CN110909719A - Flicker target detection system and method based on moving camera in specific environment - Google Patents
Flicker target detection system and method based on moving camera in specific environment Download PDFInfo
- Publication number
- CN110909719A CN110909719A CN201911274472.5A CN201911274472A CN110909719A CN 110909719 A CN110909719 A CN 110909719A CN 201911274472 A CN201911274472 A CN 201911274472A CN 110909719 A CN110909719 A CN 110909719A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- area
- flashing
- frame
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- 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
Abstract
The invention discloses a flicker target detection system and a method based on a moving camera in a specific environment, comprising an image acquisition device and an image processing device; the image acquisition equipment acquires images of the flickering target in a motion state and sends the images to the image processing equipment in real time; the image processing device is configured to: extracting a suspected area in the real-time detection area; judging the suspected area and the motion state, and replacing the previous frame of image with the current frame of image in real time; identifying the target, namely judging whether the target threshold value meets a set range or not, filtering stray light, and outputting an identification result; judging the target state, performing image frame difference and post-processing, judging whether the frame difference meets the neighborhood and connected domain, if so, determining the target as a flashing target, otherwise, determining the target as an invalid target; and outputting and storing the target position information and the subsequent motion state.
Description
Technical Field
The invention belongs to the technical field of machine vision, and particularly relates to a flicker target detection system based on a moving camera in a specific environment.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The traditional flicker target detection system can realize real-time display of monitoring pictures and video recording storage of moving objects, and has complete detection, extraction and judgment capabilities for static camera dynamic targets. But can not detect the condition of camera and measured object simultaneous movement, can't reject invalid background promptly, can't distinguish scintillation object and sunshine, its main reason is:
the threshold of sunlight varies greatly with the environment:
the sunlight collected by the cameras has different thresholds due to different degrees of sunlight intensity within 24 hours of a day or completely away from 4 hours, wherein the threshold of the sunlight can reach 255 in the midday and can be lower than 20 in the evening. However, in order to ensure that a flickering target or a moving object can be detected in real time, people must watch the monitoring screen, which is a labor and material consuming task, and a worker cannot keep 100% of concentration while monitoring a video picture, so that monitoring of an effective target may be missed.
Mass data calculation of a convolutional neural network or an optical flow method:
the conventional convolutional neural network method requires training of images one frame by one frame, which inevitably results in an increasing amount of data. The optical flow research is to determine the 'motion' of each pixel position by using the time domain variation and the correlation of the pixel intensity data in the image sequence, namely, the relation between the temporal variation of the image gray scale and the object structure and the motion thereof in the scene is researched, and the optical flow research has huge computation amount and low efficiency.
The traditional background elimination algorithm:
although the traditional background elimination algorithm has the advantages of simple thought, easy realization, high operation efficiency and the like, the algorithm itself has limitations. The method mainly has the problems of ghost, static targets, shadow foreground, incomplete moving targets and the like.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides the technical scheme of the flicker target detection system based on the moving camera in the specific environment, so that the camera in the moving state can accurately identify the flicker target.
In order to achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
the flicker target detection system based on the moving camera in the specific environment comprises image acquisition equipment and image processing equipment;
the image acquisition equipment acquires images of the flickering target in a motion state and sends the images to the image processing equipment in real time;
the image processing device is configured to:
extracting a suspected area in the real-time detection area;
judging the suspected area and the motion state, and replacing the previous frame of image with the current frame of image in real time;
identifying the target, namely judging whether the target threshold value meets a set range or not, filtering stray light, and outputting an identification result;
judging the target state, performing image frame difference and post-processing, judging whether the frame difference meets the neighborhood and connected domain, if so, determining the target as a flashing target, otherwise, determining the target as an invalid target;
and outputting and storing the target position information and the subsequent motion state.
According to the further technical scheme, a suspected area is extracted from the real-time detection area, and the method specifically comprises the following steps:
extracting an image and storing a current frame;
extracting an effective target area;
and scanning the area line by line to confirm whether the suspected target exists in the area.
