CN103455998A - Method and device for detecting shadows in video image - Google Patents
Method and device for detecting shadows in video image Download PDFInfo
- Publication number
- CN103455998A CN103455998A CN2012101810897A CN201210181089A CN103455998A CN 103455998 A CN103455998 A CN 103455998A CN 2012101810897 A CN2012101810897 A CN 2012101810897A CN 201210181089 A CN201210181089 A CN 201210181089A CN 103455998 A CN103455998 A CN 103455998A
- Authority
- CN
- China
- Prior art keywords
- target
- shadow
- current frame
- frame image
- range
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 abstract description 13
- 230000000694 effects Effects 0.000 abstract description 10
- 238000010223 real-time analysis Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 22
- 238000010586 diagram Methods 0.000 description 11
- 230000008030 elimination Effects 0.000 description 11
- 238000003379 elimination reaction Methods 0.000 description 11
- 238000000605 extraction Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a method and device for detecting shadows in a video image. The method comprises the steps of acquiring the target characteristics of a monitored target in the current frame of image, rotating all the acquired target characteristics in a preset rotating range, and matching each target characteristic obtained through rotation with the preprocessed current frame of image, wherein the preset rotating range is the changing range of the shadows generated by the monitored target in the current frame of image in a light source position changing range; determining the area where the target characteristics matched with the current frame of image to be the shadow area of the monitored target. Through the technical scheme, the technical problems that in the related technologies, an existing shadow detecting and eliminating method is poor in shadow eliminating effect and complex to achieve are solved, the effect of eliminating the shadows is enhanced, the method and device are easy to achieve, and the requirement for the real-time analysis and processing of video can be met.
Description
Technical Field
The invention relates to the field of communication, in particular to a method and a device for detecting shadows in a video image.
Background
In a video monitoring scene, particularly under the condition of irradiation of strong light sources such as outdoor sunlight, the target can generate shadows. Since the shadow has similar characteristics with the object, such as contour, size, motion characteristics, etc., the shadow is often extracted together with the object when the object is extracted. This seriously affects the extraction, tracking and behavioral analysis of real targets. In intelligent video surveillance applications, how to eliminate shadows is one of the key and very difficult problems to solve.
At present, there are various shadow detection methods to eliminate the shadow in the image, but all have defects, such as: (1) the shadow detection method based on the color model identifies the shadow by the characteristic that the difference between the shadow pixel point and the background pixel point in the color tone is small. However, the effect of eliminating the detected shadow based on the method is not good; (2) the shadow detection method based on the geometric features of the target calculates position parameters and establishes a 3D model so as to eliminate shadows. The calculation of the position parameters to establish the model is complex to realize and difficult to meet the performance requirement of real-time video processing,
in summary, the method of detecting the shadow by using the color model, the geometric feature of the shadow, etc. is not ideal from the aspect of eliminating the shadow and realizing the effect.
In view of the above problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
The invention provides a method and a device for detecting shadows in video images, aiming at the technical problems that the existing shadow detection and elimination method in the prior art has poor shadow elimination effect, complex realization and the like.
According to an aspect of the present invention, there is provided a method for detecting a shadow in a video image, including: acquiring target characteristics of a monitored target in a current frame image; rotating each acquired target feature within a preset rotation range; matching each target feature obtained by rotation with the current frame image after preprocessing, wherein the preset rotation range is the variation range of the shadow generated by the monitored target in the current frame image within the variation range of the light source position; and determining the region where the target features matched with the current frame image are located as the shadow region of the monitored target.
The preset rotation range is obtained by the following method: taking the vertical direction of the monitored target on the ground as a target direction; and in the light source position variation range, acquiring the shadow direction forming the maximum included angle and the minimum included angle with the target direction in the current frame image, and taking the angle range of the maximum included angle and the minimum included angle as a preset rotation range.
Before obtaining the target characteristics of the monitored target in the current frame image, the method comprises the following steps: acquiring the contour of a monitored target; and acquiring corner features of the monitored target in the outline range, wherein the corner features are used for describing the target features.
