CN113011227A - Auxiliary detection method for avoiding false alarm during background update pre-judgment period in occlusion detection - Google Patents
Auxiliary detection method for avoiding false alarm during background update pre-judgment period in occlusion detection Download PDFInfo
- Publication number
- CN113011227A CN113011227A CN201911320504.0A CN201911320504A CN113011227A CN 113011227 A CN113011227 A CN 113011227A CN 201911320504 A CN201911320504 A CN 201911320504A CN 113011227 A CN113011227 A CN 113011227A
- Authority
- CN
- China
- Prior art keywords
- signal
- shielding
- detection
- occlusion
- background
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 claims abstract description 31
- 230000008569 process Effects 0.000 claims abstract description 5
- 239000000126 substance Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G06Q50/40—
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The invention provides an auxiliary detection method for avoiding false alarm during background updating pre-judgment in occlusion detection, which divides the whole background updating pre-judgment process into a stage 1: calculating a defocusing signal during the unconverged period of background image exposure, and carrying out shielding auxiliary detection by adopting the defocusing signal; carrying out shielding auxiliary detection through a defocusing signal, directly outputting a shielding early warning signal equal to 1 when the defocusing signal is equal to 1, and predicting the shielding condition of the background image during the unconverged exposure period by using a cache result of shielding detection when the defocusing signal is equal to 0; and (2) stage: during the period that the background image exposure is convergent but does not meet the pre-judgment condition, the false alarm of the shielding detection is avoided by a method of shielding auxiliary detection through gradient characteristics; carrying out shielding auxiliary detection through the gradient features, and judging whether shielding is carried out or not by utilizing whether the minimum block gradient feature is larger than 0 or not during the period that the background image exposure is converged but does not meet the pre-judgment condition; and (3) stage: the background image exposure converges and satisfies the pre-determination condition.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring video processing, in particular to an auxiliary detection method for avoiding false alarm during background updating pre-judgment in occlusion detection.
Background
With the continuous development of science and technology, particularly the development of intelligent technology and the wide application of the internet, particularly in recent years, the promises of the internet appointment vehicle provide convenience for the travel of the public, and in order to guarantee the personal safety of personnel in the vehicle, a monitoring camera is additionally arranged in the vehicle, so that lawless persons can be deterred, the on-site information in the vehicle can be effectively saved, and a powerful evidence is provided for the criminal marching. The in-vehicle monitoring camera needs to save in-vehicle field information on one hand, and needs to give an alarm on the other hand for self abnormal conditions (such as shielding, moving, damage and the like). At present, whether a scene in a vehicle is shielded or not is judged by a monitoring camera in the vehicle mainly through a background frame difference, and the correctness of the background is greatly depended on, so that the system needs to timely and correctly update the background according to the change of the environment in the vehicle (such as garage entering and exiting, day and night change and the like), and the background frame which is possibly updated needs to be pre-judged to ensure the updating of the correct background. During the background update pre-judgment period, occlusion judgment based on the background frame difference may cause occlusion misjudgment, so that occlusion detection needs to be performed by methods other than the background frame difference to avoid occlusion misjudgment. During the occlusion detection background update pre-judgment period, because the environment has changed and the background has not been effectively determined at this time, the background frame difference calculated by the previous background cannot determine the occlusion detection result in the current environment, so that during the background update pre-judgment period, occlusion misinformation can be caused only by the background frame difference method.
Disclosure of Invention
The technical problem that the invention is actually intended to solve is,
during the background update pre-judgment period of occlusion detection, the background frame difference detection result cannot represent the actual occlusion situation due to the change of the environment, so that an auxiliary detection method needs to be adopted to replace a background frame difference method in the period, thereby avoiding the occurrence of false alarm situation.
