle-mounted camera pre-image processing-based identification method according to claim 2, characterized in that: the camera processor comprises a face recognition module and a license plate information recognition module.
5. The intelligent police vehicle-mounted camera pre-image processing-based identification method according to claim 4, characterized in that: the face recognition module comprises face image acquisition and detection, face image preprocessing, face image feature extraction, matching and recognition.
6. The identification method based on the front-facing image processing of the intelligent police vehicle-mounted camera is characterized by comprising the following steps of: the vehicle-mounted comparison server comprises an information comparison module and an algorithm processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911039973.5A CN110909619A (en) | 2019-10-29 | 2019-10-29 | Recognition method based on intelligent police vehicle-mounted camera front-facing image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911039973.5A CN110909619A (en) | 2019-10-29 | 2019-10-29 | Recognition method based on intelligent police vehicle-mounted camera front-facing image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110909619A true CN110909619A (en) | 2020-03-24 |
Family
ID=69814637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911039973.5A Pending CN110909619A (en) | 2019-10-29 | 2019-10-29 | Recognition method based on intelligent police vehicle-mounted camera front-facing image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110909619A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113591620A (en) * | 2021-07-15 | 2021-11-02 | 北京广亿兴业科技发展有限公司 | Early warning method, device and system based on integrated mobile acquisition equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1801181A (en) * | 2006-01-06 | 2006-07-12 | 华南理工大学 | Robot capable of automatically recognizing face and vehicle license plate |
| CN109291841A (en) * | 2018-10-24 | 2019-02-01 | 成都安杰联科技有限公司 | A kind of intelligence investigation patrol radio car |
| US20190138842A1 (en) * | 2017-11-06 | 2019-05-09 | Po-Wen Wang | Method of Recognizing Human Face and License Plate Utilizing Wearable Device |
| CN209488674U (en) * | 2018-12-29 | 2019-10-11 | 智慧眼科技股份有限公司 | It is integrated with the video camera of vehicle identification and recognition of face |
-
2019
- 2019-10-29 CN CN201911039973.5A patent/CN110909619A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1801181A (en) * | 2006-01-06 | 2006-07-12 | 华南理工大学 | Robot capable of automatically recognizing face and vehicle license plate |
| US20190138842A1 (en) * | 2017-11-06 | 2019-05-09 | Po-Wen Wang | Method of Recognizing Human Face and License Plate Utilizing Wearable Device |
| CN109291841A (en) * | 2018-10-24 | 2019-02-01 | 成都安杰联科技有限公司 | A kind of intelligence investigation patrol radio car |
| CN209488674U (en) * | 2018-12-29 | 2019-10-11 | 智慧眼科技股份有限公司 | It is integrated with the video camera of vehicle identification and recognition of face |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113591620A (en) * | 2021-07-15 | 2021-11-02 | 北京广亿兴业科技发展有限公司 | Early warning method, device and system based on integrated mobile acquisition equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020077866A1 (en) | Moire-based image recognition method and apparatus, and device and storage medium | |
| CN113052210B (en) | Rapid low-light target detection method based on convolutional neural network | |
| CN109871780B (en) | Face quality judgment method and system and face identification method and system | |
| CN109711407B (en) | License plate recognition method and related device | |
| Nagpal et al. | Facial detection and recognition using OPENCV on Raspberry Pi Zero | |
| CN109801265B (en) | Real-time transmission equipment foreign matter detection system based on convolutional neural network | |
| CN108090428B (en) | Face recognition method and system | |
| CN104408780A (en) | Face recognition attendance system | |
| US7349588B2 (en) | Automatic meter reading | |
| CN109753904A (en) | A kind of face identification method and system | |
| CN107766864B (en) | Method and device for extracting features and method and device for object recognition | |
| CN104616002A (en) | Facial recognition equipment used for judging age groups | |
| CN110188715A (en) | A kind of video human face biopsy method of multi frame detection ballot | |
| CN111444801A (en) | Real-time detection method for infrared target of unmanned aerial vehicle | |
| CN109886086A (en) | Pedestrian detection method based on HOG feature and Linear SVM cascade classifier | |
| Guofeng et al. | Traffic sign recognition based on SVM and convolutional neural network | |
| Ou et al. | Vehicle logo recognition based on a weighted spatial pyramid framework | |
| CN110909619A (en) | Recognition method based on intelligent police vehicle-mounted camera front-facing image processing | |
| CN111325709A (en) | Wireless capsule endoscope image detection system and detection method | |
| CN110866435B (en) | Far infrared pedestrian training method for self-similarity gradient orientation histogram | |
| CN116363535A (en) | Ship detection method in unmanned aerial vehicle aerial image based on convolutional neural network | |
| CN112308193B (en) | Station ticket checking entrance people flow data collection device | |
| US20220405527A1 (en) | Target Detection Methods, Apparatuses, Electronic Devices and Computer-Readable Storage Media | |
| CN112733738A (en) | Method for comparing face recognition data | |
| CN110097758A (en) | Information of vehicles output, storage method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200324 |
|
| RJ01 | Rejection of invention patent application after publication |