According to the further technical scheme, connected domain and eight neighborhood judgment is carried out on the image after difference, and then later morphological judgment is carried out.
And assigning the judgment result to a flashing target zone bit, if the target is in a flashing state, enabling the processor to set the flashing marker position to be 1, and otherwise, setting the flashing marker position to be 0.
A flicker target detection method based on a moving camera in a specific environment comprises the following steps:
collecting images in real time;
extracting a suspected area in the real-time detection area;
judging the suspected area and the motion state, and replacing the previous frame of image with the current frame of image in real time;
identifying the target, namely judging whether the target threshold value meets a set range or not, filtering stray light, and outputting an identification result;
judging the target state, performing image frame difference and post-processing, judging whether the frame difference meets the neighborhood and connected domain, if so, determining the target as a flashing target, otherwise, determining the target as an invalid target;
and outputting and storing the target position information and the subsequent motion state.
When the image is collected, field interruption is triggered once every set time to enter image collection, and a global shutter camera is adopted to provide an updated background for frame difference.
Determination of suspected targets: the target pixel value is larger than a set threshold value and the image area does not exceed a set maximum area, and no hole exists in the target.
Replacing the previous frame image with the current frame image in real time: updating the background once every time an image is acquired, storing the image of the frame as the image of the previous frame before the next acquisition, and preparing for the frame difference method after the image of the subsequent acquisition comes.
The flashing target is a flashing infrared alarm lamp or a flashing beacon lamp.
The above one or more technical solutions have the following beneficial effects:
the camera in the motion state can accurately identify the flickering target. Setting the target threshold may exclude invalid target disturbances with smaller thresholds.
The frame difference method has the advantages that the time interval between two adjacent frames is very short, the previous frame image is used as a background model and is not accumulated, and the combination of the connected domain algorithm has high updating speed, simple algorithm, small calculated amount and strong timeliness.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a functional block diagram of a motion camera based flash target detection system in a particular environment of the present invention;
FIG. 2 is a flowchart of the operation of a motion camera based flash target detection system in certain circumstances of the present invention;
fig. 3(a) -3 (c) are diagrams of the effect of frame difference post-processing of a motion camera based flicker object detection system in certain environments of the present invention.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The general idea provided by the invention is as follows:
target tracking: the field interruption carries out dynamic scanning on the suspected area, a camera detection area is selected by adjusting a proper threshold value, a real-time image of each frame is extracted, the image of the frame is stored, and the frame is covered with the image of the previous frame; identifying a target, namely judging whether the target is in a flashing state, performing frame difference on the suspected target, performing later-stage judgment, marking the position 1 of a flashing object if the target is a real flashing target, returning to the central coordinate of the tracking target, continuously tracking and informing an MCU (microprogrammed control Unit) to perform related operation; and outputting the target position information and the subsequent motion state.
The detection system is suitable for detection and subsequent tracking of a scintillation object by a motion carrier carrying a camera.
Example one
The embodiment discloses a flicker target detection system based on a moving camera in a specific environment, which comprises image acquisition equipment and image processing equipment;
the image acquisition equipment acquires images of the flickering target in a motion state and sends the images to the image processing equipment in real time;
the image processing device is configured to:
the image monitoring equipment collects and stores images in real time;
extracting a suspected area in the real-time detection area;
replacing the previous frame of image with the current frame of image in real time;
identifying the target, namely judging whether the target threshold value meets a set range or not, filtering stray light, and outputting an identification result;
judging the target state, and performing image frame difference and post-processing;
and outputting and storing the target position information and the subsequent motion state.
And (5) feature extraction, wherein features are extracted from the candidate regions.
In a specific implementation example, the image is extracted and stored in the current frame, and the image information is rapidly updated by using the field interruption of the global shutter camera.
Specifically, the camera triggers a field interruption every 10ms to enter image acquisition, and a global shutter camera is adopted. The purpose is as follows: the updated background is provided for the following frame difference.
And extracting an effective target area, extracting each frame of image acquired by the camera in real time, and extracting a suspected area in the area detected in real time. During extraction, the area larger than the set threshold value is a suspected area, and multiple targets exist in the suspected area.
