CN105528617A - Method for carrying out car model retrieval based on headlight shade shard morphological characteristic - Google Patents
Method for carrying out car model retrieval based on headlight shade shard morphological characteristic Download PDFInfo
- Publication number
- CN105528617A CN105528617A CN201510882328.5A CN201510882328A CN105528617A CN 105528617 A CN105528617 A CN 105528617A CN 201510882328 A CN201510882328 A CN 201510882328A CN 105528617 A CN105528617 A CN 105528617A
- Authority
- CN
- China
- Prior art keywords
- submeter
- angle
- fragment
- standard database
- next step
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24317—Piecewise classification, i.e. whereby each classification requires several discriminant rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention relates to a method for carrying out car model retrieval based on a headlight shade shard morphological characteristic. The method comprises a step of establishing a headlight shade morphological characteristic information standard database, a step of selecting a plurality of headlight shade shards at an accident scene, and judging shard colors, a step of judging shard materials, a step of judging whether the shards are subjected to matting processing, a step of judging whether the shards have characters, a step of measuring the thickness of the shards, a step of judging whether the shards have fixed seat holes, a step of judging whether the shards have stripes, a step of judging whether the front side ridges and the side edges of shards have angles, a step of judging whether the front face and the side faces of the shards have angles, a step of judging whether the shards have side edge angles, a step of comparing the sub list information obtained in each step and the existing sub lists in a standard database, performing the car model automobile retrieval in a car model main list according to the result of comparison, searching all car models which are in accordance with shard characteristic information and listing car models and characteristic information and images, and a step of carrying out comparison again to confirm the result, and outputting a final comparison result. The method can be widely applied to various traffic accidents.
Description
Technical field
The present invention relates to the method for a kind of vehicle retrieval, particularly about a kind of method of carrying out vehicle retrieval based on headlamp lampshade fragment morphological feature used in traffic hazard field.
Background technology
Along with growing with each passing day of vehicle, the frequency of traffic hazard is also in the gesture of rising year by year, in traffic hazard, the headlamp lampshade of vehicle is cracky position, headlamp lampshade comprises a lot of information from objective pattern, as color, material, character, special processing, thickness, holder hole dimension, front fringe spacing, side fringe spacing, lateral edges angle, front streakline angle, front streakline and lateral edges angle, front and side angle, lampshade overall dimensions etc.Now these information do not arrange and use, and be the confirmation of accident and investigate troublemaker's responsibility and do not form help public security deparment and traffic police department.
Summary of the invention
For the problems referred to above, the object of this invention is to provide a kind of method of carrying out vehicle retrieval based on headlamp lampshade fragment morphological feature, it is simple to operate, according to the information from objective pattern of the headlamp lampshade fragment that scene stays, utilize standard database, exclusive segment vehicle and then case-involving vehicle of more effectively, accurately tracing to the source, help public security deparment and traffic police department to reduce investigation scope, find case-involving car amount as early as possible.
For achieving the above object, the present invention takes following technical scheme: a kind of method of carrying out vehicle retrieval based on headlamp lampshade fragment morphological feature, it is characterized in that comprising the following steps: (1) sets up headlamp lampshade information from objective pattern standard database, this database comprises 13 kinds of lists, wherein one is vehicle master meter, other 12 kinds of lists are the color of headlamp lampshade respectively, material, friction treatment submeter, the molecular weight of plastics car light and molecular weight distribution data submeter thereof, character submeter, thickness submeter, fixing bore submeter, front fringe spacing submeter, side fringe spacing and position submeter, front streakline angle submeter, front streakline and lateral edges angle submeter, front and side angle submeter, lateral edges angle submeter, lampshade overall dimensions length and high submeter, by can mutually inquire about between master meter and submeter, (2) choose some, scene of the accident headlamp lampshade fragment, judge fragment color, comprise the type of color, the position of color, and judged result is inputted color, material, the friction treatment submeter in standard database, (3) judge that chip material is plastics or glass, and judged result is inputted color, material, the special processing submeter in standard database, (4) judge whether fragment has frosted process, and judged result is inputted color, material, the special processing submeter in standard database, (5) judge whether fragment has character, if there is character, then character content inputed to the character submeter in standard database, and enter next step, otherwise, directly enter next step, (6) measure chip thickness, and measurement result is inputted the thickness submeter in standard database, judge measurement result whether in tolerance, if in tolerance, then enter next step, otherwise remeasure, (7) judge whether fragment has fixing bore, if not, enter next step, if have, judge it is solid bore or hollow bore, and judged result is inputted the fixing bore submeter in standard database, measure the length of fixing bore and wide, and measurement result is inputted respectively fixing bore submeter, judge whether in tolerance, if in tolerance, then enter next step, otherwise remeasure, (8) judge whether fragment has striped, if not, enter next step, if have, measure maximal value and the minimum value of fringe spacing, and measurement result is inputted respectively the front fringe spacing submeter in standard database, then enter next step, (9) judge on fragment, whether front streakline and lateral edges have angle, if there is angle, then measure maximal value and the minimum value of angle, and front streakline measurement result inputted respectively in standard database and lateral edges angle submeter, then enter next step, otherwise, then directly next step is entered, (10) judge on fragment, whether front and side have angle, if there is angle, then measure maximal value and the minimum value of angle, and front measurement result inputted respectively in standard database and side angle submeter, then enter next step, otherwise, then directly next step is entered, (11) judge whether fragment has lateral edges angle, if having, measure maximal value and the minimum value of angle, and measurement result is inputted respectively the lateral edges angle submeter in standard database, otherwise, then directly next step is entered, (12) the submeter information obtained in above steps is contrasted with existing submeter in standard database respectively, result after contrast is carried out vehicle and is automatically retrieved in vehicle master meter, retrieve all vehicles meeting shred characterization information, and list vehicle and characteristic information thereof and picture, (13) again to compare confirmation result, confirm then to export final comparison result, otherwise, return step (2) and again retrieve.
In described step (1), in vehicle master meter, comprise automobile full figure, headlamp picture, headlamp disassemble after lampshade picture and the decorative pattern schematic diagram in lampshade front.
The present invention is owing to taking above technical scheme, and it has the following advantages: 1, the present invention is according to the information from objective pattern being retained in on-the-spot car headlamp lampshade fragment, the vehicle of the case-involving vehicle that can realize tracing to the source.2, the present invention sets up a kind of database, and this database comprises 13 kinds of lists, and wherein one is master meter, other 12 kinds of submeters.Can be linked to any submeter by master meter, also can be linked to master meter by submeter, master meter is the tie of each submeter.By framework and the method for this database retrieval, the vehicle of the case-involving vehicle that can realize tracing to the source according to headlamp lampshade information from objective pattern.The present invention can extensively apply in various traffic hazard.
Accompanying drawing explanation
Fig. 1 is overall flow schematic diagram of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in detail.
As shown in Figure 1, the invention provides a kind of method of carrying out vehicle retrieval based on headlamp lampshade fragment morphological feature, the method is the headlamp lampshade information from objective pattern standard database by setting up, adopt the on-the-spot left headlamp lampshade fragment of vehicle, carry out one by one examining, inputting in this relational database, then compare, and then realize tracing to the source vehicle vehicle.The present invention is described for the main vehicle of the serial car of masses, and it comprises the following steps:
(1) headlamp lampshade information from objective pattern standard database is set up, this database comprises 13 kinds of lists, wherein one is vehicle master meter, other 12 kinds of lists are the color of headlamp lampshade respectively, material, friction treatment submeter, the molecular weight of plastics car light and molecular weight distribution data submeter thereof, character submeter, thickness submeter, fixing bore submeter, front fringe spacing submeter, side fringe spacing and position submeter, front streakline angle submeter, front streakline and lateral edges angle submeter, front and side angle submeter, lateral edges angle submeter, lampshade overall dimensions length and high submeter, by can mutually inquire about between master meter and submeter.
