CN105469403A - Freight train door and window opening detection method - Google Patents
Freight train door and window opening detection method Download PDFInfo
- Publication number
- CN105469403A CN105469403A CN201510831339.0A CN201510831339A CN105469403A CN 105469403 A CN105469403 A CN 105469403A CN 201510831339 A CN201510831339 A CN 201510831339A CN 105469403 A CN105469403 A CN 105469403A
- Authority
- CN
- China
- Prior art keywords
- car body
- hot spot
- detection method
- doors
- measured
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30236—Traffic on road, railway or crossing
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention relates to a freight train door and window opening detection method. The freight train door and window opening detection method includes the following steps that: a direct-emission light source is adopted to irradiate the compartment of a driving train, so that a light spot can be formed on the surface of a train body; an imaging device is adopted to photograph the light spot and the surface of the train body around the light spot, so that a compartment image can be formed; a brightness threshold value is set, binarization segmentation is performed on the generated image, so that a complete light spot sample of a closed train body and the binarization-segmented image of a train body to be detected can be obtained; the complete light spot sample is compared with the binarization-segmented image of the train body to be detected; and if the defect of the binarization-segmented image of the train body to be detected is large, a train door and window is in an open state, and warning is performed. According to the freight train door and window opening detection method of the invention, the opening state of the door of the driving train can be known fast in real time, and the accuracy rate of door and window opening detection can be improved, and railway transportation accidents can be prevented, and railway freight transportation cost can be reduced.
Description
Technical field
The present invention relates to the technical field of railroad train monitoring, is a kind of detection method of goods train opening of doors and windows specifically.
Background technology
In organization of rail transport, goods train door and window unnormal unlocking is a kind of breakneck abnormal conditions, usually adopts the method investigation dangerous situation of artificial visually examine.And undetected situation easily appears in visual inspection opening of doors and windows, the process such as follow-up warning, record, notice needs manual operation, and automaticity is low, and flow process is comparatively complicated, becomes the bottleneck of Information-based Railway development, constrains railway operation management development.Therefore to the Aulomatizeted Detect of railway freight train opening of doors and windows, just seem rather important.
At present, be still in the starting stage to the Aulomatizeted Detect of railway freight train opening of doors and windows.The technical scheme negligible amounts of association area, the technology of employing is comparatively complicated, and error rate is higher, and the more difficult manual detection that departs from completely is run.How to improve detection accuracy, realize reliable fully-automated synthesis, remain a difficult problem.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of detection method of goods train opening of doors and windows.
The technical scheme that the present invention takes for the technical matters existed in solution known technology is:
The detection method of goods train opening of doors and windows of the present invention, comprises the following steps:
Step 1: the railway car in advancing with direct projection light source irradiation, forms hot spot at car body surface;
Step 2: with the car body surface near imaging device shooting hot spot and hot spot, generate compartment image;
Step 3: setting luminance threshold, carries out binarization segmentation to synthetic image;
Step 4: the binarization segmentation image preserving closed car body, as complete hot spot sample, completes initialization;
Step 5: treat measuring car body weight multiple step 1, step 2, step 3, obtain the binarization segmentation image of car body to be measured;
Step 6: the binarization segmentation image of comparison car body to be measured and complete hot spot sample, as defect is comparatively large, then thinks that car body to be measured has open hole in defect;
Step 7: if car body hole detected, be then judged as that there is car door car window opens situation, output alarm signal prompting staff process;
Step 8: return step 5 and proceed to detect.
The present invention can also adopt following technical measures:
In step 1, the light that direct projection light source is launched is at least one in visible ray, infrared light, ultraviolet light, X-ray, laser, polarized light.
In step 1, direction of illumination or the normal direction of direct projection light source are vertical with car body surface.
The scope of hot spot in step 1, its upper edge height higher than the upper edge in region to be detected lower than the lower edge in region to be detected.
In step 1, the pattern of hot spot is two dimension or one-dimensional patterns.
Imaging device described in step 2, is the photoelectricity collecting device matched with light source, comprises video camera, camera, thermal infrared imager, light sensor.
Imaging device described in step 2, its camera lens optical axis and plane-parallel are acute angle with car body surface normal angle.