Specifically, the invention provides an auxiliary detection method for avoiding false alarm during background update pre-judgment in occlusion detection, which divides the whole background update pre-judgment process into three stages:
stage 1: background image exposure unconverged period, stage 2: stage 3, during the period that the background image exposure is converged but does not satisfy the predetermined condition: the exposure of the background image is converged and meets the pre-judgment condition;
wherein the content of the first and second substances,
stage 1: calculating a defocusing signal during the unconverged period of background image exposure, and carrying out shielding auxiliary detection through the defocusing signal; the auxiliary shielding detection is carried out through the defocusing signal, when the defocusing signal is equal to 1, a shielding early warning signal is directly output to be equal to 1, and when the defocusing signal is equal to 0, the shielding condition of the background image during the exposure unconvergence period is predicted by using the cache result of the shielding detection;
and (2) stage: during the period that the background image exposure is convergent but does not meet the pre-judging condition, shielding auxiliary detection is carried out through gradient characteristics; and the shielding auxiliary detection is carried out through the gradient characteristic, and whether shielding is carried out or not is judged by utilizing whether the minimum block gradient characteristic is larger than 0 or not during the period that the background image exposure is converged but does not meet the pre-judgment condition.
Before the calculating the defocus signal, a step of initializing a parameter, wherein a counter cn is 0, is further included.
After the auxiliary shielding detection is carried out through the gradient characteristics, a shielding early warning signal is output, the next frame of image is waited, and a defocusing signal is calculated.
Between the step of calculating the defocusing signal and the step of carrying out shielding auxiliary detection by the defocusing signal, the method further comprises the following steps of:
A. when the background is updated and judged in advance;
B. judging whether the counter is larger than a set delay threshold value: if the time delay is larger than the time delay threshold, executing a step of judging whether a background updating pre-judging condition is met; otherwise, executing the step of shielding auxiliary detection through the defocusing signal.
After the step of performing occlusion auxiliary detection by the defocus signal, the method further comprises a step of judging whether a background update pre-judgment condition is satisfied.
The step of judging whether the background updating pre-judgment condition is satisfied further comprises: if yes, updating the background, performing subsequent occlusion detection, outputting an occlusion early warning signal, waiting for the next frame of image, and performing the step of calculating a defocusing signal; otherwise, executing the step of shielding auxiliary detection through the gradient characteristic.
The step of calculating the defocus signal further includes: acquiring an ISP (image signal processor) defocus parameter afferic; the defocus signal equals 1 if afmetric <0.4 × 65535, otherwise the defocus signal equals 0.
The occlusion-assisted detection by the defocus signal further includes:
H. if the defocusing signal is equal to 1, the shielding early warning signal is equal to 1, the step of outputting the shielding early warning signal, waiting for the next frame of image and calculating the defocusing signal is executed;
I. if the defocus signal is equal to 0, the occlusion warning signal is equal to the occlusion warning signal corresponding to the 15 th frame of image buffered before background updating pre-judgment, wherein 30 frames of images are buffered in total.
The shielding auxiliary detection is carried out through the gradient characteristics, and the method further comprises the following steps:
a. calculating a gradient image by using a sobel operator;
b. calculating the block gradient characteristic distribution; the specific calculation method comprises the following steps: carrying out 4x4 block equalization on the gradient image, and respectively counting the number of pixels with pixel values larger than 100 in each block gradient image, namely the corresponding block gradient characteristic distribution;
c. if the minimum block gradient feature is larger than 0 and the defocus signal is equal to 0, the auxiliary detection result is no occlusion, namely the occlusion early warning signal is equal to 0.
Thus, the present application has the advantages that:
(1) the whole process of background updating pre-judgment is divided into three stages: the exposure of the background image is in a non-convergence period, the exposure of the background image is in a convergence period but does not meet the pre-judgment condition period, and the exposure of the background image is in a convergence period and meets the pre-judgment condition; aiming at the image characteristics of the first two stages, a method of carrying out shielding auxiliary detection through a defocusing signal and a method of carrying out shielding auxiliary detection through gradient characteristics are respectively adopted to avoid misinformation of shielding detection;
(2) the occlusion auxiliary detection is carried out through the defocusing signal, when the defocusing signal is equal to 1, an occlusion early warning signal which is equal to 1 can be directly output, and when the defocusing signal is equal to 0, the occlusion condition of the background image during the exposure unconvergence period is predicted by using the cache result of the occlusion detection, so that the false alarm of the occlusion detection at this stage is avoided;
(3) and performing shielding auxiliary detection through the gradient feature, and judging whether shielding is performed or not by utilizing whether the minimum block gradient feature is larger than 0 or not during the period that the background image exposure is converged but does not meet the pre-judgment condition, thereby avoiding false alarm of shielding detection at the stage.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention.
Fig. 1 is a three-stage schematic block diagram of a method to which the present invention relates.
Fig. 2 is a block flow diagram of a specific method to which the present invention relates.
Fig. 3 is a flow chart of a particular embodiment of the present invention relating to a method.
Detailed Description
In order that the technical contents and advantages of the present invention can be more clearly understood, the present invention will now be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, the method of the present invention is divided into three stages, and the whole process of background update pre-judgment is divided into three stages, which are expressed as follows:
stage 1: calculating a defocusing signal during the unconverged period of background image exposure, and carrying out shielding auxiliary detection by adopting the defocusing signal; the auxiliary shielding detection is carried out through the defocusing signal, when the defocusing signal is equal to 1, a shielding early warning signal is directly output to be equal to 1, and when the defocusing signal is equal to 0, the shielding condition of the background image during the exposure unconvergence period is predicted by using the cache result of the shielding detection;
and (2) stage: during the period that the background image exposure is convergent but does not meet the pre-judgment condition, the false alarm of the shielding detection is avoided by a method of shielding auxiliary detection through gradient characteristics; the shielding auxiliary detection is carried out through the gradient characteristics, and whether shielding is carried out or not is judged by utilizing whether the minimum block gradient characteristics are larger than 0 or not during the period that the background image exposure is converged but does not meet the pre-judgment condition;
and (3) stage: the background image exposure converges and satisfies the pre-determination condition.
As shown in fig. 2, the steps of the method of the present invention can be expressed as follows:
the implementation steps of the invention are as follows:
s1, initializing parameters, wherein a counter cn is equal to 0
S2, calculating defocusing signals
Acquiring an ISP (image signal processor) defocus parameter afferic; if afmetric <0.4 × 65535, the defocus signal equals 1, otherwise the defocus signal equals 0;
s3, timing for pre-judging background updating
S4, judging whether the counter is larger than a set delay threshold value or not
If the delay time is larger than the delay time threshold, executing S6; otherwise, executing S5;
s5, shielding auxiliary detection is carried out through defocusing signals
S6, judging whether the background updating pre-judgment condition is met
If yes, updating the background, carrying out subsequent occlusion detection, and executing S8; otherwise, executing S7;
s7, shielding auxiliary detection is carried out through gradient characteristics
And S8, outputting an occlusion early warning signal, waiting for the next frame of image, and executing S2.
Wherein the content of the first and second substances,
s5, carrying out shielding auxiliary detection through the defocusing signal, comprising the following steps:
s5.1, if the defocusing signal is equal to 1, the shielding early warning signal is equal to 1, and S8 is executed;
s5.1, if the defocusing signal is equal to 0, the shielding early warning signal is equal to the shielding early warning signal corresponding to the 15 th frame of image cached before background updating pre-judgment, wherein 30 frames of images are cached in total;
s7, shielding auxiliary detection is carried out through gradient characteristics, and the method comprises the following steps:
s7.1, calculating a gradient image by using a sobel operator;
s7.2, calculating the block gradient characteristic distribution;
carrying out 4x4 block equalization on the gradient image, and respectively counting the number of pixels with pixel values larger than 100 in each block gradient image, namely the corresponding block gradient characteristic distribution;
s7.3, if the minimum block gradient feature is larger than 0 and the defocusing signal is equal to 0, the auxiliary detection result is no shielding, namely the shielding early warning signal is equal to 0.