The above-mentioned target characteristic is the angular point characteristic of the current frame image, match every above-mentioned target characteristic that will be rotated with the current frame image after preconditioning, including: matching the corner feature of the current frame image with the corner feature in the acquired contour range; determining the region where the target features matched with the current frame image are located as the shadow region of the monitored target, wherein the determining comprises the following steps: and determining the corner features of the current frame image successfully matched as the corner features of the shadow, wherein the region where the corner features of the shadow are located is a shadow region.
After determining the region where the target feature matched with the current frame image is located as the shadow region of the monitored target, the method comprises the following steps: and filtering out the shadow area in the current frame image.
According to another aspect of the present invention, there is provided an apparatus for detecting a shadow in a video image, comprising: the acquisition module is used for acquiring the target characteristics of the monitored target in the current frame image; the rotating module is used for rotating each acquired target feature within a preset rotating range; the matching module is used for matching each target feature obtained by rotation with the current frame image after preprocessing, wherein the preset rotation range is the variation range of the shadow generated by the monitored target in the current frame image within the variation range of the light source position; and the determining module is used for determining the region where the target features matched with the current frame image are located as the shadow region of the monitored target.
The preset rotation range is obtained by the following method: taking the vertical direction of the monitored target on the ground as a target direction; and in the light source position variation range, acquiring the shadow direction forming the maximum included angle and the minimum included angle with the target direction in the current frame image, and taking the angle range of the maximum included angle and the minimum included angle as a preset rotation range.
The acquisition module is further used for acquiring the contour of the monitored target; and acquiring corner features of the monitored target within the contour range, wherein the corner features are used for describing the target features.
The matching module is further configured to match the corner feature of the current frame image with the corner feature in the acquired contour range when the target feature is the corner feature of the current frame image; the determining module is further configured to determine the corner features of the successfully matched current frame image as the corner features of the shadow, where an area where the corner features of the shadow are located is a shadow area.
The above-mentioned device still includes: and the filtering module is used for filtering the shadow area in the current frame image.
According to the invention, by adopting the technical means of rotating and extracting each target feature in the current frame image within the included angle range of the monitored target direction and the shadow direction thereof and matching the extracted target feature with the preprocessed current frame image, the technical problems of poor shadow elimination effect, complex realization and the like in the existing shadow detection and elimination method in the related art are solved, so that the shadow elimination effect is enhanced, the realization is simple, and the requirement of real-time video analysis and processing can be met.
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 invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a method for detecting shadows in a video image according to an embodiment of the invention;
FIG. 2 is a block diagram of an apparatus for detecting shadows in a video image according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a device for detecting shadows in a video image according to a preferred embodiment of the present invention;
FIG. 4 is a flow diagram of a method of human-assisted shadow detection according to an embodiment of the invention;
FIG. 5 is a block diagram of a target extraction system according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of the principle of setting the target direction and the shadow direction according to an embodiment of the present invention;
FIG. 7 is a schematic view of a target profile according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of corner features within the target contour based on the embodiment shown in FIG. 7;
fig. 9 is a schematic diagram of a process of matching the characteristics of the rotating target corner points according to an embodiment of the present invention;
fig. 10 is a schematic diagram of extracting corner features in a current image according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Fig. 1 is a flowchart of a method for detecting shadows in a video image according to an embodiment of the invention. As shown in fig. 1, the method includes:
step S102, obtaining the target characteristics of the monitored target in the current frame image;
step S104, rotating each acquired target feature within a preset rotation range;
step S106, matching each target feature obtained by rotation with a current frame image after preprocessing, wherein the preset rotation range is the variation range of the shadow generated by the monitored target in the current frame image within the variation range of the light source position;
and step S108, determining the area where the target features matched with the current frame image are located as the shadow area of the monitored target.
By adopting the processing steps, the shadow is detected according to the variation range of the shadow generated by the monitored target in the variation range of the light source position in the current frame image, so the shadow can be effectively identified, the shadow in the image can be effectively eliminated based on the shadow, and meanwhile, the requirement of real-time analysis and processing of the video can be met due to simple detection implementation.