In step 3, luminance threshold sets manually or algorithm self-adaptation.
The binarization segmentation image of car body to be measured described in step 6 and the comparison of complete hot spot sample, be specially at least one in following graphic processing method:
(1) comparing to complete hot spot sample and foreground pixel quantity in the binarization segmentation image of car body to be measured;
(2) comparing to complete hot spot sample and foreground pixel shape in the binarization segmentation image of car body to be measured;
(3) comparing to complete hot spot sample and foreground pixel color in the binarization segmentation image of car body to be measured or brightness;
(4) comparing to complete hot spot sample and foreground pixel marginal information in the binarization segmentation image of car body to be measured;
(5) comparing to complete hot spot sample and foreground pixel frequency domain information in the binarization segmentation image of car body to be measured.
The advantage that the present invention has and good effect are:
In the detection method of goods train opening of doors and windows of the present invention, railway car in advancing with direct projection light source irradiation step by step, hot spot is formed at car body surface, with the car body surface near imaging device shooting hot spot and hot spot, generate compartment image, setting luminance threshold, binarization segmentation is carried out to synthetic image, thus obtain the closed complete hot spot sample of car body and the binarization segmentation image of car body to be measured, the binarization segmentation pattern of complete hot spot sample and car body to be measured is compared, is in opening as defect is then considered as train door and window comparatively greatly and reports to the police.The car door opening situation of train in operation can be known by the present invention real-time, improve the accuracy that opening of doors and windows detects, prevent the generation of transportation by railroad accident, and reduce railway freight cost.
Accompanying drawing explanation
Fig. 1 utilizes the detection schematic diagram of the detection method of goods train opening of doors and windows of the present invention when car body is closed;
Fig. 2 utilizes the detection schematic diagram of the detection method of goods train opening of doors and windows of the present invention when opening of doors and windows;
Fig. 3 is the hot spot schematic diagram utilizing the detection method of goods train opening of doors and windows of the present invention to be formed when car body is closed;
Fig. 4 is the hot spot schematic diagram utilizing the detection method of goods train opening of doors and windows of the present invention to be formed when opening of doors and windows.
Embodiment
The technical scheme that the present invention takes for the technical matters existed in solution known technology is:
The detection method of goods train opening of doors and windows of the present invention, comprises the following steps:
Step 1: the railway car in advancing with direct projection light source irradiation, forms hot spot at car body surface;
Step 2: with the car body surface near imaging device shooting hot spot and hot spot, generate compartment image;
Step 3: setting luminance threshold, carries out binarization segmentation to synthetic image;
Step 4: the binarization segmentation image preserving closed car body, as complete hot spot sample, completes initialization;
Step 5: treat measuring car body weight multiple step 1, step 2, step 3, obtain the binarization segmentation image of car body to be measured;
Step 6: the binarization segmentation image of comparison car body to be measured and complete hot spot sample, as defect is comparatively large, then thinks that car body to be measured has open hole in defect;
Step 7: if car body hole detected, be then judged as that there is car door car window opens situation, output alarm signal prompting staff process;
Step 8: return step 5 and proceed to detect.
The present invention can also adopt following technical measures:
In step 1, the light that direct projection light source is launched is at least one in visible ray, infrared light, ultraviolet light, X-ray, laser, polarized light.
In step 1, direction of illumination or the normal direction of direct projection light source are vertical with car body surface.
The scope of hot spot in step 1, its upper edge height higher than the upper edge in region to be detected lower than the lower edge in region to be detected.
In step 1, the pattern of hot spot is two dimension or one-dimensional patterns.
Imaging device described in step 2, is the photoelectricity collecting device matched with light source, comprises video camera, camera, thermal infrared imager, light sensor.
Imaging device described in step 2, its camera lens optical axis and plane-parallel are acute angle with car body surface normal angle.
In step 3, luminance threshold sets manually or algorithm self-adaptation.