As shown in fig. 3, the method of the present invention relates to a flow of a specific embodiment, wherein the method comprises the following main implementation steps:
step 2. calculating defocus signal
2.1 acquiring ISP (image signal processor) defocusing parameter afferic;
2.2 if afferic <0.4 × 65535, then defocus signal defocus _ flag is 1, otherwise defocus _ flag is 0;
step 3, timing for background updating pre-judgment
Accumulating cn to cn +1 by a counter to realize a timing function of pre-judgment;
step 4, judging whether the counter is larger than the set delay threshold value
If cn > UPDATE _ DELAY, perform step 6; otherwise, executing step 5;
5.1 if the defocusing signal is equal to 1, the shielding early warning signal is equal to 1, and the step 8 is executed;
5.2 if the defocusing signal is equal to 0, the blocking early warning signal is equal to the blocking early warning signal corresponding to the 15 th frame of image cached before background updating pre-judgment, wherein 30 frames of images are cached in total;
step 6, judging whether the background updating pre-judging condition is satisfied
If yes, updating the background, performing subsequent shielding detection, and executing the step 8; otherwise, executing step 7;
step 7, shielding auxiliary detection is carried out through gradient characteristics
7.1 calculating a gradient image by using a sobel operator;
7.2 calculating the block gradient characteristic distribution;
carrying out 4x4 block equalization on the gradient image, and respectively counting the number of pixels with pixel values larger than 100 in each block gradient image, namely the corresponding block gradient characteristic distribution;
7.3 if the minimum block gradient feature is greater than 0 and the defocusing signal is equal to 0, the auxiliary detection result is no shielding, namely the shielding early warning signal is equal to 0;
and 8, outputting a shielding early warning signal, waiting for the next frame of image, and executing the step 2.
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 to the embodiment of the present invention 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.
Claims (9)
1. An auxiliary detection method for avoiding false alarm during background update pre-judgment in occlusion detection is characterized in that the whole background update pre-judgment process is divided into three stages:
stage 1: background image exposure unconverged period, stage 2: stage 3, during the period that the background image exposure is converged but does not satisfy the predetermined condition: the exposure of the background image is converged and meets the pre-judgment condition;
wherein the content of the first and second substances,
stage 1: calculating a defocusing signal during the unconverged period of background image exposure, and carrying out shielding auxiliary detection by adopting the defocusing signal; the auxiliary shielding detection is carried out through the defocusing signal, when the defocusing signal is equal to 1, a shielding early warning signal is directly output to be equal to 1, and when the defocusing signal is equal to 0, the shielding condition of the background image during the exposure unconvergence period is predicted by using the cache result of the shielding detection;
and (2) stage: during the period that the background image exposure is convergent but does not meet the pre-judgment condition, the false alarm of the shielding detection is avoided by a method of shielding auxiliary detection through gradient characteristics; and the shielding auxiliary detection is carried out through the gradient characteristic, and whether shielding is carried out or not is judged by utilizing whether the minimum block gradient characteristic is larger than 0 or not during the period that the background image exposure is converged but does not meet the pre-judgment condition.
2. The method of claim 1, further comprising a step of initializing a parameter, wherein a counter cn is 0, before the step of calculating the defocus signal.
3. The method of claim 1, further comprising outputting an occlusion warning signal after the occlusion assistant detection is performed by the gradient feature, waiting for a next frame of image, and performing a step of calculating a defocus signal.
4. The method of claim 1, further comprising, between the step of calculating the defocus signal and the step of performing occlusion aided detection by using the defocus signal, the steps of avoiding false alarms during pre-determination of background update in occlusion detection:
A. when the background is updated and judged in advance;
B. judging whether the counter is larger than a set delay threshold value: if the time delay is larger than the time delay threshold, executing a step of judging whether a background updating pre-judging condition is met; otherwise, executing the step of shielding auxiliary detection through the defocusing signal.
5. The method of claim 1, further comprising a step of determining whether a background update pre-determination condition is satisfied after the step of performing occlusion assisted detection by a defocus signal.
6. The auxiliary detection method for avoiding false alarm during background update pre-judgment in occlusion detection according to claim 4 or 5, wherein the step of judging whether the background update pre-judgment condition is satisfied further comprises: if yes, updating the background, performing subsequent occlusion detection, outputting an occlusion early warning signal, waiting for the next frame of image, and performing the step of calculating a defocusing signal; otherwise, executing the step of shielding auxiliary detection through the gradient characteristic.
7. The method according to claim 4 or 5, wherein the step of calculating the defocus signal further comprises: acquiring a defocusing parameter afferic of an image signal processor; the defocus signal equals 1 if afmetric <0.4 × 65535, otherwise the defocus signal equals 0.