Wherein comprise automobile full figure in vehicle master meter, headlamp (headlight is integrated) picture, headlamp disassemble after lampshade picture and the decorative pattern schematic diagram in lampshade front.
(2) choose some, scene of the accident headlamp lampshade fragment, such as, choose 7 fragments, respectively called after 1# ~ 7#; Judge fragment color, comprise the type of color, the position of color, and judged result is inputted color, material, the friction treatment submeter in standard database; Such as, in the present embodiment acquired fragment is colourless; The color of existing masses serial automobile headlamp lampshade only has colourless and black two kinds, if there are other colors in the future, can increase respective color data in standard database.
(3) headlamp lampshade has plastic and glass bi-material, judges that chip material is plastics or glass, and judged result is inputted color, material, the special processing submeter in standard database; Such as, in step (2) acquired fragment is plastics.
(4) judge whether fragment has frosted process, and judged result is inputted color, material, the special processing submeter in standard database; Such as, in step (2) acquired fragment has frosted process.
(5) judge whether fragment has character; If there is character, then character content inputed to the character submeter in standard database, and enter next step; Otherwise, directly enter next step; Such as, acquired fragment 1# sheet there is alphabetical Valeo and >PC<, then in standard database, inputs Valeo and >PC<.
(6) measure chip thickness, and measurement result is inputted the thickness submeter in standard database, there is error owing to measuring, judge measurement result whether in tolerance, if in tolerance, then enter next step, otherwise remeasure.Such as, acquired 4# ~ 7# fragment can only measure its thickness characteristics, and thickness characteristics all can be measured at 1# ~ 3# fragment, therefore, chooses 1# ~ 3# fragment and measures.
(7) judge whether fragment has fixing bore, if not, enter next step; If have, judge it is solid bore or hollow bore, and judged result is inputted the fixing bore submeter in standard database, measure the length of fixing bore and wide, and measurement result is inputted respectively fixing bore submeter, judge whether in tolerance; If in tolerance, then enter next step, otherwise remeasure.
(8) judge whether fragment has striped, if not, enter next step; If have, measure maximal value and the minimum value of fringe spacing, and measurement result is inputted respectively the front fringe spacing submeter in standard database, then enter next step; Such as, acquired 1# ~ 3# fragment has front striped, the maximal value of front fringe spacing respectively: 11.6mm, 12.0mm and 12.8mm, the minimum value of front fringe spacing respectively: 10.8mm, 11.8mm and 12.4mm.
(9) judge on fragment, whether front streakline and lateral edges have angle, if there is angle, then measure maximal value and the minimum value of angle, and front streakline measurement result inputted respectively in standard database and lateral edges angle submeter, then enter next step; Otherwise, then directly next step is entered.Such as, acquired fragment 1# ~ 3# fragment front streakline and lateral edges have angle, the maximal value of angle respectively: 51.4,57.8 and 86.3, the minimum value of angle respectively: 50.1,45.6 and 58.6.
(10) judge on fragment, whether front and side have angle, if there is angle, then measure maximal value and the minimum value of angle, and front measurement result inputted respectively in standard database and side angle submeter, then enter next step; Otherwise, then directly next step is entered.Such as, acquired fragment 1# ~ 3# fragment has front and side angle, its maximal value respectively: 83.6,112.8 and 89.6, its minimum value respectively: 82.1,92.7 and 76.4.
(11) judge whether fragment has lateral edges angle, if having, measure maximal value and the minimum value of angle, and measurement result is inputted respectively the lateral edges angle submeter in standard database; Otherwise, then directly next step is entered.Such as, acquired fragment 1# ~ 3# fragment, wherein 1# fragment has lateral edges angle, and its maximal value is 215.7, and minimum value is 215.7.
(12) the submeter information obtained in above steps is contrasted with existing submeter in standard database respectively, result after contrast is carried out vehicle and is automatically retrieved in vehicle master meter, retrieve all vehicles meeting shred characterization information, and list vehicle and characteristic information thereof and picture.Such as, in step (1) acquired fragment 1# ~ 3# fragment, measurement result is as follows: the vehicle that 1# fragment searching goes out has: Magotan (2007 sections); The vehicle that 2# fragment searching goes out has: Magotan (2007 sections), and (2010 sections) are seen on way; The vehicle that 3# fragment searching goes out has: Magotan (2007 sections), CC (2010 sections).
(13) again to compare confirmation result, after confirming, export final comparison result; Otherwise, return step (2) and again retrieve.
The various embodiments described above are only for illustration of the present invention; the structure of each parts, size, setting position and shape all can change to some extent; on the basis of technical solution of the present invention; all improvement of carrying out individual part according to the principle of the invention and equivalents, all should not get rid of outside protection scope of the present invention.
Claims (2)
1. carry out a method for vehicle retrieval based on headlamp lampshade fragment morphological feature, it is characterized in that comprising the following steps:
(1) headlamp lampshade information from objective pattern standard database is set up, this database comprises 13 kinds of lists, wherein one is vehicle master meter, other 12 kinds of lists are the color of headlamp lampshade respectively, material, friction treatment submeter, the molecular weight of plastics car light and molecular weight distribution data submeter thereof, character submeter, thickness submeter, fixing bore submeter, front fringe spacing submeter, side fringe spacing and position submeter, front streakline angle submeter, front streakline and lateral edges angle submeter, front and side angle submeter, lateral edges angle submeter, lampshade overall dimensions length and high submeter, by can mutually inquire about between master meter and submeter,
(2) choose some, scene of the accident headlamp lampshade fragment, judge fragment color, comprise the type of color, the position of color, and judged result is inputted color, material, the friction treatment submeter in standard database;
(3) judge that chip material is plastics or glass, and judged result is inputted color, material, the special processing submeter in standard database;
(4) judge whether fragment has frosted process, and judged result is inputted color, material, the special processing submeter in standard database;
(5) judge whether fragment has character; If there is character, then character content inputed to the character submeter in standard database, and enter next step; Otherwise, directly enter next step;
(6) measure chip thickness, and measurement result is inputted the thickness submeter in standard database, judge measurement result whether in tolerance, if in tolerance, then enter next step, otherwise remeasure;
(7) judge whether fragment has fixing bore, if not, enter next step; If have, judge it is solid bore or hollow bore, and judged result is inputted the fixing bore submeter in standard database, measure the length of fixing bore and wide, and measurement result is inputted respectively fixing bore submeter, judge whether in tolerance; If in tolerance, then enter next step, otherwise remeasure;
(8) judge whether fragment has striped, if not, enter next step; If have, measure maximal value and the minimum value of fringe spacing, and measurement result is inputted respectively the front fringe spacing submeter in standard database, then enter next step;
(9) judge on fragment, whether front streakline and lateral edges have angle, if there is angle, then measure maximal value and the minimum value of angle, and front streakline measurement result inputted respectively in standard database and lateral edges angle submeter, then enter next step; Otherwise, then directly next step is entered;
(10) judge on fragment, whether front and side have angle, if there is angle, then measure maximal value and the minimum value of angle, and front measurement result inputted respectively in standard database and side angle submeter, then enter next step; Otherwise, then directly next step is entered;
(11) judge whether fragment has lateral edges angle, if having, measure maximal value and the minimum value of angle, and measurement result is inputted respectively the lateral edges angle submeter in standard database; Otherwise, then directly next step is entered;
(12) the submeter information obtained in above steps is contrasted with existing submeter in standard database respectively, result after contrast is carried out vehicle and is automatically retrieved in vehicle master meter, retrieve all vehicles meeting shred characterization information, and list vehicle and characteristic information thereof and picture;
(13) again to compare confirmation result, confirm then to export final comparison result; Otherwise, return step (2) and again retrieve.
2. a kind of method of carrying out vehicle retrieval based on headlamp lampshade fragment morphological feature as claimed in claim 1, it is characterized in that: in described step (1), in vehicle master meter, comprise automobile full figure, headlamp picture, headlamp disassemble after lampshade picture and the decorative pattern schematic diagram in lampshade front.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510882328.5A CN105528617A (en) | 2015-12-03 | 2015-12-03 | Method for carrying out car model retrieval based on headlight shade shard morphological characteristic |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510882328.5A CN105528617A (en) | 2015-12-03 | 2015-12-03 | Method for carrying out car model retrieval based on headlight shade shard morphological characteristic |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105528617A true CN105528617A (en) | 2016-04-27 |
Family
ID=55770831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510882328.5A Pending CN105528617A (en) | 2015-12-03 | 2015-12-03 | Method for carrying out car model retrieval based on headlight shade shard morphological characteristic |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105528617A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1363483A (en) * | 2001-01-04 | 2002-08-14 | 中国科学院长春光学精密机械与物理研究所 | Method and equipment for discriminating headlight of troublemaking car by computer |
| US8503777B2 (en) * | 2010-12-16 | 2013-08-06 | Sony Corporation | Geometric feature based image description and fast image retrieval |
| CN103679191A (en) * | 2013-09-04 | 2014-03-26 | 西交利物浦大学 | An automatic fake-licensed vehicle detection method based on static state pictures |
-
2015
- 2015-12-03 CN CN201510882328.5A patent/CN105528617A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1363483A (en) * | 2001-01-04 | 2002-08-14 | 中国科学院长春光学精密机械与物理研究所 | Method and equipment for discriminating headlight of troublemaking car by computer |
| US8503777B2 (en) * | 2010-12-16 | 2013-08-06 | Sony Corporation | Geometric feature based image description and fast image retrieval |
| CN103679191A (en) * | 2013-09-04 | 2014-03-26 | 西交利物浦大学 | An automatic fake-licensed vehicle detection method based on static state pictures |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107067722B (en) | Method for constructing vehicle running condition | |
| CN109598929B (en) | Multi-class traffic accident starting number prediction method | |
| TWI493513B (en) | Lane departure warning system and lane identification apparatus and related method thereof | |
| CN112154446B (en) | Stereo lane line determining method and device and electronic equipment | |
| CN104899285A (en) | Display method and apparatus for search result | |
| CN106204497B (en) | A kind of pavement crack extraction algorithm based on smooth smoothed curve and matched curve | |
| CN103411565A (en) | Automobile body inclination degree measurement method of small automobile | |
| CN102663353A (en) | Vehicle identification method based on single frame image and apparatus thereof | |
| CN105354638A (en) | Prediction method and system for repair and maintenance costs of automobile | |
| CN105574944A (en) | Highway intelligent toll collection system based on vehicle identification and method thereof | |
| CN109034226A (en) | A kind of track of vehicle clustering method based on graph theory | |
| Tsai et al. | Horizontal roadway curvature computation algorithm using vision technology | |
| CN105654038A (en) | Vehicle lamp identification method and device | |
| Wood et al. | EPA GHG certification of medium-and heavy-duty vehicles: Development of road grade profiles representative of US controlled access highways | |
| CN104166789A (en) | Lamp light distribution method for equal-brightness illumination on straight road and lamp | |
| CN105528617A (en) | Method for carrying out car model retrieval based on headlight shade shard morphological characteristic | |
| Ki et al. | Bridging the gap between pedestrian and street views for human-centric environment measurement: A GIS-based 3D virtual environment | |
| CN104252707A (en) | Object detecting method and device | |
| CN104849024B (en) | The evaluating method of automotive headlamp | |
| CN110892794A (en) | System and method for displaying street lighting levels | |
| Šeporaitis et al. | Evaluation of horizontal curve radius effect on driving speed in two lane rural road. Pilot study | |
| Zhang et al. | Reliability analysis of vehicle speed estimation based on uncertainty of information obtained on accident scene | |
| Machsus et al. | Generalized additive models for estimating motorcycle collisions on collector roads | |
| KR101573685B1 (en) | System and Method for Combining Traffic Data | |
| KR101407658B1 (en) | Car detection method and system using it |
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: 20160427 |
|
| RJ01 | Rejection of invention patent application after publication |