The binarization segmentation image of car body to be measured described in step 6 and the comparison of complete hot spot sample, be specially at least one in following graphic processing method:
(1) comparing to complete hot spot sample and foreground pixel quantity in the binarization segmentation image of car body to be measured;
(2) comparing to complete hot spot sample and foreground pixel shape in the binarization segmentation image of car body to be measured;
(3) comparing to complete hot spot sample and foreground pixel color in the binarization segmentation image of car body to be measured or brightness;
(4) comparing to complete hot spot sample and foreground pixel marginal information in the binarization segmentation image of car body to be measured;
(5) comparing to complete hot spot sample and foreground pixel frequency domain information in the binarization segmentation image of car body to be measured.
Referring to drawings and Examples, the present invention will be described in detail.
Embodiment 1:
As shown in figures 1 and 3, the detection method of goods train opening of doors and windows of the present invention, comprises the following steps:
Step 1: direct projection light source launches visible ray, and vertical irradiation car body, car body is formed a vertical bands shaped laser spot, and in figure, vertical light stripes is divided into spot area, and range of exposures is at the bottom of roof to car, and spot width is 20 centimetres;
Step 2: adopt general visible video camera as imaging device, camera lens optical axis and plane-parallel, and acutangulate with car body surface normal, the car body surface near shooting hot spot;
Step 3: use adaptive algorithm setting luminance threshold, the pixel higher than luminance threshold in car body surface image is set to 1, and the pixel being equal to or less than threshold value is set to 0;
Step 4: using the binary image of acquisition in step 3 as complete hot spot Sample preservation, complete initialization step;
Step 5: repeat step 1, step 2, step 3, obtain the binarization segmentation image of car body to be measured;
Step 6: the comprehensive comparison method adopting shape and area, the binarization segmentation image of complete hot spot sample and car body to be measured is carried out inter-frame difference, and add up the quantity of its variant pixel, in this example, difference is minimum, can judge that the complete nothing of car body opens wide situation;
Step 7: according to the judged result of step 6, without the need to sending warning, so far completes one-time detection;
Step 8: return step 5 and proceed subsequent detection.
Embodiment 2:
As shown in Figure 1, Figure 2, Figure 3 and Figure 4, the detection method of goods train opening of doors and windows of the present invention, comprises the following steps:
Step 1: direct projection light source launches visible ray, and vertical irradiation car body, car body is formed a vertical bands shaped laser spot, and range of exposures is at the bottom of roof to car, and spot width is 20 centimetres;
Step 2: adopt general visible video camera as imaging device, camera lens optical axis and plane-parallel, and acutangulate with car body surface normal, the car body surface near shooting hot spot;
Step 3: use adaptive algorithm setting luminance threshold, the pixel higher than luminance threshold in car body surface image is set to 1, and the pixel being equal to or less than threshold value is set to 0;
Step 4: using the binary image of acquisition in step 3 as complete hot spot Sample preservation, complete initialization step;
Step 5: repeat step 1, step 2, step 3, obtain the binarization segmentation image of car body to be measured, in figure, vertical light stripes is divided into spot area, and black rectangle is the vehicle window opened;
Step 6: the comprehensive comparison method adopting shape and area, the binarization segmentation image of complete hot spot sample and car body to be detected is carried out inter-frame difference, add up the quantity of its variant pixel, differ greatly in this example, large area difference pixel is formed at vehicle window correspondence position, can judge that car body has open hole in this position accordingly, and can judge as vehicle window is opened by hole location;
Step 7: according to the judged result of step 6, send warning, notifies that other equipment or staff carry out subsequent treatment, so far completes one-time detection;
Step 8: return step 5 and proceed subsequent detection.
The above, it is only preferred embodiment of the present invention, not any pro forma restriction is done to the present invention, although the present invention with preferred embodiment openly as above, but, and be not used to limit the present invention, any those skilled in the art, do not departing within the scope of technical solution of the present invention, certainly the technology contents of announcement can be utilized to make a little change or modification, become the Equivalent embodiments of equivalent variations, in every case be the content not departing from technical solution of the present invention, according to any simple modification that technical spirit of the present invention is done above embodiment, equivalent variations and modification, all belong in the scope of technical solution of the present invention.