8. The method of claim 1, wherein the occlusion assisted detection with defocus signals further comprises:
H. if the defocusing signal is equal to 1, the shielding early warning signal is equal to 1, the step of outputting the shielding early warning signal, waiting for the next frame of image and calculating the defocusing signal is executed;
I. if the defocus signal is equal to 0, the occlusion warning signal is equal to the occlusion warning signal corresponding to the 15 th frame of image buffered before background updating pre-judgment, wherein 30 frames of images are buffered in total.
9. The method according to claim 1, wherein the occlusion assisted detection by gradient features further comprises:
a. calculating a gradient image by using a sobel operator;
b. calculating the block gradient characteristic distribution; the specific calculation method comprises the following steps: carrying out 4x4 block equalization on the gradient image, and respectively counting the number of pixels with pixel values larger than 100 in each block gradient image, namely the corresponding block gradient characteristic distribution;
c. if the minimum block gradient feature is larger than 0 and the defocus signal is equal to 0, the auxiliary detection result is no occlusion, namely the occlusion early warning signal is equal to 0.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911320504.0A CN113011227B (en) | 2019-12-19 | 2019-12-19 | Auxiliary detection method for avoiding false alarm during background updating pre-judgment in shielding detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911320504.0A CN113011227B (en) | 2019-12-19 | 2019-12-19 | Auxiliary detection method for avoiding false alarm during background updating pre-judgment in shielding detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113011227A true CN113011227A (en) | 2021-06-22 |
CN113011227B CN113011227B (en) | 2024-01-26 |
Family
ID=76382385
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911320504.0A Active CN113011227B (en) | 2019-12-19 | 2019-12-19 | Auxiliary detection method for avoiding false alarm during background updating pre-judgment in shielding detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113011227B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010073835A (en) * | 2008-09-17 | 2010-04-02 | Canon Inc | Exposure apparatus, and method for manufacturing device |
CN102111532A (en) * | 2010-05-27 | 2011-06-29 | 周渝斌 | Camera lens occlusion detecting system and method |
US20120026326A1 (en) * | 2010-07-30 | 2012-02-02 | Hitachi, Ltd. | Surveillance camera system having camera malfunction detection function |
US20120243792A1 (en) * | 2008-12-09 | 2012-09-27 | Mikhail Kostyukov | Detecting and Correcting Blur and Defocusing |
CN104504707A (en) * | 2014-12-26 | 2015-04-08 | 西安理工大学 | Foreign matter blocking detecting method of monitoring camera video images |
CN105657245A (en) * | 2015-11-08 | 2016-06-08 | 乐视移动智能信息技术(北京)有限公司 | Method and apparatus for controlling image exposure convergence in camera starting |
CN107948465A (en) * | 2017-12-11 | 2018-04-20 | 南京行者易智能交通科技有限公司 | A kind of method and apparatus for detecting camera and being disturbed |
CN109858455A (en) * | 2019-02-18 | 2019-06-07 | 南京航空航天大学 | A kind of piecemeal detection scale adaptive tracking method for circular target |
CN109886994A (en) * | 2019-01-11 | 2019-06-14 | 上海交通大学 | Adaptive sheltering detection system and method in video tracking |
CN110121034A (en) * | 2019-05-09 | 2019-08-13 | 腾讯科技(深圳)有限公司 | A kind of method, apparatus and storage medium being implanted into information in video |
CN110233991A (en) * | 2019-06-03 | 2019-09-13 | 上海眼控科技股份有限公司 | A kind of detection method and system for video shelter in video monitoring |
CN110321819A (en) * | 2019-06-21 | 2019-10-11 | 浙江大华技术股份有限公司 | The occlusion detection method, apparatus and storage device of picture pick-up device |
-
2019
- 2019-12-19 CN CN201911320504.0A patent/CN113011227B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010073835A (en) * | 2008-09-17 | 2010-04-02 | Canon Inc | Exposure apparatus, and method for manufacturing device |