In step S102, the target feature of the monitored target may be obtained in real time, or may be obtained from a target feature library.
The preset rotation range can be obtained by manual pre-measurement, and at the moment, the vertical direction of the monitored target on the ground is required to be used as a target direction; and in the light source position variation range, acquiring the shadow direction forming a maximum included angle and a minimum included angle with the target direction in the current frame image, and taking the angle range of the maximum included angle and the minimum included angle as a preset rotation range.
In step S106, the matching may be performed by corner feature matching, in which case, before acquiring the target feature of the monitored target in the current frame image, the following processing procedure needs to be performed: acquiring the outline of the monitored target (which can be manually drawn and acquired); acquiring corner features of the monitored target within the outline range, wherein the corner features are used for describing the target features.
Based on the above processing procedure, in order to implement a corner feature matching manner, when the obtained target feature is a corner feature of a current frame image, determining a region where the target feature matched with the current frame image is located as a shadow region of the monitored target, including: and matching the corner features of the current frame image with the corner features in the acquired contour range. At this time, the corner features of the current frame image which are successfully matched are determined as the corner features of the shadow, wherein the region where the corner features of the shadow are located is the shadow region.
In order to realize the shadow removing effect of the image, after determining the region where the target feature matched with the current frame image is located as the shadow region in step S108, the method includes: and filtering the shadow area in the current frame image.
In a preferred implementation of the present invention, the above processes and preferred implementations may be embodied in the following forms:
first, each frame of video image is captured by the camera.
The target direction and the shadow direction are then set manually. When the target direction is set, the vertical direction of the target on the ground is set. When the shadow direction is set, namely in the light source position change range, the change direction of the shadow formed by the target only needs to be recorded: one is the shadow direction forming the largest angle with the target direction and the other is the shadow direction forming the smallest angle with the target direction. The two angles describe the extent of the shade variation.
And then manually assisting in extracting the target features. The curve is used for drawing the outline of the target, and then the corner points in the curve description range are extracted by using a corner point detection algorithm to describe the target features. The corner points can effectively reduce the data volume of the information while keeping the important characteristics of the image graph, so that the content of the information is high, the calculation speed is effectively improved, the reliable matching of the image is facilitated, and the real-time processing becomes possible. For some common targets, the target characteristics can be saved and recorded into a target characteristic library.
When the features are matched, each target corner feature in the target feature library is used for matching the corner features of the shadow in the image. Since the target and the shadow have similar outlines but different directions, the target shadow can be detected by using corner feature matching. The detection method comprises the following steps: a frame of image is selected from a real-time video stream, and after preprocessing, a corner detection algorithm is used for extracting corners on the frame of image. Each target feature is then selected from the library of target features. And rotating the target characteristics by a certain angle according to a preset included angle range. And matching with the target corner features on the video frame image to identify the target shadow.
After the included angle range is set, the range of shadow detection can be limited, and similar target objects are effectively prevented from being filtered.
Finally, the shadow is eliminated. And directly filtering the objects in the successfully matched shadow area.
Based on the uploading processing step, in the preferred embodiment, there is further provided a target extraction system to implement the processing procedure, where the target extraction system includes: the system comprises a video image acquisition module, a setting module, a target feature library maintenance module, a feature matching module and a shadow elimination module. Wherein,
the video image acquisition module is used for acquiring real-time video frame images;
and the setting module is used for setting the target direction and the shadow direction, and calculating the range of an included angle between the target direction and the shadow direction so as to limit the rotation range of the target characteristic.
And the target feature library maintenance module is used for manually assisting in describing the target contour, then extracting the target features through a corner detection algorithm and inputting the target features into the feature library.
And the characteristic matching module is used for identifying the shadow in the video image frame. And (3) matching each target feature in the feature library with the preprocessed video image frame after rotating a certain angle according to a preset included angle range, and recognizing a target shadow.