Claims (9)
1. a detection method for goods train opening of doors and windows, comprises the following steps:
Step 1: the railway car in advancing with direct projection light source irradiation, forms hot spot at car body surface;
Step 2: with the car body surface near imaging device shooting hot spot and hot spot, generate compartment image;
Step 3: setting luminance threshold, carries out binarization segmentation to synthetic image;
Step 4: the binarization segmentation image preserving closed car body, as complete hot spot sample, completes initialization;
Step 5: treat measuring car body weight multiple step 1, step 2, step 3, obtain the binarization segmentation image of car body to be measured;
Step 6: the binarization segmentation image of comparison car body to be measured and complete hot spot sample, as defect is comparatively large, then thinks that car body to be measured has open hole in defect;
Step 7: if car body hole detected, be then judged as that there is car door car window opens situation, output alarm signal prompting staff process;
Step 8: return step 5 and proceed to detect.
2. the detection method of goods train opening of doors and windows according to claim 1, is characterized in that: in step 1, and the light that direct projection light source is launched is at least one in visible ray, infrared light, ultraviolet light, X-ray, laser, polarized light.
3. the detection method of goods train opening of doors and windows according to claim 1 and 2, is characterized in that: in step 1, and direction of illumination or the normal direction of direct projection light source are vertical with car body surface.
4. the detection method of goods train opening of doors and windows according to claim 3, is characterized in that: the scope of hot spot in step 1, its upper edge height higher than the upper edge in region to be detected lower than the lower edge in region to be detected.
5. the detection method of goods train opening of doors and windows according to claim 4, is characterized in that: in step 1, the pattern of hot spot is two dimension or one-dimensional patterns.
6. the detection method of goods train opening of doors and windows according to claim 1 or 5, is characterized in that: imaging device described in step 2, is the photoelectricity collecting device matched with light source, comprises video camera, camera, thermal infrared imager, light sensor.
7. the detection method of goods train opening of doors and windows according to claim 6, is characterized in that: imaging device described in step 2, its camera lens optical axis and plane-parallel, is acute angle with car body surface normal angle.
8. the detection method of the goods train opening of doors and windows according to claim 1 or 7, is characterized in that: in step 3, luminance threshold sets manually or algorithm self-adaptation.
9. the detection method of the goods train opening of doors and windows according to any one of claim 1,2,4,5,7, it is characterized in that: the binarization segmentation image of car body to be measured described in step 6 and the comparison of complete hot spot sample, be specially at least one in following graphic processing method:
(1) comparing to complete hot spot sample and foreground pixel quantity in the binarization segmentation image of car body to be measured;
(2) comparing to complete hot spot sample and foreground pixel shape in the binarization segmentation image of car body to be measured;
(3) comparing to complete hot spot sample and foreground pixel color in the binarization segmentation image of car body to be measured or brightness;
(4) comparing to complete hot spot sample and foreground pixel marginal information in the binarization segmentation image of car body to be measured;
(5) comparing to complete hot spot sample and foreground pixel frequency domain information in the binarization segmentation image of car body to be measured.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510831339.0A CN105469403A (en) | 2015-11-25 | 2015-11-25 | Freight train door and window opening detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510831339.0A CN105469403A (en) | 2015-11-25 | 2015-11-25 | Freight train door and window opening detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105469403A true CN105469403A (en) | 2016-04-06 |
Family
ID=55607062
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510831339.0A Pending CN105469403A (en) | 2015-11-25 | 2015-11-25 | Freight train door and window opening detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105469403A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108961704A (en) * | 2018-07-03 | 2018-12-07 | 盯盯拍(深圳)技术股份有限公司 | It reminds vehicle window method for closing and vehicle window is reminded to close device |