US20120243792A1 (en) * | 2008-12-09 | 2012-09-27 | Mikhail Kostyukov | Detecting and Correcting Blur and Defocusing |
CN102111532A (en) * | 2010-05-27 | 2011-06-29 | 周渝斌 | Camera lens occlusion detecting system and method |
US20120026326A1 (en) * | 2010-07-30 | 2012-02-02 | Hitachi, Ltd. | Surveillance camera system having camera malfunction detection function |
CN104504707A (en) * | 2014-12-26 | 2015-04-08 | 西安理工大学 | Foreign matter blocking detecting method of monitoring camera video images |
CN105657245A (en) * | 2015-11-08 | 2016-06-08 | 乐视移动智能信息技术(北京)有限公司 | Method and apparatus for controlling image exposure convergence in camera starting |
CN107948465A (en) * | 2017-12-11 | 2018-04-20 | 南京行者易智能交通科技有限公司 | A kind of method and apparatus for detecting camera and being disturbed |
CN109886994A (en) * | 2019-01-11 | 2019-06-14 | 上海交通大学 | Adaptive sheltering detection system and method in video tracking |
CN109858455A (en) * | 2019-02-18 | 2019-06-07 | 南京航空航天大学 | A kind of piecemeal detection scale adaptive tracking method for circular target |
CN110121034A (en) * | 2019-05-09 | 2019-08-13 | 腾讯科技(深圳)有限公司 | A kind of method, apparatus and storage medium being implanted into information in video |
CN110233991A (en) * | 2019-06-03 | 2019-09-13 | 上海眼控科技股份有限公司 | A kind of detection method and system for video shelter in video monitoring |
CN110321819A (en) * | 2019-06-21 | 2019-10-11 | 浙江大华技术股份有限公司 | The occlusion detection method, apparatus and storage device of picture pick-up device |
Non-Patent Citations (1)
Title |
---|
胡良梅等: "聚焦性检测与彩色信息引导的光场图像深度提取", 《中国图象图形学报》, vol. 21, no. 2, pages 155 - 164 * |
Also Published As
Publication number | Publication date |
---|---|
CN113011227B (en) | 2024-01-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8611593B2 (en) | Foreground object detection system and method | |
WO2020038091A1 (en) | Intelligent driving control method and apparatus, electronic device, program and medium | |
EP3859708B1 (en) | Traffic light image processing method and device, and roadside device | |
JP4203736B2 (en) | Image motion detection apparatus and computer program | |
CN111444854B (en) | Abnormal event detection method, related device and readable storage medium | |
CN104902265A (en) | Background edge model-based video camera anomaly detection method and system | |
KR101939700B1 (en) | Method and Apparatus for Detecting Camera Tampering Using Edge Images | |
WO2022194147A1 (en) | Target object monitoring method and monitoring device | |
KR101630286B1 (en) | Apparatus for separating foreground from background and method thereof | |
CN110636281A (en) | Real-time monitoring camera shielding detection method based on background model | |
CN112770112A (en) | Traffic data anomaly detection method and device, electronic equipment and storage medium | |
CN114821414A (en) | Smoke and fire detection method and system based on improved YOLOV5 and electronic equipment | |
CN102479416B (en) | Method and device for eliminating false alarm in monitoring system | |
CN113011227A (en) | Auxiliary detection method for avoiding false alarm during background update pre-judgment period in occlusion detection | |
WO2013132711A1 (en) | Object detection device, object detection method and program | |
JP2011217201A (en) | Leaving or carrying-away determination apparatus and method | |
US20120243740A1 (en) | Scene Determination and Prediction | |
JP5710230B2 (en) | Monitoring system and monitoring method | |
CN105635524A (en) | Intelligent enhancement method based on dark region histogram area statistics of history frame image | |
CN112927178A (en) | Occlusion detection method, occlusion detection device, electronic device, and storage medium | |
US20070217655A1 (en) | Image detection device | |
CN111325075B (en) | Video sequence target detection method | |
CN113642509A (en) | Garbage bin overflow state detection method and device, storage medium and electronic equipment | |
CN113014744B (en) | Method for detecting shielding of monitoring picture in vehicle | |
CN113011219A (en) | Method for automatically updating background in response to light change in occlusion detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |