CN110765823A - Target identification method and device - Google Patents
Target identification method and device Download PDFInfo
- Publication number
- CN110765823A CN110765823A CN201810846611.6A CN201810846611A CN110765823A CN 110765823 A CN110765823 A CN 110765823A CN 201810846611 A CN201810846611 A CN 201810846611A CN 110765823 A CN110765823 A CN 110765823A
- Authority
- CN
- China
- Prior art keywords
- target
- detail
- image
- determining
- identified
- 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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- 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)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application provides a target identification method, which comprises the following steps: under the condition that the sound signal is detected, acquiring a scene image collected aiming at a current scene; determining a sound source position of the sound signal; determining an object to be recognized in the scene image based on the sound source position; acquiring a detail image acquired aiming at the target to be identified; obtaining the identity information of the target to be recognized by analyzing the detail image; therefore, the identity information of the target is not recognized based on the scene image acquired when the sound signal is detected, but the detail image acquired aiming at the target is acquired, and the identity information of the target is recognized based on the detail image; even if the target is far away from the camera for collecting the scene image, the accuracy of the recognition result is improved by acquiring the detail image containing the clear target.
Description
Technical Field
The present application relates to the field of target detection technologies, and in particular, to a target identification method and apparatus.
Background
In some scenarios, when the presence of an object emitting a sound signal is detected, identity information identifying the object is required. For example, if there is a vehicle that is peccancy on a road, the license plate number of the peccancy vehicle needs to be identified in order to warn or penalize the peccancy vehicle.
The existing target identification method generally comprises the following steps: firstly, a microphone array is used for receiving sound signals, the geographical position of a target which sends the sound signals is determined by positioning the sound signals, then a camera is used for capturing a scene image of a current scene, the target is determined in the scene image according to the geographical position of the target, and further the identity information of the target is identified through the scene image.
In the scheme, if the distance between the target and the camera is long, the shot scene image is not clear, and the target identification result is not accurate.
Disclosure of Invention
The embodiment of the application aims to provide a target identification method and a target identification device so as to improve the accuracy of an identification result.
The specific technical scheme is as follows:
the embodiment of the invention provides a target identification method, which comprises the following steps:
under the condition that the sound signal is detected, acquiring a scene image collected aiming at a current scene;
determining a sound source position of the sound signal;
determining an object to be recognized in the scene image based on the sound source position;
acquiring a detail image acquired aiming at the target to be identified;
and obtaining the identity information of the target to be recognized by analyzing the detail image.
Optionally, in the case that the sound signal is detected, the method further includes:
analyzing the sound signal to obtain the frequency spectrum characteristic of the sound signal;
and judging whether the frequency spectrum characteristics meet a first preset condition, and if so, executing the step of acquiring the scene image acquired aiming at the current scene.
Optionally, the determining the sound source position of the sound signal includes:
and determining the position of a sound source according to the time difference of receiving the sound signal between the microphones in the microphone array for collecting the sound signal.
Optionally, the determining, based on the sound source position, an object to be recognized in the scene image includes:
determining the geographical position of each candidate target in the scene image in the current scene by identifying the scene image;
and matching the sound source position with each determined geographic position, and determining the candidate target at the geographic position successfully matched as the target to be identified.
Optionally, the acquiring a detail image collected for the target to be recognized includes:
determining the moment when the target to be identified reaches the trigger position corresponding to the detail camera;
and acquiring a detail image acquired by the detail camera at the determined moment.
Optionally, the determining the time when the target to be recognized reaches the trigger position corresponding to the detail camera includes:
acquiring a plurality of tracking images collected by a panoramic camera, wherein the panoramic camera is: a camera that captures images of the scene;
tracking the target to be identified in the plurality of tracking images;
and determining the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the tracking result.
Optionally, the determining the time when the target to be recognized reaches the trigger position corresponding to the detail camera includes:
and calculating the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the distance between the sound source position and the trigger position corresponding to the detail camera.
Optionally, before the acquiring the detail image acquired by the detail camera at the determined moment, the method further includes:
judging whether the target to be identified reaches a trigger position corresponding to the detail camera;
and if so, acquiring a detail image aiming at the trigger position by using the detail camera, and recording the acquisition time.
Optionally, the acquiring a detail image collected for the target to be recognized includes:
acquiring candidate detail images acquired by a detail camera;
matching the candidate detail image with a target to be identified in the scene image;
and if the matching is successful, determining the candidate detailed image as a detailed image acquired aiming at the target to be identified.
Optionally, acquiring a scene image collected for a current scene when the sound signal is detected includes:
under the condition that vehicle whistling is detected, a scene image collected aiming at the current scene is obtained;
the determining a sound source position of the sound signal includes:
determining the sound source position of the vehicle whistling;
the determining of the target to be identified in the scene image based on the sound source position comprises:
determining a vehicle target to be identified in the scene image based on the sound source position;
the acquiring of the detail image collected for the target to be identified comprises:
acquiring a detail image acquired aiming at the vehicle target to be identified;
the obtaining of the identity information of the target to be recognized by analyzing the detail image includes:
and obtaining the license plate number of the vehicle target to be identified by analyzing the detail image.
An embodiment of the present invention further provides a target identification apparatus, where the apparatus includes:
the sound signal detection module is used for triggering the scene image acquisition module under the condition that the sound signal is detected;
the scene image acquisition module is used for acquiring a scene image acquired aiming at a current scene;
the sound source positioning module is used for determining the sound source position of the sound signal;
the target determining module is used for determining a target to be identified in the scene image based on the sound source position;
the detail image acquisition module is used for acquiring a detail image acquired aiming at the target to be identified;
and the identity information identification module is used for obtaining the identity information of the target to be identified by analyzing the detail image.
Optionally, the sound signal detection module is further configured to:
analyzing the sound signal to obtain the frequency spectrum characteristic of the sound signal;
and judging whether the frequency spectrum characteristics meet a first preset condition, and if so, executing the step of triggering the scene image acquisition module.