And the shadow elimination module is used for eliminating the shadow area. And directly filtering the targets in the shadow area identified by the feature matching module.
In this embodiment, a device for detecting a shadow in a video image is further provided, which is used to implement the foregoing embodiments and preferred embodiments, and the description already made is omitted, and the modules involved in the device are described below. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Fig. 2 is a block diagram of an apparatus for detecting shadows in a video image according to an embodiment of the present invention. As shown in fig. 2, the apparatus includes:
the acquisition module 20 is connected to the rotation module 22 and is used for acquiring the target characteristics of the monitored target in the current frame image;
the rotating module 22 is connected to the matching module 24 and is used for rotating each acquired target feature within a preset rotating range;
the matching module 24 is connected to the determining module 26, and matches each target feature obtained by rotation with the current frame image after preprocessing, wherein the preset rotation range is a variation range of a shadow generated by the monitored target in the current frame image within a variation range of the light source position;
and the determining module 26 is configured to determine a region where the target feature matched with the current frame image is located as a shadow region of the monitored target.
Through the functions realized by the processing modules, the shadow can be detected according to the variation range of the shadow generated by the monitored target in the variation range of the light source position in the current frame image, so that the shadow can be effectively identified, the shadow in the image can be effectively eliminated based on the detection, and meanwhile, the requirements of real-time video analysis and processing can be met due to simple detection realization
In a preferred embodiment of the present invention, the preset rotation range is obtained by: taking the vertical direction of the monitored target on the ground as a target direction; and in the light source position variation range, acquiring the shadow direction forming a maximum included angle and a minimum included angle with the target direction in the current frame image, and taking the angle range of the maximum included angle and the minimum included angle as the preset rotation range.
Preferably, the obtaining module 20 is further configured to obtain a contour of the monitored target; and acquiring corner features of the monitored target in the contour range, wherein the corner features are used for describing the target features.
Preferably, the matching module 22 is further configured to match the corner feature of the current frame image with the obtained corner feature in the contour range, when the target feature is the corner feature of the current frame image; the determining module 26 is further configured to determine the corner features of the current frame image successfully matched as the corner features of the shadow, where the region where the corner features of the shadow are located is a shadow region.
Preferably, as shown in fig. 3, the apparatus may further include: and the filtering module 28 is configured to filter out the shadow area in the current frame image.
For a better understanding of the above embodiments, reference is made to the following detailed description of the embodiments taken in conjunction with the accompanying drawings
Examples
The present embodiment provides a method for artificially assisting shadow detection, as shown in fig. 4, the method includes the following steps:
step S402, the camera collects video images.
And S404, setting a shadow direction and a target direction, and calculating the range of an included angle between the shadow direction and the target direction. The method is used for limiting the direction of the identified shadow and reducing the matching range.
And S406, drawing a target contour by using a curve, extracting target characteristics by adopting an angular point detection algorithm, and inputting a target characteristic library.
Step S408, rotating the target contour features within the included angle range, and matching the shadow by using the corner features: rotating the target contour features within the included angle range for each target feature in the feature library; preprocessing a video frame to obtain a gray scale image, extracting corner features of the gray scale image, and then matching the rotated target corner features with the corner features of the gray scale image to identify a shadow.
Step S410, elimination of shadow: the labeling identifies the shaded area, which is not the target extraction area.
In this embodiment, a system for extracting a target by human assistance is further provided, as shown in fig. 5, the system includes: video image acquisition module 50, setup module 52, feature extraction module 54, feature matching module 56, shadow elimination module 58, wherein:
and a video image acquisition module 50 connected to the setup module 52 and the feature extraction module 54 for acquiring video image data. General devices include IPC (internet protocol camera), DVS (network video server), DVR (hard disk video recorder);
a setting module 52, connected to the feature matching module 56, for obtaining the target direction and the shadow direction (which may be obtained by manual setting), and calculating an included angle range between the target direction and the shadow direction to limit a rotation range of the target feature;
the feature extraction module 54 is connected to the feature matching module 56, and after the target contour is drawn, the target corner points in the area are calculated by using a corner point detection algorithm to form target features, and the target features are recorded into a feature library;
the feature matching module 56 is connected to the shadow elimination module 58, selects a frame of image acquired by the video image acquisition module 50, obtains a gray-scale image after preprocessing, and then extracts corner points on the gray-scale image by using the corner point detection module; for the target features in the feature library, according to the angle range calculated by the setting module 52, after rotating the angle of the target features, matching the target features with the corner features on the gray-scale image, wherein the successfully matched region is the shadow region;
the shadow elimination module 58 directly filters the object search within the region detected by the feature matching module 56.