CN109239734A (en) * | 2018-08-24 | 2019-01-18 | 河南东网信息技术有限公司 | A kind of Along Railway environmental safety monitor and control early warning system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050074142A1 (en) * | 2001-07-10 | 2005-04-07 | Ludwig Ertl | Method and device for optically detecting the open state of a vehicle door |
CN201016002Y (en) * | 2006-12-26 | 2008-02-06 | 曹亮 | Structural light recognizing railway vehicle fittings application state test apparatus |
CN102221553A (en) * | 2011-03-25 | 2011-10-19 | 上海交通大学 | Structured light-based high-speed detection system and method for railway fastener |
US20120154477A1 (en) * | 2010-12-21 | 2012-06-21 | Yoshirou Yamazaki | Defective recording element detecting apparatus, defective recording element detecting method, and image forming apparatus |
CN103047943A (en) * | 2012-12-31 | 2013-04-17 | 吉林大学 | Method for detecting vehicle door outer plate shape and size based on single-projection encoding structured light |
CN104359921A (en) * | 2014-11-20 | 2015-02-18 | 中南大学 | Method and device for detecting fastener loss based on structured light |
-
2015
- 2015-11-25 CN CN201510831339.0A patent/CN105469403A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050074142A1 (en) * | 2001-07-10 | 2005-04-07 | Ludwig Ertl | Method and device for optically detecting the open state of a vehicle door |
CN201016002Y (en) * | 2006-12-26 | 2008-02-06 | 曹亮 | Structural light recognizing railway vehicle fittings application state test apparatus |
US20120154477A1 (en) * | 2010-12-21 | 2012-06-21 | Yoshirou Yamazaki | Defective recording element detecting apparatus, defective recording element detecting method, and image forming apparatus |
CN102221553A (en) * | 2011-03-25 | 2011-10-19 | 上海交通大学 | Structured light-based high-speed detection system and method for railway fastener |
CN103047943A (en) * | 2012-12-31 | 2013-04-17 | 吉林大学 | Method for detecting vehicle door outer plate shape and size based on single-projection encoding structured light |
CN104359921A (en) * | 2014-11-20 | 2015-02-18 | 中南大学 | Method and device for detecting fastener loss based on structured light |
Non-Patent Citations (1)
Title |
---|
严柏军等: ""基于数学形态学的货车车门状态的检测"", 《计算机工程》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108961704A (en) * | 2018-07-03 | 2018-12-07 | 盯盯拍(深圳)技术股份有限公司 | It reminds vehicle window method for closing and vehicle window is reminded to close device |
CN109239734A (en) * | 2018-08-24 | 2019-01-18 | 河南东网信息技术有限公司 | A kind of Along Railway environmental safety monitor and control early warning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10204268B2 (en) | Method and system for identifying train number and train type, and method and system for security inspection | |
US8335606B2 (en) | Thermal imaging-based vehicle analysis | |
US9945652B2 (en) | Brake component monitoring | |
US9050984B2 (en) | Anomalous railway component detection | |
US20200055531A1 (en) | Broken Wheel Detection System | |
US9330339B2 (en) | System and method for detecting cargo container seals | |
US20170161586A1 (en) | Train type identification method and system, and security inspection method and system | |
JP4269316B2 (en) | Label inspection equipment | |
US20110164789A1 (en) | Detection of vehicles in images of a night time scene | |
CN105447854A (en) | Small-size glass panel surface defect detection method and small-size glass panel surface defect detection system | |
US20210088454A1 (en) | Inspection device with colour lighting | |
JP2015519554A5 (en) | ||
CN103839255A (en) | Method and device for detecting video image matting tampering | |
CN105469403A (en) | Freight train door and window opening detection method | |
CN107967445A (en) | A kind of car installs the intelligent checking system and method for skylight additional | |
JP2024041829A (en) | System and method for identifying potential defect in railway environmental object | |
US10134123B2 (en) | Methods, systems, and apparatuses for inspecting goods | |
CN108805145A (en) | A kind of subway work railcar signal lamp and ambient brightness detecting device | |
CN112001908B (en) | Railway freight car sleeper beam hole carried foreign matter detection method | |
CN113673614A (en) | Machine vision-based subway tunnel foreign matter intrusion detection device and method | |
JP6015296B2 (en) | Image processing apparatus, ambient environment estimation method, and ambient environment estimation program | |
CN105301016A (en) | Image detection method for scratches of wheel tread | |
TWI662509B (en) | Development of a disdrometer and particle tracking process thereof | |
Frías-Velázquez et al. | A mathematical morphology-based approach for vehicle detection in road tunnels | |
Sirpotdar | Adaptive thresholding and wagon counting technique for day and night time images |
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: 20160406 |
|
RJ01 | Rejection of invention patent application after publication |