CN114202721A - Detection method of low-altitude aircraft - Google Patents
Detection method of low-altitude aircraft Download PDFInfo
- Publication number
- CN114202721A CN114202721A CN202111392734.5A CN202111392734A CN114202721A CN 114202721 A CN114202721 A CN 114202721A CN 202111392734 A CN202111392734 A CN 202111392734A CN 114202721 A CN114202721 A CN 114202721A
- Authority
- CN
- China
- Prior art keywords
- target
- low
- altitude aircraft
- video
- 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
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The invention relates to a detection method of a low-altitude aircraft. The technical scheme adopted by the invention is as follows: a detection method of a low-altitude aircraft is characterized by comprising the following steps: acquiring a video file to be detected; identifying a video file to be detected frame by frame, detecting each frame image in the video file to be detected, and identifying whether a low-altitude aircraft target exists in a video frame of the video file to be detected; determining the continuous occurrence time of the low-altitude aircraft target based on the video frame number of the continuously occurring low-altitude aircraft target and the frame rate of the video file; and segmenting the video file to be detected into a plurality of video segments, and storing the video segments with the continuous occurrence time of the low-altitude aircraft target being greater than a preset value as detection evidence for storage. After whether the low-altitude aircraft target exists in the video frame is identified, the continuous occurrence time of the low-altitude aircraft target is determined according to the number of the video frame frames in which the low-altitude aircraft target continuously appears, and whether the low-altitude aircraft target is reserved as an evidence is determined according to the time.
Description
Technical Field
The invention relates to a detection method of a low-altitude aircraft. The method is suitable for low-altitude target detection and judgment.
Background
With the continuous development of low-altitude aircraft technology, the flight height and the cruising ability of the low-altitude aircraft are continuously improved, and the attention degree on privacy and safety problems is obviously improved. In order to protect safety and privacy, a no-fly zone is arranged in a part of special areas, and due to the particularity of a scene, 24-hour uninterrupted monitoring cannot be realized manually. Therefore, after a privacy-revealing event due to a low-altitude aircraft occurs, it is difficult to trace back the origin of the event, difficult to supervise, difficult to control the event, and may have serious consequences in a special area.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: in order to solve the existing problems, a detection method of the low-altitude aircraft is provided.
The technical scheme adopted by the invention is as follows: a detection method of a low-altitude aircraft is characterized by comprising the following steps:
acquiring a video file to be detected;
identifying a video file to be detected frame by frame, detecting each frame image in the video file to be detected, and identifying whether a low-altitude aircraft target exists in a video frame of the video file to be detected;
determining the continuous occurrence time of the low-altitude aircraft target based on the video frame number of the continuously occurring low-altitude aircraft target and the frame rate of the video file;
and segmenting the video file to be detected into a plurality of video segments, and storing the video segments with the continuous occurrence time of the low-altitude aircraft target being greater than a preset value as detection evidence for storage.
The identifying whether the low-altitude aircraft target exists in the video frame of the video file to be detected comprises the following steps:
and inputting the video frame into the trained target identification model, identifying whether a low-altitude aircraft target exists in the video frame by the target identification model, and if so, outputting the type of the target and the position information of the target area.
Inputting a video to be detected into a trained target tracking model, and predicting the possible predicted position of a target in the current frame by the target tracking model based on the position information of the target in the previous frames of videos;
and jointly judging whether the target appears in the current frame based on the target prediction position in the current frame predicted by the target tracking model and the target position identified from the current frame by the target identification model.
A detection device for a low-altitude aircraft, comprising:
the file acquisition module is used for acquiring a video file to be detected;
the target identification module is used for identifying the video file to be detected frame by frame and identifying whether a low-altitude aircraft target exists in the video frame of the video file to be detected;
the time calculation module is used for determining the continuous occurrence time of the low-altitude aircraft target based on the number of video frames of the continuously occurring low-altitude aircraft target and the frame rate of the video file;
and the evidence preservation module is used for segmenting the video file to be detected into a plurality of video segments, and preserving the video segments of which the continuous occurrence time of the low-altitude aircraft target is greater than a preset value as the detection evidence.