For the above design system, the present invention also specifically describes the principle of setting the target direction and the shadow direction, as shown in fig. 6:
setting a target direction and setting the vertical direction of the target on the ground;
setting a shadow direction, setting a strong light source such as the shadow direction under the irradiation of sunlight, and selecting the shadow direction cast by a target at morning, noon and evening time points;
and calculating the range of an included angle formed by the target direction and the shadow direction, wherein the included angle formed by the target direction and the shadow direction can be limited within a range and is used for controlling the rotation angle of the target angular point characteristic.
FIG. 7 is a schematic diagram of a target contour according to an embodiment of the present invention, where the dashed curve in FIG. 7 is a manual-assisted description target contour line;
and then extracting the characteristics of the target corner through a corner detection algorithm. The corner point is an important feature of the image, and is generally a crossing of two lines, or may be a point located on two adjacent objects with different main directions, such as a black point shown in fig. 8, which is an extracted target corner point. The use of line segments connecting the corners is for easy understanding of the reading, and line segments are not used for corner feature matching.
As shown in fig. 9, according to the set angular range of the target direction and the shadow direction, rotating the target corner feature within the angular range, and the rotated corner feature for matching the corner (black dot in fig. 9) in the video frame image;
fig. 10 is a schematic diagram of extracting corner features in a current image according to an embodiment of the present invention. As shown in fig. 10, a gray image is obtained by preprocessing a frame of video image acquired from a video capture device, and then a corner point in the image is extracted by using a corner point detection method. The rotated corner features of fig. 9 are then used to match the extracted corner features on fig. 10 (black dots in fig. 10). In the matching process, in order to improve the accuracy, angular point offset or loss within a certain range can be tolerated. The successful matching is the shadow cast by the target under the light source.
By using the detection scheme in the embodiment, the target shadow is detected, the effect is obvious, the performance requirement is low, and the real-time video analysis processing can be met.
In conclusion, the detection method in the embodiment of the invention is adopted to eliminate the shadow, and the effect is obviously better than that of other algorithms. The method can accurately extract the actual target and avoid the influence of the shadow on the target identification and tracking. Meanwhile, the scheme is simple to realize, the performance is excellent, and the method can be well applied to the fields of video monitoring and the like
In another embodiment, a software is provided, which is used to execute the technical solutions described in the above embodiments and preferred embodiments.
In another embodiment, a storage medium is provided, in which the software is stored, and the storage medium includes but is not limited to: optical disks, floppy disks, hard disks, erasable memory, etc.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented in a general purpose computing system, centralized on a single computing system or distributed across a network of computing systems, or alternatively implemented in program code that is executable by a computing system, such that the steps shown and described may be executed by a computing system on storage systems, and in some cases, performed in an order other than that shown and described herein, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from a plurality of modules or steps. Thus, 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.
Claims (10)
1. A method for detecting shadows in a video image, comprising:
acquiring target characteristics of a monitored target in a current frame image;
rotating each acquired target feature within a preset rotation range;
matching each target feature obtained by rotation with the current frame image after preprocessing, wherein the preset rotation range is the variation range of the shadow generated by the monitored target in the current frame image within the variation range of the light source position;
and determining the area where the target features matched with the current frame image are located as the shadow area of the monitored target.
2. The method according to claim 1, wherein the preset rotation range is obtained by:
taking the vertical direction of the monitored target on the ground as a target direction; and in the light source position variation range, acquiring the shadow direction forming a maximum included angle and a minimum included angle with the target direction in the current frame image, and taking the angle range of the maximum included angle and the minimum included angle as the preset rotation range.
3. The method of claim 1, wherein before obtaining the target feature of the monitored target in the current frame image, the method comprises:
acquiring the contour of a monitored target;
and acquiring corner features of the monitored target in the contour range, wherein the corner features are used for describing the target features.
4. The method of claim 3,
the target features are corner features of the current frame image, and each target feature obtained by rotation is matched with the current frame image after preprocessing, and the method comprises the following steps: matching the corner feature of the current frame image with the acquired corner feature in the contour range;
determining the region where the target feature matched with the current frame image is located as the shadow region of the monitored target, including: and determining the corner features of the current frame image successfully matched as the corner features of the shadow, wherein the region where the corner features of the shadow are located is a shadow region.
5. The method according to any one of claims 1 to 4, wherein determining the region where the target feature matched with the current frame image is located as the shadow region of the monitored target comprises:
and filtering the shadow area in the current frame image.
6. An apparatus for detecting shadows in a video image, comprising:
the acquisition module is used for acquiring the target characteristics of the monitored target in the current frame image;
the rotating module is used for rotating each acquired target feature within a preset rotating range;
the matching module is used for matching each target feature obtained by rotation with the current frame image after preprocessing, wherein the preset rotation range is the variation range of the shadow generated by the monitored target in the current frame image within the variation range of the light source position;
and the determining module is used for determining the area where the target feature matched with the current frame image is located as the shadow area of the monitored target.
7. The device according to claim 6, wherein the preset rotation range is obtained by:
taking the vertical direction of the monitored target on the ground as a target direction; and in the light source position variation range, acquiring the shadow direction forming a maximum included angle and a minimum included angle with the target direction in the current frame image, and taking the angle range of the maximum included angle and the minimum included angle as the preset rotation range.
8. The apparatus of claim 6,
the acquisition module is also used for acquiring the contour of the monitored target; and acquiring corner features of the monitored target in the contour range, wherein the corner features are used for describing the target features.
9. The apparatus of claim 8,
the matching module is further used for matching the corner features of the current frame image with the acquired corner features in the contour range under the condition that the target features are the corner features of the current frame image;
the determining module is further configured to determine the corner features of the successfully matched current frame image as the corner features of a shadow, where an area where the corner features of the shadow are located is a shadow area.
10. The apparatus of any one of claims 6 to 9, further comprising:
and the filtering module is used for filtering the shadow area in the current frame image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210181089.7A CN103455998B (en) | 2012-06-04 | 2012-06-04 | The detection method and device of shade in video image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210181089.7A CN103455998B (en) | 2012-06-04 | 2012-06-04 | The detection method and device of shade in video image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103455998A true CN103455998A (en) | 2013-12-18 |
| CN103455998B CN103455998B (en) | 2017-12-22 |
Family
ID=49738328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210181089.7A Active CN103455998B (en) | 2012-06-04 | 2012-06-04 | The detection method and device of shade in video image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103455998B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309838A (en) * | 2019-07-08 | 2019-10-08 | 上海天诚比集科技有限公司 | Video detection area contour of object based on exponential transform detects preprocess method |