Optionally, the sound source positioning module is specifically configured to:
and determining the position of a sound source according to the time difference of receiving the sound signal between the microphones in the microphone array for collecting the sound signal.
Optionally, the target determining module is specifically configured to:
determining the geographical position of each candidate target in the scene image in the current scene by identifying the scene image;
and matching the sound source position with each determined geographic position, and determining the candidate target at the geographic position successfully matched as the target to be identified.
Optionally, the detail image obtaining module is specifically configured to:
determining the moment when the target to be identified reaches the trigger position corresponding to the detail camera;
and acquiring a detail image acquired by the detail camera at the determined moment.
Optionally, the detail image obtaining module is specifically configured to:
acquiring a plurality of tracking images collected by a panoramic camera, wherein the panoramic camera is: a camera that captures images of the scene;
tracking the target to be identified in the plurality of tracking images;
and determining the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the tracking result.
Optionally, the detail image obtaining module is specifically configured to:
and calculating the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the distance between the sound source position and the trigger position corresponding to the detail camera.
Optionally, the apparatus further comprises:
the detail image acquisition module is used for judging whether the target to be identified reaches a trigger position corresponding to the detail camera; and if so, acquiring a detail image aiming at the trigger position by using the detail camera, and recording the acquisition time.
Optionally, the detail image obtaining module is specifically configured to:
acquiring candidate detail images acquired by a detail camera;
matching the candidate detail image with a target to be identified in the scene image;
and if the matching is successful, determining the candidate detailed image as a detailed image acquired aiming at the target to be identified.
Optionally, the sound signal detection module is specifically configured to trigger the scene image acquisition module when a vehicle whistling sound is detected;
the scene image acquisition module is specifically used for acquiring a scene image acquired aiming at a current scene;
the sound source positioning module is specifically used for determining the sound source position of the vehicle whistling;
the target determining module is specifically configured to determine a vehicle target to be identified in the scene image based on the sound source position;
the detailed image acquisition module is specifically used for acquiring a detailed image acquired aiming at the vehicle target to be identified;
the identity information identification module is specifically used for obtaining the license plate number of the vehicle target to be identified by analyzing the detail image.
The embodiment of the invention also provides electronic equipment which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus;
a memory for storing a computer program;
and a processor for implementing any of the above object recognition methods when executing the program stored in the memory.
An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements any of the above-mentioned object identification methods.
Embodiments of the present application also provide a computer program product containing instructions, which when run on a computer, cause the computer to perform any of the above-mentioned object recognition methods.
According to the target identification method and device provided by the embodiment of the application, under the condition that a sound signal is detected, a scene image acquired aiming at a current scene is acquired, the sound source position of the sound signal is determined, a target to be identified is determined in the scene image based on the sound source position, then a detail image acquired aiming at the target to be identified is acquired, and the identity information of the target to be identified is obtained by analyzing the detail image; therefore, the scheme is not to identify the identity information of the target based on the scene image acquired when the sound signal is detected, but to acquire the detail image acquired aiming at the target and identify the identity information of the target based on the detail image; even if the target is far away from the camera for collecting the scene image, the accuracy of the recognition result is improved by acquiring the detail image containing the clear target. Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a first flowchart of a target identification method according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a second method for identifying a target according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an object recognition apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
In some scenarios, when the presence of an object emitting a sound signal is detected, identity information identifying the object is required. For example, if there is a vehicle peccancy on the road, the license plate number of the peccancy vehicle needs to be identified so as to warn or punish the peccancy vehicle; alternatively, if a person speaks during an examination, information such as the person's admission ticket number needs to be identified in order to be processed.
Generally, in a target identification method, after a sound signal is received by using a microphone array, the sound signal is positioned to determine the geographical position of a target emitting the sound signal, meanwhile, a scene image of a current scene is captured by using a camera, then, the target is determined in the scene image according to the geographical position of the target, and further, the identity information of the target is identified through the scene image.
In the above scheme, the identity information of the target can be acquired by identifying the scene image only when the definition of the scene image is relatively high, so that the coverage area of the camera is limited, and the identity information of the target can be identified only when the image containing the target is shot in a short distance. If the target is far away from the camera or limited by the nature of the camera, the shot scene image is not clear, and the target recognition result is inaccurate.
In order to solve the foregoing technical problem, an embodiment of the present application provides a target identification method, which may be applied to various electronic devices, for example, the target identification method may be implemented by a terminal or a server, and is not limited specifically. The terminal can be arranged on the grab bar, can be a certain image acquisition device, and can also be an independent device connected with the image acquisition device. The image acquisition equipment comprises a panoramic camera and a detail camera. The server may be a background server for analyzing the image collected by the image collecting device and/or positioning the sound source position according to the sound signal collected by the sound collecting device.
The following generally describes the object recognition method provided in the embodiments of the present application.
In one implementation, the target identification method includes:
under the condition that the sound signal is detected, acquiring a scene image collected aiming at a current scene;
determining a sound source position of the sound signal;
determining an object to be recognized in the scene image based on the sound source position;
acquiring a detail image acquired aiming at the target to be identified;
and obtaining the identity information of the target to be recognized by analyzing the detail image.
As can be seen from the above, the target identification method provided in the embodiment of the present application identifies the identity information of the target not based on the scene image acquired when the sound signal is detected, but acquires the detail image acquired for the target, and identifies the identity information of the target based on the detail image; even if the target is far away from the camera for collecting the scene image, the accuracy of the recognition result is improved by acquiring the detail image containing the clear target.
The object identification method provided in the embodiments of the present application will be described in detail below with specific embodiments.
As shown in fig. 1, a first flowchart of a target identification method provided in the embodiment of the present application includes the following steps:
s101: in the case where a sound signal is detected, a scene image captured for the current scene is acquired.
In the scenes of roads, examination rooms and the like, a target emitting a sound signal needs to be identified, for example, if a vehicle peccancy on the road, the peccancy whistle vehicle needs to be identified; alternatively, if a person speaks during the test, the test taker needs to be identified. In these scenes, the current scene may be monitored by the sound acquisition device, and when a sound signal is detected, the large-scene image acquisition device may be further triggered, so as to acquire a scene image acquired for the current scene, where the scene image has a large coverage area and a comprehensive shot content, and the scene image generally includes a plurality of targets.
The sound collecting device may be a single microphone or a group of microphone arrays, and the large-scene image collecting device may be a monitoring camera, a panoramic camera, or the like, which is not limited specifically.
In an implementation manner, after a sound signal is detected, the sound signal may be further analyzed to obtain a spectrum feature of the sound signal, and then, whether the spectrum feature of the sound signal meets a first preset condition is determined, and if the spectrum feature of the sound signal meets the first preset condition, a scene image acquired for a current scene is acquired.
Specifically, the first preset condition may be that the amplitude of the sound signal is greater than a preset amplitude threshold, and if the amplitude is greater than the preset amplitude threshold, it indicates that the volume of the sound signal is greater; it can be understood that the scene image is triggered and acquired only under the condition that the volume of the sound signal is large, and the false triggering condition caused by noise in the scene can be reduced.
Or, the first preset condition may also be that a matching degree between the waveform of the sound signal and a preset waveform is greater than a preset matching degree threshold, and it may be determined that the sound signal is a preset certain sound signal, for example, the preset waveform may be a waveform of a vehicle whistling sound, so that the step of acquiring the scene image collected for the current scene is performed only when the detected sound signal is the whistling sound.
In this way, the step of acquiring the scene image is executed only when a certain specific sound signal meeting the first preset condition is detected, so that the target recognition is carried out, and unnecessary target recognition processes caused by other sound signals are reduced.
S102: the sound source position of the sound signal is determined.
From the detected sound signal, sound source localization can be performed, thereby determining the sound source location of the sound signal.
Specifically, in one implementation, the sound source position may be calculated by using an algorithm based on a time difference, and first, the sound source position may be determined according to a time difference between sound signals received by each microphone in a microphone array that collects the sound signals.
It can be understood that, since the propagation speed of sound is constant, the difference between the distances between the sound source and the microphones can be calculated by the difference between the times at which the respective microphones receive the sound signals, a hyperbola can be determined according to the distance between each two microphones and the difference between the distances between the sound source and the two microphones, and the position of the sound source can be determined according to the intersection point between the determined hyperbolas between each two microphones.
Furthermore, a pair of microphones in each column of the microphone array can be used for collecting sound signals independently, the signal intensity of each sound signal is compared, a pair of microphones with the strongest signal intensity is selected from the sound signals, and the sound signals collected by the microphones are used for determining the position of a sound source, so that the accuracy of sound source positioning is improved, and the calculated amount is reduced.
Alternatively, an algorithm based on high-resolution spectral estimation may be used, or an algorithm based on sparse representation may be used to calculate the sound source position, which is not limited specifically.
S103: and determining the target to be identified in the scene image based on the sound source position.
In one implementation, the target to be identified may be determined in the scene image according to a correspondence between a sound source position and an image coordinate in the scene image. Specifically, the method for determining the correspondence between the sound source position and the image coordinates in the scene image may include: the method comprises the steps of determining some sampling points in a scene in advance, sending sound signals at the sampling points, obtaining sound source positions corresponding to the sound signals and image coordinates of the sampling points in a scene image through calculation, and establishing a mapping relation between the sound source positions and the image coordinates, so that the image coordinates of the sound source positions in the scene image can be directly determined, and further, a target to be recognized can be determined at the image coordinates corresponding to the sound source positions by utilizing a target recognition algorithm.
Or, in another implementation manner, the target to be recognized may be determined in the scene image by matching the target recognition result of the scene image with the sound source position. Specifically, the target recognition may be performed on the scene image, all candidate targets in the scene image are recognized, then the geographic position of each candidate target is calculated, the sound source position is further matched with the geographic position of each candidate target, and the candidate target at the geographic position where the matching is successful is determined as the target to be recognized.
Or, the sound source position may be corresponding to the scene image in other manners, so as to determine the target to be identified in the scene image, which is not limited specifically.
S104: and acquiring a detail image collected aiming at the target to be identified.
After the target to be recognized is determined, a detail image collected aiming at the target to be recognized can be further obtained, the detail image has high definition and contains identity information of the target to be recognized, for example, if a vehicle peccancy on a road, the license plate number of the peccancy whistle vehicle needs to be recognized; alternatively, if a person speaks during the examination, the test taker's reference number may need to be identified.
The detail camera may be an image acquisition device with higher resolution, such as a bayonet capture machine, and the detail camera and the large scene image acquisition device may be two independent image acquisition devices, may also be structurally combined into the same device, may also be two different modes of the same image acquisition device, and is not particularly limited.
For example, if the detail camera and the large-scene image capturing device are two independent image capturing devices, in one implementation, a time when the target to be recognized reaches the trigger position corresponding to the detail camera may be determined first, and then a detail image captured by the detail camera at the determined time may be determined from the multiple detail images, where the detail camera captures the detail image for the target to be recognized only when the target to be recognized reaches the trigger position corresponding to the detail camera, and therefore, the detail image captured by the detail camera at the determined time is the detail image corresponding to the target to be recognized.
The method for determining the acquisition time of the detail image comprises the following steps:
for example, a panoramic camera for acquiring scene images acquires a plurality of tracking images in real time or in each preset period, and the target to be recognized is tracked through the acquired plurality of tracking images, so that the geographic position of the target to be recognized at each moment can be determined, and the moment when the target to be recognized reaches the trigger position corresponding to the detail camera is determined;
or, the distance between the sound source position and the trigger position corresponding to the detail camera may be calculated first, and then the time when the target to be recognized reaches the trigger position corresponding to the detail camera is directly calculated according to the moving speed of the target to be recognized, where the moving speed of the target to be recognized may be preset by a user according to the type of the target to be recognized, for example, if the target to be recognized is a vehicle, the moving speed may be set to 40 kilometers per hour, and if the target to be recognized is a person, the moving speed may be set to 3 kilometers per hour; the panoramic camera may also collect a plurality of tracking images including the target to be recognized within a short time interval, and calculate the displacement of the target to be recognized in the plurality of collected tracking images, so as to obtain the movement speed of the target to be recognized, which is not particularly limited.
In addition, in one implementation manner, the detailed image corresponding to the target to be recognized may be determined by matching the feature information of the target to be recognized.
Specifically, first, in an acquired scene image acquired for a current scene, feature information of an object to be recognized, such as a color and a model of a vehicle or a height and a body type of a person, is recognized, and the feature information may embody some characteristics of the object to be recognized, but is limited by the definition of the scene image, and identity information of the object to be recognized still cannot be further determined.
Then, target recognition is carried out on a plurality of candidate detail images acquired by the detail camera, feature information of a candidate target corresponding to each candidate detail image is recognized, further, the feature information recognized in each candidate detail image can be matched with the feature information of a target to be recognized in the scene image, if matching is successful, the feature information in the candidate detail image is consistent with the feature information of the target to be recognized, and therefore the candidate detail image can be determined to be the detail image acquired aiming at the target to be recognized.
In one case, when each target reaches a trigger position corresponding to the detail camera, the detail image acquisition is performed on the target. Specifically, the position of the detail camera can be monitored through a radar, a coil or a virtual coil, and if a target is detected to reach the position, the detail camera is triggered to acquire a detail image. Alternatively, the detailed image may be acquired in other manners, which are not limited specifically.
S105: and obtaining the identity information of the target to be recognized by analyzing the detail image.
Further, the identification information of the target to be recognized can be obtained by analyzing the detail image collected aiming at the target to be recognized, wherein the identification information can be a license plate of a vehicle or facial features of people, and the like, the identification information and the target to be recognized have a unique corresponding relation, and further, the target to be recognized can be correspondingly processed.
As can be seen from the above, in the target identification method provided in the embodiment of the present application, when a sound signal is detected, a scene image acquired for a current scene is acquired, a sound source position of the sound signal is determined, a target to be identified is determined in the scene image based on the sound source position, then a detail image acquired for the target to be identified is acquired, and the identity information of the target to be identified is obtained by analyzing the detail image; therefore, the identity information of the target is not recognized based on the scene image acquired when the sound signal is detected, but the detail image acquired aiming at the target is acquired, and the identity information of the target is recognized based on the detail image; even if the target is far away from the camera for collecting the scene image, the accuracy of the recognition result is improved by acquiring the detail image containing the clear target.
As shown in fig. 2, a second flowchart of the target identification method provided in the embodiment of the present application includes the following steps:
s201: and under the condition that vehicle whistling is detected, acquiring a scene image acquired aiming at the current scene.
On the road, if there is a vehicle violation, the license plate number of the vehicle violating the whistle needs to be identified so as to warn or punish the vehicle violating the whistle. In the above scene, the current scene may be monitored by the sound collection device, and when a sound signal is detected, the large-scene image collection device may be further triggered, so as to obtain a scene image collected for the current scene, where the scene image has a large coverage area and a comprehensive shot content, and the scene image generally includes a plurality of targets.
The sound collecting device may be a single microphone or a group of microphone arrays, and the large-scene image collecting device may be a monitoring camera, a panoramic camera, or the like, which is not limited specifically.
In one implementation, after a sound signal is detected, the sound signal may be further analyzed to obtain a spectrum characteristic of the sound signal, and then, whether the sound signal is a whistle sound is determined by judging whether the spectrum characteristic satisfies a first preset condition, and if so, a scene image acquired for a current scene is acquired.
Specifically, the first preset condition may be that a matching degree between the waveform of the sound signal and a preset waveform is greater than a preset matching degree threshold, and if the matching degree is greater than the preset matching degree threshold, the sound signal is a whistling sound. Therefore, only when the sound signal is detected to be the whistle, the step of acquiring the scene image is executed, so that the target recognition is carried out, and the unnecessary target recognition process caused by other sound signals is reduced.
S202: and determining the sound source position of the vehicle whistling.
According to the detected whistling sound, sound source positioning can be carried out, and therefore the sound source position of the whistling sound is determined.
Specifically, in one implementation, the sound source position may be calculated by using an algorithm based on a time difference, and first, the sound source position may be determined according to a time difference between sound signals received by each microphone in a microphone array that collects the sound signals.
It can be understood that, since the propagation speed of sound is constant, the difference between the distances between the sound source and the microphones can be calculated by the difference between the times at which the respective microphones receive the sound signals, a hyperbola can be determined according to the distance between each two microphones and the difference between the distances between the sound source and the two microphones, and the position of the sound source can be determined according to the intersection point between the determined hyperbolas between each two microphones.
Furthermore, a pair of microphones in each column of the microphone array can be used for collecting sound signals independently, the signal intensity of each sound signal is compared, a pair of microphones with the strongest signal intensity is selected from the sound signals, and the sound signals collected by the microphones are used for determining the position of a sound source, so that the accuracy of sound source positioning is improved, and the calculated amount is reduced.
Alternatively, an algorithm based on high-resolution spectral estimation may be used, or an algorithm based on sparse representation may be used to calculate the sound source position, which is not limited specifically.
S203: and determining the vehicle target to be identified in the scene image based on the sound source position.
In one implementation, the target to be recognized may be determined in the scene image by matching the target recognition result of the scene image with the sound source position. Specifically, the target recognition may be performed on the scene image, all candidate vehicle targets in the scene image are recognized, then the geographic position of each candidate vehicle target is calculated, the sound source position is further matched with the geographic position of each candidate vehicle target, and the candidate vehicle target at the geographic position where the matching is successful is determined as the vehicle target to be recognized.
Or, the sound source position may be corresponding to the scene image in other manners, so as to determine the vehicle target to be identified in the scene image, which is not limited specifically.
S204: and acquiring a detail image collected aiming at the vehicle target to be identified.
After the vehicle target to be recognized is determined, a detail image collected aiming at the vehicle target to be recognized can be further obtained, wherein the detail image has high definition and contains identity information of the vehicle target to be recognized, such as a license plate number.
The detail camera can be used for acquiring detail images acquired aiming at a vehicle target to be identified, the detail camera can be image acquisition equipment with higher resolution, such as a bayonet snapshot machine and the like, the detail camera and the large scene image acquisition equipment can be two independent image acquisition equipment, can also be structurally combined into the same equipment, can also be two different modes of the same image acquisition equipment, and is not limited specifically.
For example, if the detail camera and the large-scene image capturing device are two independent image capturing devices, in one implementation, a time when the target to be recognized reaches the trigger position corresponding to the detail camera may be determined first, and then a detail image captured by the detail camera at the determined time may be determined from the multiple detail images, where the detail camera captures the detail image for the target to be recognized only when the target to be recognized reaches the trigger position corresponding to the detail camera, and therefore, the detail image captured by the detail camera at the determined time is the detail image corresponding to the target to be recognized.
The mode for determining the acquisition time of the detail image may be as follows: the method comprises the steps that a panoramic camera for collecting scene images collects a plurality of tracking images in real time or in each preset period, and a vehicle target to be identified is tracked through the plurality of acquired tracking images, so that the geographic position of the vehicle target to be identified at each moment can be determined, and the moment when the vehicle target to be identified reaches a trigger position corresponding to a detail camera is determined.
Specifically, after the vehicle target to be recognized is recognized in the scene image, multiple tracking images are acquired, and the vehicle target to be recognized is tracked, or each vehicle target in the tracking images is tracked at the same time, and different identifiers are assigned to each vehicle target, and after the vehicle target to be recognized is recognized in the scene image, the tracking result of the vehicle target to be recognized is directly acquired according to the identifier of the vehicle target to be recognized, which is not limited specifically.
In one case, when each vehicle reaches the position of the detail camera, the detail image acquisition is performed for the vehicle. Specifically, the position of the detail camera can be monitored through a radar, a coil or a virtual coil, and if a vehicle is detected to reach the position, the detail camera is triggered to acquire a detail image. Alternatively, the detailed image may be acquired in other manners, which are not limited specifically.
S205: and obtaining the license plate number of the vehicle target to be identified by analyzing the detail image.
Further, the license plate number of the vehicle target to be recognized can be obtained by analyzing the detail image acquired aiming at the vehicle target to be recognized, and further, the vehicle target to be recognized can be correspondingly processed.
For example, in one implementation, a panoramic camera monitors a current road in real time and assigns identification information to each vehicle in the monitored image. A virtual coil is arranged at the position of a gate of the current road, and when a vehicle passes through the position of the virtual coil, a gate snapshot machine is triggered to snapshot the vehicle. In addition, the microphone array can collect sound signals on the current road.
If vehicles whistle on the current road, the panoramic camera is triggered to capture the current scene after whistling sounds are collected through the microphone array, and a scene image is obtained. And then, positioning the whistling sound, determining the position of the sound source, and matching the position of the sound source with the positions of all vehicles in the scene image, so as to determine the identification information of the whistling vehicles in the monitored image, wherein the identification information is the identification information distributed by the panoramic camera. Furthermore, the whistle vehicle is tracked according to the monitoring image collected by the panoramic camera, the time when the whistle vehicle passes through the bayonet is determined, namely the time when the whistle vehicle passes through the bayonet snapshot machine, so that the detail image corresponding to the whistle vehicle is determined from the image snapshot by the bayonet snapshot machine according to the determined time, and therefore the identity information of the whistle vehicle can be determined by detecting the detail image.
As can be seen from the above, in the target identification method provided in the embodiment of the present application, under the condition that a whistling sound is detected, a scene image acquired for a current scene is obtained, a sound source position of the whistling sound is determined, a vehicle target to be identified is determined in the scene image based on the sound source position, then a detail image acquired for the vehicle target to be identified is obtained, and a license plate number of the vehicle target to be identified is obtained by analyzing the detail image; therefore, the identity information of the target is not recognized based on the scene image acquired when the sound signal is detected, but the detail image acquired aiming at the target is acquired, and the identity information of the target is recognized based on the detail image; even if the target is far away from the camera for collecting the scene image, the accuracy of the recognition result is improved by acquiring the detail image containing the clear target.
An embodiment of the present application further provides a target identification device, as shown in fig. 3, which is a schematic structural diagram of the target identification device provided in the embodiment of the present application, and the device includes:
a sound signal detection module 301, configured to trigger the scene image acquisition module 302 when a sound signal is detected;
the scene image obtaining module 302 is configured to obtain a scene image acquired for a current scene;
a sound source localization module 303, configured to determine a sound source location of the sound signal;
a target determining module 304, configured to determine a target to be identified in the scene image based on the sound source position;
a detail image obtaining module 305, configured to obtain a detail image collected for the target to be identified;
and the identity information identification module 306 is configured to obtain the identity information of the target to be identified by analyzing the detail image.
In one implementation, the sound signal detection module 301 is further configured to:
analyzing the sound signal to obtain the frequency spectrum characteristic of the sound signal;
and judging whether the frequency spectrum characteristics meet a first preset condition, and if so, triggering the scene image acquisition module 302.
In one implementation, the sound source positioning module 303 is specifically configured to:
and determining the position of a sound source according to the time difference of receiving the sound signal between the microphones in the microphone array for collecting the sound signal.
In an implementation manner, the goal determining module 304 is specifically configured to:
determining the geographical position of each candidate target in the scene image in the current scene by identifying the scene image;
and matching the sound source position with each determined geographic position, and determining the candidate target at the geographic position successfully matched as the target to be identified.
In one implementation, the detail image obtaining module 305 is specifically configured to:
determining the moment when the target to be identified reaches the trigger position corresponding to the detail camera;
and acquiring a detail image acquired by the detail camera at the determined moment.
In one implementation, the detail image obtaining module 305 is specifically configured to:
acquiring a plurality of tracking images collected by a panoramic camera, wherein the panoramic camera is: a camera that captures images of the scene;
tracking the target to be identified in the plurality of tracking images;
and determining the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the tracking result.
In one implementation, the detail image obtaining module 305 is specifically configured to:
and calculating the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the distance between the sound source position and the trigger position corresponding to the detail camera.
In one implementation, the apparatus further includes:
the detail image acquisition module 306 is configured to determine whether the target to be identified reaches a trigger position corresponding to the detail camera; and if so, acquiring a detail image aiming at the trigger position by using the detail camera, and recording the acquisition time.
In one implementation, the detail image obtaining module 305 is specifically configured to:
acquiring candidate detail images acquired by a detail camera;
matching the candidate detail image with a target to be identified in the scene image;
and if the matching is successful, determining the candidate detailed image as a detailed image acquired aiming at the target to be identified.
In one implementation, the sound signal detection module 301 is specifically configured to trigger the scene image acquisition module 302 when a vehicle whistling sound is detected;
the scene image obtaining module 302 is specifically configured to obtain a scene image acquired for a current scene;
the sound source positioning module 303 is specifically configured to determine a sound source position of the vehicle whistling;
the target determining module 304 is specifically configured to determine a vehicle target to be identified in the scene image based on the sound source position;
the detail image obtaining module 305 is specifically configured to obtain a detail image collected for the vehicle target to be identified;
the identity information identifying module 307 is specifically configured to obtain the license plate number of the vehicle target to be identified by analyzing the detail image.
As can be seen from the above, the target recognition device provided in the embodiment of the present application, when detecting a whistling sound, acquires a scene image acquired for a current scene, determines a sound source position of the whistling sound, determines a vehicle target to be recognized in the scene image based on the sound source position, then acquires a detailed image acquired for the vehicle target to be recognized, and obtains a license plate number of the vehicle target to be recognized by analyzing the detailed image; therefore, the identity information of the target is not recognized based on the scene image acquired when the sound signal is detected, but the detail image acquired aiming at the target is acquired, and the identity information of the target is recognized based on the detail image; even if the target is far away from the camera for collecting the scene image, the accuracy of the recognition result is improved by acquiring the detail image containing the clear target.
The embodiment of the present application further provides an electronic device, as shown in fig. 4, which includes a processor 401, a communication interface 402, a memory 403, and a communication bus 404, where the processor 401, the communication interface 402, and the memory 403 complete mutual communication through the communication bus 404,
a memory 403 for storing a computer program;
the processor 401, when executing the program stored in the memory 403, implements the following steps:
under the condition that the sound signal is detected, acquiring a scene image collected aiming at a current scene;
determining a sound source position of the sound signal;
determining an object to be recognized in the scene image based on the sound source position;
acquiring a detail image acquired aiming at the target to be identified;
and obtaining the identity information of the target to be recognized by analyzing the detail image.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
As can be seen from the above, the target identification method provided in the embodiment of the present application identifies the identity information of the target not based on the scene image acquired when the sound signal is detected, but acquires the detail image acquired for the target, and identifies the identity information of the target based on the detail image; even if the target is far away from the camera for collecting the scene image, the accuracy of the recognition result is improved by acquiring the detail image containing the clear target.
In yet another embodiment provided by the present application, there is also provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to perform the object identification method as described in any of the above embodiments.
In yet another embodiment provided by the present application, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the object recognition method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be 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. Also, 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 an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device embodiment, the electronic device embodiment and the storage medium embodiment, since they are basically similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.
Claims (15)
1. A method of object recognition, the method comprising:
under the condition that the sound signal is detected, acquiring a scene image collected aiming at a current scene;
determining a sound source position of the sound signal;
determining an object to be recognized in the scene image based on the sound source position;
acquiring a detail image acquired aiming at the target to be identified;
and obtaining the identity information of the target to be recognized by analyzing the detail image.
2. The method according to claim 1, wherein in case of detecting a sound signal, further comprising:
analyzing the sound signal to obtain the frequency spectrum characteristic of the sound signal;
and judging whether the frequency spectrum characteristics meet a first preset condition, and if so, executing the step of acquiring the scene image acquired aiming at the current scene.
3. The method of claim 1, wherein determining the location of the sound source of the sound signal comprises:
and determining the position of a sound source according to the time difference of receiving the sound signal between the microphones in the microphone array for collecting the sound signal.
4. The method according to claim 1, wherein the determining an object to be recognized in the scene image based on the sound source position comprises:
determining the geographical position of each candidate target in the scene image in the current scene by identifying the scene image;
and matching the sound source position with each determined geographic position, and determining the candidate target at the geographic position successfully matched as the target to be identified.
5. The method according to claim 1, wherein the acquiring a detail image acquired for the target to be identified comprises:
determining the moment when the target to be identified reaches the trigger position corresponding to the detail camera;
and acquiring a detail image acquired by the detail camera at the determined moment.
6. The method according to claim 5, wherein the determining the time when the target to be recognized reaches the trigger position corresponding to the detail camera comprises:
acquiring a plurality of tracking images collected by a panoramic camera, wherein the panoramic camera is: a camera that captures images of the scene;
tracking the target to be identified in the plurality of tracking images;
and determining the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the tracking result.
7. The method according to claim 5, wherein the determining the time when the target to be recognized reaches the trigger position corresponding to the detail camera comprises:
and calculating the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the distance between the sound source position and the trigger position corresponding to the detail camera.
8. The method of claim 5, wherein prior to the acquiring the detail image captured by the detail camera at the determined time, the method further comprises:
judging whether the target to be identified reaches a trigger position corresponding to the detail camera;
and if so, acquiring a detail image aiming at the trigger position by using the detail camera, and recording the acquisition time.
9. The method according to claim 1, wherein the acquiring a detail image acquired for the target to be identified comprises:
acquiring candidate detail images acquired by a detail camera;
matching the candidate detail image with a target to be identified in the scene image;
and if the matching is successful, determining the candidate detailed image as a detailed image acquired aiming at the target to be identified.
10. The method of claim 1, wherein acquiring a scene image captured for a current scene if a sound signal is detected comprises:
under the condition that vehicle whistling is detected, a scene image collected aiming at the current scene is obtained;
the determining a sound source position of the sound signal includes:
determining the sound source position of the vehicle whistling;
the determining of the target to be identified in the scene image based on the sound source position comprises:
determining a vehicle target to be identified in the scene image based on the sound source position;
the acquiring of the detail image collected for the target to be identified comprises:
acquiring a detail image acquired aiming at the vehicle target to be identified;
the obtaining of the identity information of the target to be recognized by analyzing the detail image includes:
and obtaining the license plate number of the vehicle target to be identified by analyzing the detail image.
11. An object recognition apparatus, characterized in that the apparatus comprises:
the sound signal detection module is used for triggering the scene image acquisition module under the condition that the sound signal is detected;
the scene image acquisition module is used for acquiring a scene image acquired aiming at a current scene;
the sound source positioning module is used for determining the sound source position of the sound signal;
the target determining module is used for determining a target to be identified in the scene image based on the sound source position;
the detail image acquisition module is used for acquiring a detail image acquired aiming at the target to be identified;
and the identity information identification module is used for obtaining the identity information of the target to be identified by analyzing the detail image.
12. The apparatus of claim 11, wherein the goal determination module is specifically configured to:
determining the geographical position of each candidate target in the scene image in the current scene by identifying the scene image;
and matching the sound source position with each determined geographic position, and determining the candidate target at the geographic position successfully matched as the target to be identified.
13. The apparatus according to claim 11, wherein the detail image acquisition module is specifically configured to:
determining the moment when the target to be identified reaches the trigger position corresponding to the detail camera;
and acquiring a detail image acquired by the detail camera at the determined moment.
14. The apparatus of claim 13, wherein the detail image acquisition module is specifically configured to:
acquiring a plurality of tracking images collected by a panoramic camera, wherein the panoramic camera is: a camera that captures images of the scene;
tracking the target to be identified in the plurality of tracking images;
and determining the moment when the target to be recognized reaches the trigger position corresponding to the detail camera according to the tracking result.
15. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-10 when executing a program stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810846611.6A CN110765823A (en) | 2018-07-27 | 2018-07-27 | Target identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810846611.6A CN110765823A (en) | 2018-07-27 | 2018-07-27 | Target identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110765823A true CN110765823A (en) | 2020-02-07 |
Family
ID=69327093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810846611.6A Pending CN110765823A (en) | 2018-07-27 | 2018-07-27 | Target identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110765823A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112165608A (en) * | 2020-09-22 | 2021-01-01 | 长城汽车股份有限公司 | Parking safety monitoring method and device, storage medium and vehicle |
| CN112738394A (en) * | 2020-12-25 | 2021-04-30 | 浙江大华技术股份有限公司 | Linkage method and device of radar and camera equipment and storage medium |
| CN113255406A (en) * | 2020-02-12 | 2021-08-13 | 浙江宇视科技有限公司 | Video alarm parameter adjusting method, device, equipment and storage medium |
| CN115174818A (en) * | 2022-09-08 | 2022-10-11 | 深圳市维海德技术股份有限公司 | Target tracking method based on sound positioning, electronic equipment and readable storage medium |
| CN115188200A (en) * | 2022-06-30 | 2022-10-14 | 广西中烟工业有限责任公司 | Vehicle identification method and device, electronic equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030323A (en) * | 2007-04-23 | 2007-09-05 | 凌子龙 | Automatic evidence collecting device on crossroad for vehicle horning against traffic regulation |
| US20070237358A1 (en) * | 2006-04-11 | 2007-10-11 | Wei-Nan William Tseng | Surveillance system with dynamic recording resolution and object tracking |
| CN102572282A (en) * | 2012-01-06 | 2012-07-11 | 鸿富锦精密工业（深圳）有限公司 | Intelligent tracking device |
| CN103945098A (en) * | 2014-03-20 | 2014-07-23 | 上海华章信息科技有限公司 | Ultrahigh-definition photographing camera with double camera lenses |
| CN104135645A (en) * | 2014-07-31 | 2014-11-05 | 天津市亚安科技股份有限公司 | Video surveillance system and method for face tracking and capturing |
| CN104200668A (en) * | 2014-07-28 | 2014-12-10 | 四川大学 | Image-analysis-based detection method for helmet-free motorcycle driving violation event |
| CN104794894A (en) * | 2015-01-29 | 2015-07-22 | 青岛智能产业技术研究院 | Automobile whistle noise monitoring device, system and method |
| CN105100724A (en) * | 2015-08-13 | 2015-11-25 | 电子科技大学 | Remote and safe intelligent household monitoring method and device based on visual analysis |
| CN105096606A (en) * | 2015-08-31 | 2015-11-25 | 成都众孚理想科技有限公司 | Automobile whistling and red light running snapshot system |
| CN105893510A (en) * | 2016-03-30 | 2016-08-24 | 北京格灵深瞳信息技术有限公司 | Video structurization system and target search method thereof |
| CN106355893A (en) * | 2016-10-28 | 2017-01-25 | 东方智测（北京）科技有限公司 | Method and system for real-time positioning of whistling motor vehicle |
| CN106487929A (en) * | 2016-12-09 | 2017-03-08 | 庄耿华 | A kind of vehicle-mounted rule-breaking vehicle is blown a whistle automatic detection and evidence-obtaining system |
| CN107045784A (en) * | 2017-01-22 | 2017-08-15 | 苏州奇梦者网络科技有限公司 | A kind of electronic traffic police system |
| CN107346661A (en) * | 2017-06-01 | 2017-11-14 | 李昕 | A kind of distant range iris tracking and acquisition method based on microphone array |
-
2018
- 2018-07-27 CN CN201810846611.6A patent/CN110765823A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070237358A1 (en) * | 2006-04-11 | 2007-10-11 | Wei-Nan William Tseng | Surveillance system with dynamic recording resolution and object tracking |
| CN101030323A (en) * | 2007-04-23 | 2007-09-05 | 凌子龙 | Automatic evidence collecting device on crossroad for vehicle horning against traffic regulation |
| CN102572282A (en) * | 2012-01-06 | 2012-07-11 | 鸿富锦精密工业（深圳）有限公司 | Intelligent tracking device |
| CN103945098A (en) * | 2014-03-20 | 2014-07-23 | 上海华章信息科技有限公司 | Ultrahigh-definition photographing camera with double camera lenses |
| CN104200668A (en) * | 2014-07-28 | 2014-12-10 | 四川大学 | Image-analysis-based detection method for helmet-free motorcycle driving violation event |
| CN104135645A (en) * | 2014-07-31 | 2014-11-05 | 天津市亚安科技股份有限公司 | Video surveillance system and method for face tracking and capturing |
| CN104794894A (en) * | 2015-01-29 | 2015-07-22 | 青岛智能产业技术研究院 | Automobile whistle noise monitoring device, system and method |
| CN105100724A (en) * | 2015-08-13 | 2015-11-25 | 电子科技大学 | Remote and safe intelligent household monitoring method and device based on visual analysis |
| CN105096606A (en) * | 2015-08-31 | 2015-11-25 | 成都众孚理想科技有限公司 | Automobile whistling and red light running snapshot system |
| CN105893510A (en) * | 2016-03-30 | 2016-08-24 | 北京格灵深瞳信息技术有限公司 | Video structurization system and target search method thereof |
| CN106355893A (en) * | 2016-10-28 | 2017-01-25 | 东方智测（北京）科技有限公司 | Method and system for real-time positioning of whistling motor vehicle |
| CN106487929A (en) * | 2016-12-09 | 2017-03-08 | 庄耿华 | A kind of vehicle-mounted rule-breaking vehicle is blown a whistle automatic detection and evidence-obtaining system |
| CN107045784A (en) * | 2017-01-22 | 2017-08-15 | 苏州奇梦者网络科技有限公司 | A kind of electronic traffic police system |
| CN107346661A (en) * | 2017-06-01 | 2017-11-14 | 李昕 | A kind of distant range iris tracking and acquisition method based on microphone array |
Non-Patent Citations (1)
| Title |
|---|
| CHOUFANXIA8451: "车牌识别助力鸣笛抓拍，快准狠", 《HTTPS://BLOG.CSDN.NET/CHOUFANXIA8451/ARTICLE/DETAILS/100944403》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113255406A (en) * | 2020-02-12 | 2021-08-13 | 浙江宇视科技有限公司 | Video alarm parameter adjusting method, device, equipment and storage medium |
| CN112165608A (en) * | 2020-09-22 | 2021-01-01 | 长城汽车股份有限公司 | Parking safety monitoring method and device, storage medium and vehicle |
| CN112738394A (en) * | 2020-12-25 | 2021-04-30 | 浙江大华技术股份有限公司 | Linkage method and device of radar and camera equipment and storage medium |
| CN115188200A (en) * | 2022-06-30 | 2022-10-14 | 广西中烟工业有限责任公司 | Vehicle identification method and device, electronic equipment and storage medium |
| CN115174818A (en) * | 2022-09-08 | 2022-10-11 | 深圳市维海德技术股份有限公司 | Target tracking method based on sound positioning, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110765823A (en) | Target identification method and device | |
| CN107590439B (en) | Target person identification and tracking method and device based on monitoring video | |
| CN110363076B (en) | Personnel information association method and device and terminal equipment | |
| US11398235B2 (en) | Methods, apparatuses, systems, devices, and computer-readable storage media for processing speech signals based on horizontal and pitch angles and distance of a sound source relative to a microphone array | |
| CN106104654B (en) | Vehicle identification | |
| CN112017250B (en) | Calibration parameter determination method and device, radar equipment and Lei Qiu relay system | |
| CN111369799B (en) | Method, device and system for detecting modified vehicle | |
| CN110837077B (en) | Sound source position verification method and device | |
| KR101553000B1 (en) | Video surveillance system and method using beacon, and object managing apparatus therefor | |
| CN101430827B (en) | Taxi wireless video monitoring system and method based on GPS | |
| CN111935641B (en) | Indoor self-positioning realization method, intelligent mobile device and storage medium | |
| CN111368619A (en) | Method, device and equipment for detecting suspicious people | |
| CN112084824A (en) | Passenger reminding method and device, electronic equipment and storage medium | |
| CN112532941A (en) | Vehicle source intensity monitoring method and device, electronic equipment and storage medium | |
| CN111615047B (en) | Method and device for real-time passenger flow statistics, storage medium and electronic equipment | |
| KR101711156B1 (en) | Image security system and method using mobile identification | |
| KR101107120B1 (en) | Device for sound source tracing and object recognition and method for sound source tracing and object recognition | |
| CN117751301A (en) | Method, device, equipment and storage medium for processing laser radar point cloud | |
| CN110728249B (en) | Cross-camera recognition method, device and system for target pedestrian | |
| CN108111802B (en) | Video monitoring method and device | |
| CN112348891A (en) | Image detection and positioning method and device, storage medium and electronic device | |
| CN110263700B (en) | Video processing method, device and equipment and video monitoring system | |
| CN115767424A (en) | Video positioning method based on RSS and CSI fusion | |
| WO2020093828A1 (en) | Method and apparatus for identifying whether device is located in target area, and electronic device | |
| CN108363985B (en) | Target object perception system testing method and device and computer readable storage medium |
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: 20200207 |
|
| RJ01 | Rejection of invention patent application after publication |