The identifying whether the low-altitude aircraft target exists in the video frame of the video file to be detected comprises the following steps:
and inputting the video frame into the trained target identification model, identifying whether a low-altitude aircraft target exists in the video frame by the target identification model, and if so, outputting the type of the target and the position information of the target area.
The identifying whether the low-altitude aircraft target exists in the video frame of the video file to be detected further comprises:
inputting a video to be detected into a trained target tracking model, and predicting the possible predicted position of a target in the current frame by the target tracking model based on the position information of the target in the previous frames of videos;
and jointly judging whether the target appears in the current frame based on the target prediction position in the current frame predicted by the target tracking model and the target position identified from the current frame by the target identification model.
A storage medium having stored thereon a computer program executable by a processor, the computer program comprising: the computer program, when executed, implements the steps of the method for detecting a low-altitude aircraft.
A detection device for a low-altitude aircraft, having a memory and a processor, the memory having stored thereon a computer program executable by the processor, characterized by: the computer program, when executed, implements the steps of the method for detecting a low-altitude aircraft.
The invention has the beneficial effects that: after whether the low-altitude aircraft target exists in the video frame is identified, the continuous occurrence time of the low-altitude aircraft target is determined according to the number of the video frame frames in which the low-altitude aircraft target continuously appears, and whether the low-altitude aircraft target is reserved as an evidence is determined according to the time.
According to the invention, through the analysis of the continuous multi-frame detection results, an analysis mechanism is added on the basis of common detection only, so that the false detection rate is reduced to a certain extent. The invention only simply analyzes the detection result information of the low-altitude aircraft, has small calculation amount and does not influence the real-time detection.
The invention mainly aims to detect the low-altitude aircraft, and the detection of the target type firstly aims to judge whether a target to be detected exists in a current picture and secondly aims to send accurate detection type information when a user is informed; the position information can directly inform the user of the type when reminding the user in order to mark the position of the low-altitude aircraft in the detection image, so that the user can conveniently perform corresponding processing. The track is identified, firstly, continuous multi-frame detection results are analyzed, the false detection rate of single-frame images is reduced, and secondly, videos containing target tracks are generated, so that a user can be helped to quickly locate the position where the aircraft appears in the retained video evidence.
Drawings
FIG. 1 is a flow chart of an embodiment.
Detailed Description
The embodiment is a detection method of a low-altitude aircraft, which specifically comprises the following steps:
and S1, acquiring the video file to be detected, and acquiring the video file to a local video or a network camera and the like.
And S2, identifying the video file to be detected frame by frame, and identifying whether the low-altitude aircraft target exists in the video frame of the video file to be detected.
And inputting the video frame into the trained target identification model, identifying whether a low-altitude aircraft target exists in the video frame by the target identification model, if so, positioning the target through a rectangular frame in a detection result, and outputting the type of the target and the position information of a target area.
Simultaneously inputting a video to be detected into a trained target tracking model, and predicting the position of a target possibly appearing in a current frame by the target tracking model according to target position information recognized by a target recognition model in continuous frames before the current frame in the video to be used as a predicted position; and judging whether a target appears in the current frame or not in a combined manner according to the target prediction position of the current frame and the position information identified from the current frame by the target identification model, so that the false detection rate of detection is reduced, and the accuracy of the system is improved.
In this embodiment, the intersection ratio between the predicted position and the actually recognized position is analyzed, and when the intersection ratio is greater than a set value, it is determined that the target appears, otherwise, the recognized target is considered not to be the target to be detected.
And S3, determining the continuous appearance time of the low-altitude aircraft target based on the video frame number of the continuous appearance low-altitude aircraft target and the frame rate of the video file.
And counting the continuously-appearing low-altitude aircraft target information, wherein the continuously-appearing low-altitude aircraft target information comprises target position information, frame numbers and the like, determining the continuous appearing time of the low-altitude aircraft target according to the frame numbers of the continuously-appearing low-altitude aircraft target and the frame rate of the video file, and determining the continuous appearing track of the low-altitude aircraft target according to the position information of the continuously-appearing low-altitude aircraft target.
S4, dividing the video file to be detected into a plurality of 10-second video clips, if the continuous occurrence time of the low-altitude aircraft target in a certain video clip is more than 1 second, storing the 10-second video clip as evidence of the low-altitude aircraft, and conveniently obtaining the evidence in the subsequent verification stage when the event occurs.
The embodiment can further optimize a scheme of evidence preservation by combining with the track of the low-altitude aircraft target which continuously appears, for example, when the track needs to appear in a certain specific range and the appearance time is greater than a preset value, the video clip is saved.
The embodiment also provides a detection device of the low-altitude aircraft, which comprises a file acquisition module, a target identification module, a time calculation module and an evidence storage module.
The file acquisition module in the embodiment is used for acquiring a video file to be detected; the target identification module is used for identifying the video file to be detected frame by frame and identifying whether a low-altitude aircraft target exists in the video frame of the video file to be detected; the time calculation module is used for determining the continuous occurrence time of the low-altitude aircraft target based on the number of video frames of the continuously occurring low-altitude aircraft target and the frame rate of the video file; the evidence preservation module is used for dividing the video file to be detected into a plurality of video clips, and preserving the video clips with the continuous occurrence time of the low-altitude aircraft target being greater than the preset value, and preserving the video clips as detection evidence.
The present embodiment is a storage medium having stored thereon a computer program executable by a processor, the computer program when executed implementing the steps of the method of detection of a low-altitude aircraft in the present example.
The present embodiment is a detection device for a low-altitude aircraft, which has a memory and a processor, the memory storing thereon a computer program executable by the processor, the computer program, when executed, implementing the steps of the detection method for a low-altitude aircraft in the present embodiment.
Claims (8)
1. A detection method of a low-altitude aircraft is characterized by comprising the following steps:
acquiring a video file to be detected;
identifying a video file to be detected frame by frame, detecting each frame image in the video file to be detected, and identifying whether a low-altitude aircraft target exists in a video frame of the video file to be detected;
determining the continuous occurrence time of the low-altitude aircraft target based on the video frame number of the continuously occurring low-altitude aircraft target and the frame rate of the video file;
and segmenting the video file to be detected into a plurality of video segments, and storing the video segments with the continuous occurrence time of the low-altitude aircraft target being greater than a preset value as detection evidence for storage.
2. The method for detecting the low-altitude aircraft according to claim 1, wherein the identifying whether the low-altitude aircraft target exists in the video frame of the video file to be detected comprises:
and inputting the video frame into the trained target identification model, identifying whether a low-altitude aircraft target exists in the video frame by the target identification model, and if so, outputting the type of the target and the position information of the target area.
3. The method for detecting a low-altitude aircraft according to claim 2, wherein:
inputting a video to be detected into a trained target tracking model, and predicting the possible predicted position of a target in the current frame by the target tracking model based on the position information of the target in the previous frames of videos;
and jointly judging whether the target appears in the current frame based on the target prediction position in the current frame predicted by the target tracking model and the target position identified from the current frame by the target identification model.
4. A detection device for a low-altitude aircraft, comprising:
the file acquisition module is used for acquiring a video file to be detected;
the target identification module is used for identifying the video file to be detected frame by frame and identifying whether a low-altitude aircraft target exists in the video frame of the video file to be detected;
the time calculation module is used for determining the continuous occurrence time of the low-altitude aircraft target based on the number of video frames of the continuously occurring low-altitude aircraft target and the frame rate of the video file;
and the evidence preservation module is used for segmenting the video file to be detected into a plurality of video segments, and preserving the video segments of which the continuous occurrence time of the low-altitude aircraft target is greater than a preset value as the detection evidence.
5. The device for detecting the low-altitude aircraft according to claim 4, wherein the identifying whether the low-altitude aircraft target exists in the video frame of the video file to be detected comprises:
and inputting the video frame into the trained target identification model, identifying whether a low-altitude aircraft target exists in the video frame by the target identification model, and if so, outputting the type of the target and the position information of the target area.
6. The device for detecting the low-altitude aircraft according to claim 5, wherein the identifying whether the low-altitude aircraft target exists in the video frame of the video file to be detected further comprises:
inputting a video to be detected into a trained target tracking model, and predicting the possible predicted position of a target in the current frame by the target tracking model based on the position information of the target in the previous frames of videos;
and jointly judging whether the target appears in the current frame based on the target prediction position in the current frame predicted by the target tracking model and the target position identified from the current frame by the target identification model.
7. A storage medium having stored thereon a computer program executable by a processor, the computer program comprising: the computer program when executed implements the steps of the method of detection of a low-altitude aircraft according to claim 1 or 2 or 3.
8. A detection device for a low-altitude aircraft, having a memory and a processor, the memory having stored thereon a computer program executable by the processor, characterized by: the computer program when executed implements the steps of the method of detection of a low-altitude aircraft according to claim 1 or 2 or 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111392734.5A CN114202721A (en) | 2021-11-19 | 2021-11-19 | Detection method of low-altitude aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111392734.5A CN114202721A (en) | 2021-11-19 | 2021-11-19 | Detection method of low-altitude aircraft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114202721A true CN114202721A (en) | 2022-03-18 |
Family
ID=80648508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111392734.5A Pending CN114202721A (en) | 2021-11-19 | 2021-11-19 | Detection method of low-altitude aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114202721A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114998761A (en) * | 2022-06-15 | 2022-09-02 | 北京庚图科技有限公司 | Airplane target detection method and device, electronic equipment and medium |
-
2021
- 2021-11-19 CN CN202111392734.5A patent/CN114202721A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114998761A (en) * | 2022-06-15 | 2022-09-02 | 北京庚图科技有限公司 | Airplane target detection method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9684835B2 (en) | Image processing system, image processing method, and program | |
| US20180115749A1 (en) | Surveillance system and surveillance method | |
| US9811755B2 (en) | Object monitoring system, object monitoring method, and monitoring target extraction program | |
| KR102195706B1 (en) | Method and Apparatus for Detecting Intruder | |
| US10853949B2 (en) | Image processing device | |
| US11776274B2 (en) | Information processing apparatus, control method, and program | |
| CN107122743B (en) | Security monitoring method and device and electronic equipment | |
| CN111738240A (en) | Region monitoring method, device, equipment and storage medium | |
| CN112422909B (en) | Video behavior analysis management system based on artificial intelligence | |
| CN111489380B (en) | Target object track analysis method | |
| CN103514429A (en) | Method for detecting specific part of object and image processing equipment | |
| EP3432575A1 (en) | Method for performing multi-camera automatic patrol control with aid of statistics data in a surveillance system, and associated apparatus | |
| CN114202721A (en) | Detection method of low-altitude aircraft | |
| KR20160037480A (en) | Method for establishing region of interest in intelligent video analytics and video analysis apparatus using the same | |
| US10748011B2 (en) | Method, device and system for detecting a loitering event | |
| CN110244923B (en) | Image display method and device | |
| US8126212B2 (en) | Method of detecting moving object | |
| US20200394802A1 (en) | Real-time object detection method for multiple camera images using frame segmentation and intelligent detection pool | |
| CN112883866A (en) | Method, system and storage medium for detecting regional invasion in real time | |
| KR101395666B1 (en) | Surveillance apparatus and method using change of video image | |
| CN101916380A (en) | Video-based device and method for detecting smog | |
| CN111753587B (en) | Ground falling detection method and device | |
| US20050128298A1 (en) | Method for following at least one object in a scene | |
| CN114612844A (en) | Smoking detection method and device, electronic equipment and storage medium | |
| JPH02182093A (en) | Monitor |
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 |