And scanning the area line by line, confirming whether the suspected target exists in the area, establishing a two-dimensional array for storing the previous frame of image, and replacing the previous frame of image with the current frame of image in real time.
Specifically, the target pixel value is larger than a set threshold value and the image area does not exceed a set maximum area, and meanwhile, no hole exists in the target.
Updating the background once every time an image is acquired, storing the image of the frame as the image of the previous frame before the next acquisition, and preparing for the image acquired below by using a frame difference method after the next acquisition.
And (4) carrying out difference on the current frame and the previous frame of the suspected target, wherein the image after the frame difference is a specific area. And identifying and tracking the target, judging whether the target threshold value meets a set range, and carrying out invalid target screening treatment by using a filter for filtering natural light by band-pass infrared when no special requirement exists, wherein the sunlight interference cannot be eliminated when the step is ended.
At this time, the image may be affected by the environment, and may be strongly interfered at a certain time, so that it is necessary to eliminate the noise.
And the subsequent steps of judging the connected domain and judging the eight neighborhoods of the image obtained by the method to eliminate the sunlight interference.
And judging the connected domain and the eight neighborhoods of the image after the difference, and then judging the morphology at the later stage.
And assigning the judgment result to a flashing target zone bit, if the target is in a flashing state, enabling the processor to set the flashing marker position to be 1, and otherwise, setting the flashing marker position to be 0.
If the judgment is made, the satisfied target is a true target, otherwise, the target pixel is set to 0.
And returning the flicker target position information to the MCU of the M7 series single chip microcomputer for storage, and outputting and storing the target position information and the subsequent motion state.
Referring to fig. 1 and 2, in another aspect of the present invention, a method for monitoring a flickering target in a specific environment based on vision is provided, in which a camera cannot shake violently during a moving process, sunlight is not directly incident on the camera, a flickering object cannot be too small, and the like. The effect is better indoors.
The flashing target is a flashing infrared alarm lamp, a flashing beacon lamp and the like.
The method comprises the following steps:
step 1: extracting an image and storing a current frame;
step 2: extracting an effective target area;
and step 3: scanning the area line by line to determine whether the area has a suspected target;
and 4, step 4: differentiating the current frame and the previous frame of the suspected target
And 5: image frame difference and post-processing;
and 5: judging a connected domain and an eight-neighborhood of the image after the difference;
step 6: assigning the judgment result to a flicker target zone bit;
and 7: and returning the position information of the flashing target to the MCU for storage.
The method aims to accurately distinguish stray light (including sunlight and reflected light) from a flashing object, extract and store a current frame in an image, and rapidly update image information by adopting field interruption of a global shutter camera.
And extracting an effective target area, extracting each frame of image acquired by the camera in real time, and extracting a suspected area in the area detected in real time.
And scanning the area line by line, confirming whether the suspected target exists in the area, establishing a two-dimensional array for storing the previous frame of image, and replacing the previous frame of image with the current frame of image in real time.
And carrying out difference on the current frame and the previous frame of the suspected target to obtain a specific area. And identifying and tracking the target, judging whether the target threshold value meets a set range, and carrying out invalid target screening treatment by using a filter for filtering natural light by band-pass infrared when no special requirement exists, wherein the sunlight interference cannot be eliminated when the step is ended.
And judging the connected domain and the eight neighborhoods of the image after the difference, and then judging the morphology at the later stage.
And assigning the judgment result to a flashing target zone bit, if the target is in a flashing state, enabling the processor to set the flashing marker position to be 1, and otherwise, setting the flashing marker position to be 0.
And returning the flickering target position information to the MCU for storage, and outputting and storing the target position information and the subsequent motion state.
Specifically, the area is scanned line by line to determine whether a suspected target exists in the area.
And carrying out difference on the current frame and the previous frame of the suspected target to obtain a specific area.
In the process of target identification, most of the area of a scintillation object is reserved and meets a connected domain after the difference of two continuous frames of images in the motion process of a camera, most of the area of sunlight is differentiated and only part of the edge is reserved, the edge is discrete, and if the image does not meet the connected domain and the neighborhood, the suspected area image is processed by adopting a frame difference method, and then the neighborhood and the connected domain are adopted for judgment.
Continuously tracking and informing the MCU to perform relevant operations; and outputting and storing the target position information and the subsequent motion state.
A frame difference post-processing effect diagram of a flicker target detection system based on a moving camera in a specific environment of the present invention is shown in fig. 3 (c).
Fig. 3(c) shows the image after the difference between the previous frame and the current frame, and only the discrete edge is left in the left part of the interference light.
The steps involved in the apparatuses of the above second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present invention.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means for execution by the computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (9)
1. A flicker target detection system based on a moving camera in a specific environment is characterized by comprising image acquisition equipment and image processing equipment;
the image acquisition equipment acquires images of the flickering target in a motion state and sends the images to the image processing equipment in real time;
the image processing device is configured to:
extracting a suspected area in the real-time detection area;
judging the suspected area and the motion state, and replacing the previous frame of image with the current frame of image in real time;
identifying the target, namely judging whether the target threshold value meets a set range or not, filtering stray light, and outputting an identification result;
judging the target state, performing image frame difference and post-processing, judging whether the frame difference meets the neighborhood and connected domain, if so, determining the target as a flashing target, otherwise, determining the target as an invalid target;
and outputting and storing the target position information and the subsequent motion state.
2. The system for detecting a flashing object by a moving camera in a specific environment as claimed in claim 1, wherein a suspected area is extracted from the real-time detected area, specifically:
extracting an image and storing a current frame;
extracting an effective target area;
and scanning the area line by line to confirm whether the suspected target exists in the area.
3. The system for motion-camera based detection of a flickering object as claimed in claim 1, wherein the differentiated image is subjected to connected domain and eight neighborhood decision, followed by post morphological decision.
And assigning the judgment result to a flashing target zone bit, if the target is in a flashing state, enabling the processor to set the flashing marker position to be 1, and otherwise, setting the flashing marker position to be 0.
4. A flicker target detection method based on a moving camera in a specific environment is characterized by comprising the following steps:
collecting images in real time;
extracting a suspected area in the real-time detection area;
judging the suspected area and the motion state, and replacing the previous frame of image with the current frame of image in real time;
identifying the target, namely judging whether the target threshold value meets a set range or not, filtering stray light, and outputting an identification result;
judging the target state, performing image frame difference and post-processing, judging whether the frame difference meets the neighborhood and connected domain, if so, determining the target as a flashing target, otherwise, determining the target as an invalid target;
and outputting and storing the target position information and the subsequent motion state.
5. The method as claimed in claim 4, wherein the suspected area is scanned line by line to determine whether the suspected object exists in the suspected area, a two-dimensional array is created to store the previous frame of image, and the previous frame of image is replaced by the current frame of image in real time.
6. The method as claimed in claim 4, wherein the capturing of the image is triggered by a field interruption every predetermined time period, and a global shutter camera is used to provide an updated background for the frame difference.
7. The method of motion-camera based detection of a flickering object in a particular environment as claimed in claim 4, wherein for the determination of a suspected object: the target pixel value is larger than a set threshold value and the image area does not exceed a set maximum area, and no hole exists in the target.
8. The method for detecting a flashing object based on a moving camera in a specific environment as claimed in claim 5, wherein the previous frame of image is replaced by the current frame of image in real time: updating the background once every time an image is acquired, storing the image of the frame as the image of the previous frame before the next acquisition, and preparing for the frame difference method after the image of the subsequent acquisition comes.
9. The method as claimed in claim 5, wherein the flashing object is a flashing infrared alarm light or a flashing beacon light.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911274472.5A CN110909719A (en) | 2019-12-12 | 2019-12-12 | Flicker target detection system and method based on moving camera in specific environment |
| NL2025625A NL2025625B1 (en) | 2019-12-12 | 2020-05-19 | System and method for detecting flickering target based on moving camera in specific environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911274472.5A CN110909719A (en) | 2019-12-12 | 2019-12-12 | Flicker target detection system and method based on moving camera in specific environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110909719A true CN110909719A (en) | 2020-03-24 |
Family
ID=69824924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911274472.5A Pending CN110909719A (en) | 2019-12-12 | 2019-12-12 | Flicker target detection system and method based on moving camera in specific environment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110909719A (en) |
| NL (1) | NL2025625B1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113076800A (en) * | 2021-03-03 | 2021-07-06 | 惠州市博实结科技有限公司 | Road sign board detection method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299351A (en) * | 2014-10-22 | 2015-01-21 | 常州大学 | Intelligent early warning and fire extinguishing robot |
| CN105788142A (en) * | 2016-05-11 | 2016-07-20 | 中国计量大学 | Video image processing-based fire detection system and detection method |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| CN107918765A (en) * | 2017-11-17 | 2018-04-17 | 中国矿业大学 | A kind of Moving target detection and tracing system and its method |
| CN110082781A (en) * | 2019-05-20 | 2019-08-02 | 东北大学秦皇岛分校 | Fire source localization method and system based on SLAM technology and image recognition |
-
2019
- 2019-12-12 CN CN201911274472.5A patent/CN110909719A/en active Pending
-
2020
- 2020-05-19 NL NL2025625A patent/NL2025625B1/en not_active IP Right Cessation
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299351A (en) * | 2014-10-22 | 2015-01-21 | 常州大学 | Intelligent early warning and fire extinguishing robot |
| CN105788142A (en) * | 2016-05-11 | 2016-07-20 | 中国计量大学 | Video image processing-based fire detection system and detection method |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| CN107918765A (en) * | 2017-11-17 | 2018-04-17 | 中国矿业大学 | A kind of Moving target detection and tracing system and its method |
| CN110082781A (en) * | 2019-05-20 | 2019-08-02 | 东北大学秦皇岛分校 | Fire source localization method and system based on SLAM technology and image recognition |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113076800A (en) * | 2021-03-03 | 2021-07-06 | 惠州市博实结科技有限公司 | Road sign board detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| NL2025625B1 (en) | 2021-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105844659B (en) | The tracking and device of moving component | |
| CN109766779B (en) | Loitering person identification method and related product | |
| CN108038415B (en) | Unmanned aerial vehicle automatic detection and tracking method based on machine vision | |
| US20060056702A1 (en) | Image processing apparatus and image processing method | |
| CN109711318B (en) | Multi-face detection and tracking method based on video stream | |
| CN110490043A (en) | A kind of forest rocket detection method based on region division and feature extraction | |
| CN104506819A (en) | Multi-camera real-time linkage mutual feedback tracing system and method | |
| CN108230607B (en) | Image fire detection method based on regional characteristic analysis | |
| CN109413411B (en) | Black screen identification method and device of monitoring line and server | |
| JPH1141589A (en) | Method and system for supervising mobile object | |
| CN112419261B (en) | Visual acquisition method and device with abnormal point removing function | |
| CN101715070B (en) | Method for automatically updating background in specifically monitored video | |
| CN103426183A (en) | Method and device for tracking motion objects | |
| CN111601011A (en) | Automatic alarm method and system based on video stream image | |
| CN106780544B (en) | The method and apparatus that display foreground extracts | |
| WO2022001961A1 (en) | Detection method, detection device and detection system for moving target thrown from height | |
| CN107729811B (en) | Night flame detection method based on scene modeling | |
| CN110909719A (en) | Flicker target detection system and method based on moving camera in specific environment | |
| Tao et al. | Real-time detection and tracking of moving object | |
| CN111753587B (en) | Ground falling detection method and device | |
| CN107403192B (en) | Multi-classifier-based rapid target detection method and system | |
| CN104820818B (en) | A kind of method for quickly identifying of mobile object | |
| JP6784254B2 (en) | Retained object detection system, retained object detection method and program | |
| CN111368726B (en) | Construction site operation face personnel number statistics method, system, storage medium and device | |
| CN113111847A (en) | Automatic monitoring method, device and system for process circulation |
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 |