| CN110619652A (en) * | 2019-08-19 | 2019-12-27 | 浙江大学 | Image registration ghost elimination method based on optical flow mapping repeated area detection |
| CN111915642A (en) * | 2020-09-14 | 2020-11-10 | 北京百度网讯科技有限公司 | Image sample generation method, device, equipment and readable storage medium |
| CN112437216A (en) * | 2020-11-13 | 2021-03-02 | 珠海大横琴科技发展有限公司 | Image optimization method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6349113B1 (en) * | 1997-11-03 | 2002-02-19 | At&T Corp. | Method for detecting moving cast shadows object segmentation |
| CN101393651A (en) * | 2008-11-07 | 2009-03-25 | 北京航空航天大学 | View field driving real-time shadow method |
| US8294794B2 (en) * | 2010-07-06 | 2012-10-23 | GM Global Technology Operations LLC | Shadow removal in an image captured by a vehicle-based camera for clear path detection |
-
2012
- 2012-06-04 CN CN201210181089.7A patent/CN103455998B/en active Active
Non-Patent Citations (4)
| Title |
|---|
| A USER INTERFACE FOR INTERACTIVE CINEMATIC SHADOW DESIGN: "Fabio Pellacini等", 《PROCEEDINGS OF THE 29TH ANNUAL CONFERENCE ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES》 * |
| SON-CHEOL YU等: "Development of High-Resolution Acoustic Camera based Real-Time Object Recognition System By using Autonomous Underwater Vehicles", 《OCEANS 2006》 * |
| 付萍等: "视频监控系统中运动目标检测的阴影去除方法", 《计算机工程》 * |
| 林坤杰等: "基于边缘信息及光照方向的阴影检测算法", 《计算机工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309838A (en) * | 2019-07-08 | 2019-10-08 | 上海天诚比集科技有限公司 | Video detection area contour of object based on exponential transform detects preprocess method |
| CN110309838B (en) * | 2019-07-08 | 2023-05-16 | 上海天诚比集科技有限公司 | Object contour detection preprocessing method for video detection area based on exponential transformation |
| CN110619652A (en) * | 2019-08-19 | 2019-12-27 | 浙江大学 | Image registration ghost elimination method based on optical flow mapping repeated area detection |
| CN111915642A (en) * | 2020-09-14 | 2020-11-10 | 北京百度网讯科技有限公司 | Image sample generation method, device, equipment and readable storage medium |
| CN111915642B (en) * | 2020-09-14 | 2024-05-14 | 北京百度网讯科技有限公司 | Image sample generation method, device, equipment and readable storage medium |
| CN112437216A (en) * | 2020-11-13 | 2021-03-02 | 珠海大横琴科技发展有限公司 | Image optimization method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103455998B (en) | 2017-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070570B (en) | Obstacle detection system and method based on depth information | |
| JP6336117B2 (en) | Building height calculation method, apparatus and storage medium | |
| CN108596169B (en) | Block signal conversion and target detection method and device based on video stream image | |
| CN106682620A (en) | Human face image acquisition method and device | |
| CN108038415B (en) | Unmanned aerial vehicle automatic detection and tracking method based on machine vision | |
| CN105611244A (en) | Method for detecting airport foreign object debris based on monitoring video of dome camera | |
| CN106056594A (en) | Double-spectrum-based visible light image extraction system and method | |
| CN110991452B (en) | Parking space frame detection method, device, equipment and readable storage medium | |
| CN105022999A (en) | Man code company real-time acquisition system | |
| CN114973028B (en) | Aerial video image real-time change detection method and system | |
| CN111383204A (en) | Video image fusion method, fusion device, panoramic monitoring system and storage medium | |
| CN103455998B (en) | The detection method and device of shade in video image | |
| CN107862713A (en) | Video camera deflection for poll meeting-place detects method for early warning and module in real time | |
| CN112183431A (en) | Real-time pedestrian number statistical method and device, camera and server | |
| CN113689365B (en) | Target tracking and positioning method based on Azure Kinect | |
| CN108961155B (en) | High-fidelity fisheye lens distortion correction method | |
| CN113643206A (en) | Cow breathing condition detection method | |
| CN110322508B (en) | Auxiliary positioning method based on computer vision | |
| CN116503567A (en) | Intelligent modeling management system based on AI big data | |
| CN110020572B (en) | People counting method, device and equipment based on video image and storage medium | |
| CN116030430A (en) | Rail identification method, device, equipment and storage medium | |
| CN113033551B (en) | Method, device, equipment and storage medium for detecting object | |
| CN113033355B (en) | Abnormal target identification method and device based on intensive power transmission channel | |
| CN111368608B (en) | Face recognition method, device and system | |
| CN103259964B (en) | The picture signal filtering method of video dynamic target capture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |