CN103854023A - Camera blocking detection method based on wavelet transformation and time domain pattern recognition - Google Patents
Camera blocking detection method based on wavelet transformation and time domain pattern recognition Download PDFInfo
- Publication number
- CN103854023A CN103854023A CN201210496211.XA CN201210496211A CN103854023A CN 103854023 A CN103854023 A CN 103854023A CN 201210496211 A CN201210496211 A CN 201210496211A CN 103854023 A CN103854023 A CN 103854023A
- Authority
- CN
- China
- Prior art keywords
- candidate region
- wavelet transformation
- edge feature
- camera
- blocked
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a camera blocking detection method based on wavelet transformation and time domain pattern recognition. The method comprises the following steps that: 1) the wavelet transformation of an original image is carried out to get edge features of several groups of different frequencies; 2) the edge features of several groups of different frequencies are weighted and averaged so as to obtain an edge feature map; 3) the edge feature map is divided into a plurality of small areas, and edge features of each small area is counted; 4) small areas which are adjacent to each other and provided with less information are clustered, so as to obtain a blocking candidate region; and 5) time domain feature recognition of the blocking candidate region is carried out, and according to a weighted area of the blocking candidate region and also survival time within a allowable deformation range of the blocking candidate region, whether the blocking candidate region is blocked is judged. Compared with the prior art, the method of the invention has the advantages of being simple and practical, little in calculation, high in recognition rate, low in false alarm rate, and the like.
Description
Technical field
The present invention relates to a kind of application process of vehicle vision system, especially relate to a kind of camera occlusion detection method based on wavelet transformation and Modulation identification.
Background technology
Successfully be applied on vehicle based on vision DAS (Driver Assistant System) (as forward direction collides pre-warning system, lane detection system etc.).All vision systems all need camera that realtime graphic is transferred to image processor.If camera is blocked, system need to give a warning, and notice human pilot avoids human pilot to rely on vision system, produces danger to driving.But the camera occlusion detection function of existing system is badly in need of improving.
Summary of the invention
Object of the present invention is exactly to provide in order to overcome the defect that above-mentioned prior art exists a kind of camera occlusion detection method based on wavelet transformation and Modulation identification that accuracy of detection is high, rate of false alarm is low.
Object of the present invention can be achieved through the following technical solutions:
Based on a camera occlusion detection method for wavelet transformation and Modulation identification, comprise the following steps:
1) original image is carried out to wavelet transformation, obtain the edge feature of many group different frequencies;
2) edge feature of many groups different frequency is weighted on average to synthetic edge feature map;
3) edge feature map is divided into multiple zonules, the edge feature of each zonule is added up;
4) cluster is carried out in zonule adjacent and that marginal information is few, obtain and block candidate region;
5) carry out temporal signatures identification to blocking candidate region, whether be blocked allowing survival time judgement in deformation range to block candidate region according to blocking the weighted area of candidate region and blocking candidate region.
Step 1) in original image is carried out to wavelet transformation three times, obtain respectively the edge feature of three groups of different frequencies.
Step 5) in judge whether to be blocked according to the possibility mark that is blocked, if possibility mark is higher than threshold value, camera is blocked, if possibility mark is lower than threshold value, camera is not blocked, and described possibility mark is to block the weighted area of candidate region and block candidate region at the product that allows the survival time in deformation range.
Compared with prior art, the present invention identifies by wavelet transformation and Modulation the image that camera is obtained and processes, can judge fast whether the camera for obtaining image is blocked, and the method is simple, calculated amount is little, discrimination is high, rate of false alarm is low.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.
Embodiment
As shown in Figure 1, a kind of camera occlusion detection method based on wavelet transformation and Modulation identification, comprises the following steps:
Step 1: original image is carried out to wavelet transformation three times, obtain the edge feature of three groups of different frequencies, every group of edge feature all contains the edge feature of this frequency domain on different directions;
Step 2: the edge feature of three groups of different frequencies is weighted on average, synthetic edge feature map, its weights have embodied this frequency domain to information extraction and have supported antimierophonic ability;
Step 3: edge feature map is divided into multiple zonules, the edge feature of each zonule is added up;
Step 4: cluster is carried out in zonule adjacent and that marginal information is few, obtain and block candidate region;
Step 5; Carry out temporal signatures identification to blocking candidate region, when a candidate region is out of shape not quite, and after continuing for some time, just can judge the situation that camera blocks.The specific standards judging is the possibility mark being blocked, and this possibility mark is to block the weighted area of candidate region and block candidate region at the product that allows the survival time in deformation range.If possibility mark is higher than threshold value, camera is blocked, if possibility mark lower than threshold value, camera is not blocked.
The present invention can provide and detect the simple overall plan that camera is blocked, and has calculated amount little, and discrimination is high, the feature that false alarm rate is low.
Claims (3)
1. the camera occlusion detection method based on wavelet transformation and Modulation identification, is characterized in that, comprises the following steps:
1) original image is carried out to wavelet transformation, obtain the edge feature of many group different frequencies;
2) edge feature of many groups different frequency is weighted on average to synthetic edge feature map;
3) edge feature map is divided into multiple zonules, the edge feature of each zonule is added up;
4) cluster is carried out in zonule adjacent and that marginal information is few, obtain and block candidate region;
5) carry out temporal signatures identification to blocking candidate region, whether be blocked allowing survival time judgement in deformation range to block candidate region according to blocking the weighted area of candidate region and blocking candidate region.
2. a kind of camera occlusion detection method based on the identification of wavelet transformation and Modulation according to claim 1, is characterized in that step 1) in original image is carried out to wavelet transformation three times, obtain respectively the edge feature of three groups of different frequencies.
3. a kind of camera occlusion detection method based on wavelet transformation and Modulation identification according to claim 1, it is characterized in that, step 5) in judge whether to be blocked according to the possibility mark that is blocked, if possibility mark is higher than threshold value, camera is blocked, if possibility mark is lower than threshold value, camera is not blocked, and described possibility mark is to block the weighted area of candidate region and block candidate region at the product that allows the survival time in deformation range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210496211.XA CN103854023A (en) | 2012-11-28 | 2012-11-28 | Camera blocking detection method based on wavelet transformation and time domain pattern recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210496211.XA CN103854023A (en) | 2012-11-28 | 2012-11-28 | Camera blocking detection method based on wavelet transformation and time domain pattern recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103854023A true CN103854023A (en) | 2014-06-11 |
Family
ID=50861656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210496211.XA Pending CN103854023A (en) | 2012-11-28 | 2012-11-28 | Camera blocking detection method based on wavelet transformation and time domain pattern recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103854023A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108304862A (en) * | 2018-01-08 | 2018-07-20 | 武汉大学 | A kind of map building polygon mode identification method based on wavelet transformation |
| CN110647858A (en) * | 2019-09-29 | 2020-01-03 | 上海依图网络科技有限公司 | Video occlusion judgment method and device and computer storage medium |
| US10769454B2 (en) | 2017-11-07 | 2020-09-08 | Nvidia Corporation | Camera blockage detection for autonomous driving systems |
| CN111815556A (en) * | 2020-05-28 | 2020-10-23 | 北京易航远智科技有限公司 | Vehicle-mounted fisheye camera self-diagnosis method based on texture extraction and wavelet transformation |
| CN111860120A (en) * | 2020-06-03 | 2020-10-30 | 江西江铃集团新能源汽车有限公司 | Automatic shielding detection method and device for vehicle-mounted camera |
| CN112242045A (en) * | 2020-12-18 | 2021-01-19 | 宁波视控汽车电子有限公司 | Fault alarm method and device |
| US11961308B2 (en) | 2017-11-07 | 2024-04-16 | Nvidia Corporation | Camera blockage detection for autonomous driving systems |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080095399A1 (en) * | 2006-10-23 | 2008-04-24 | Samsung Electronics Co., Ltd. | Device and method for detecting occlusion area |
| CN102098531A (en) * | 2010-12-16 | 2011-06-15 | 东软集团股份有限公司 | Method and device for detecting interference of video camera |
| CN102176244A (en) * | 2011-02-17 | 2011-09-07 | 东方网力科技股份有限公司 | Method and device for determining shielding condition of camera head |
| CN102436638A (en) * | 2010-08-24 | 2012-05-02 | 奥林巴斯株式会社 | Image processing apparatus, image processing method, and computer-readable recording medium |
-
2012
- 2012-11-28 CN CN201210496211.XA patent/CN103854023A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080095399A1 (en) * | 2006-10-23 | 2008-04-24 | Samsung Electronics Co., Ltd. | Device and method for detecting occlusion area |
| CN102436638A (en) * | 2010-08-24 | 2012-05-02 | 奥林巴斯株式会社 | Image processing apparatus, image processing method, and computer-readable recording medium |
| CN102098531A (en) * | 2010-12-16 | 2011-06-15 | 东软集团股份有限公司 | Method and device for detecting interference of video camera |
| CN102176244A (en) * | 2011-02-17 | 2011-09-07 | 东方网力科技股份有限公司 | Method and device for determining shielding condition of camera head |
Non-Patent Citations (2)
| Title |
|---|
| YUANKAI WANG ET AL: "Real-time camera anomaly detection for real-world video surveillance", 《PROCEEDINGS OF THE 2011 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS》 * |
| 姬贯新等: "一种改进的摄像机干扰检测方法", 《信息工程大学学报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10769454B2 (en) | 2017-11-07 | 2020-09-08 | Nvidia Corporation | Camera blockage detection for autonomous driving systems |
| US11574481B2 (en) | 2017-11-07 | 2023-02-07 | Nvidia Corporation | Camera blockage detection for autonomous driving systems |
| US11961308B2 (en) | 2017-11-07 | 2024-04-16 | Nvidia Corporation | Camera blockage detection for autonomous driving systems |
| CN108304862A (en) * | 2018-01-08 | 2018-07-20 | 武汉大学 | A kind of map building polygon mode identification method based on wavelet transformation |
| CN110647858A (en) * | 2019-09-29 | 2020-01-03 | 上海依图网络科技有限公司 | Video occlusion judgment method and device and computer storage medium |
| CN111815556A (en) * | 2020-05-28 | 2020-10-23 | 北京易航远智科技有限公司 | Vehicle-mounted fisheye camera self-diagnosis method based on texture extraction and wavelet transformation |
| CN111815556B (en) * | 2020-05-28 | 2024-01-16 | 北京易航远智科技有限公司 | Vehicle-mounted fisheye camera self-diagnosis method based on texture extraction and wavelet transformation |
| CN111860120A (en) * | 2020-06-03 | 2020-10-30 | 江西江铃集团新能源汽车有限公司 | Automatic shielding detection method and device for vehicle-mounted camera |
| CN111860120B (en) * | 2020-06-03 | 2023-11-17 | 江西江铃集团新能源汽车有限公司 | Automatic shielding detection method and device for vehicle-mounted camera |
| CN112242045A (en) * | 2020-12-18 | 2021-01-19 | 宁波视控汽车电子有限公司 | Fault alarm method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103854023A (en) | Camera blocking detection method based on wavelet transformation and time domain pattern recognition | |
| CN106980113B (en) | Object detection device and object detection method | |
| EP3258214B1 (en) | Object detection device | |
| CN106647776B (en) | Method and device for judging lane changing trend of vehicle and computer storage medium | |
| CN106841196B (en) | Use the wet road surface condition detection of the view-based access control model of tire footprint | |
| US20120300078A1 (en) | Environment recognizing device for vehicle | |
| US10132919B2 (en) | Object detecting device, radar device, and object detection method | |
| CN105426864A (en) | Multiple lane line detecting method based on isometric peripheral point matching | |
| CN110386065B (en) | Vehicle blind area monitoring method and device, computer equipment and storage medium | |
| CN107991671A (en) | A kind of method based on radar data and vision signal fusion recognition risk object | |
| EP2879111A1 (en) | Image processing device | |
| US9530063B2 (en) | Lane-line recognition apparatus including a masking area setter to set a masking area ahead of a vehicle in an image captured by an image capture unit | |
| CN113370977A (en) | Intelligent vehicle forward collision early warning method and system based on vision | |
| JP6020567B2 (en) | Three-dimensional object detection apparatus and three-dimensional object detection method | |
| JP5907700B2 (en) | Image processing apparatus, vehicle system, and image processing method | |
| WO2016002900A1 (en) | Method and device for detecting objects, and computer program product | |
| CN104794856A (en) | Driver's attention comprehensive evaluation system | |
| CN104094311A (en) | Three-dimensional object detection device | |
| KR101687094B1 (en) | Apparatus for recognizing traffic sign and method thereof | |
| KR101998584B1 (en) | Lane detection apparatus and lane detection method | |
| CN104115201A (en) | Three-dimensional object detection device | |
| Skodras et al. | Rear lights vehicle detection for collision avoidance | |
| CN103854293A (en) | Vehicle tracking method and device based on feature point matching | |
| CN104268859A (en) | Image preprocessing method for night lane line detection | |
| Ju et al. | Vision-based moving objects detection for intelligent automobiles and a robustness enhancing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140611 |