CN102467669B - Method and equipment for improving matching precision in laser detection - Google Patents
Method and equipment for improving matching precision in laser detection Download PDFInfo
- Publication number
- CN102467669B CN102467669B CN201010547507.0A CN201010547507A CN102467669B CN 102467669 B CN102467669 B CN 102467669B CN 201010547507 A CN201010547507 A CN 201010547507A CN 102467669 B CN102467669 B CN 102467669B
- Authority
- CN
- China
- Prior art keywords
- characteristic parameter
- parameter group
- matching
- unmatched
- weak coupling
- 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.)
- Active
Links
Landscapes
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention relates to a method and equipment for improving matching precision in laser detection, wherein the method comprises the following steps: selecting parameters needing matching from laser detection data; weighting the parameters, wherein the weight value distributed to each parameter is different; searching a matching object among the weighted parameter groups; wherein, whether the parameter group is matched or not is determined according to a preset matching error threshold value. According to the invention, the parameters required by matching are weighted, and then the matching range is adjusted in the matching process by establishing a weak matching library or adjusting a matching error threshold, so that the overall matching precision is improved.
Description
Technical field
The present invention relates to a kind of method and apparatus improving matching precision in laser detection.
Background technology
At present, the mode that have employed laser scanning under increasing occasion detects pedestrian, vehicle, goods etc.In addition, in the process of laser detection, often need to mate testing result, to carry out the subsequent step detected.Such as, the example utilizing double excitation to scan to judge pedestrian's direct of travel just this situation due to.In general, this technology is by carrying out double excitation scanning to pedestrian/passenger flow passage, scan-data analysis is drawn to the pedestrian's data comprising pedestrian's characteristic parameter.Then, mate many group pedestrian characteristic parameters, be same a group traveling together by the pedestrian determination belonging to it in the successful situation of two stack features parameter matching.Finally, determined the direct of travel of this pedestrian by the time of twice lasing area according to same a group traveling together.
But, in the matching process of said method, a match error threshold is generally only set.As long as the matching result of two groups of pedestrian's characteristic parameters does not exceed this match error threshold, the match is successful just can to think them.In general, match error threshold sets based on experience value or drawn by statistics.But in some cases, match error threshold is too high, then the reliability of matching result may be caused low; Match error threshold is too low, then may cause that it fails to match.As can be seen here, there is the not high enough shortcoming of matching precision in above-mentioned matching process.
Therefore, a kind of method and apparatus that can improve matching precision in laser detection is needed.
Summary of the invention
Detailed description by setting forth below, accompanying drawing and claim are become obvious by other characteristic sum benefits of exemplary embodiment of the present invention.
According to an aspect of the present invention, provide a kind of method improving matching precision in laser detection, comprising: in laser detection data, select needs to carry out the parameter of mating; Be weighted process to described parameter, the weights wherein distributing to each parameter are different; And search match objects between parameter group after weighting; Wherein, determine whether parameter group mates according to the match error threshold preset.
Preferably, for a parameter group unmatched, adjust its matching range, proceed coupling.
Preferably, for a parameter group unmatched, adjust its matching range, the step proceeding to mate comprises: to a parameter group unmatched, in weak coupling storehouse, search match objects, wherein said weak coupling storehouse is set up in advance; A parameter group unmatched in weak coupling storehouse is put into described weak coupling storehouse.
Preferably, exist in described weak coupling storehouse between the parameter group exceeding the schedule time and search match objects, for the parameter group that remaining unmatches, be mutually appointed as coupling at random.
Preferably, for a parameter group unmatched, adjust its matching range, the step proceeding to mate comprises: to a parameter group unmatched, adjust described match error threshold, proceeds coupling.
According to a second aspect of the invention, provide a kind of equipment improving matching precision in laser detection, comprising: parameter selecting module, for selecting the parameter needing to carry out mating in laser detection data; Weighting block, for being weighted process to described parameter, the weights wherein distributing to each parameter are different; And matching module, for searching match objects between the parameter group after weighting; Wherein, determine whether parameter group mates according to the match error threshold preset.
Preferably, described equipment also comprises matching range adjusting module, for for a parameter group unmatched, adjusts its matching range, proceeds coupling.
Preferably, described matching range adjusting module comprises: weak coupling library storage module, for setting up weak coupling storehouse wherein; Wherein, to a parameter group unmatched, in weak coupling storehouse, search match objects; By in weak coupling storehouse the parameter group unmatched stored in described weak coupling storehouse.
Preferably, described matching range adjusting module comprises:
Match error threshold adjusting module, for a parameter group unmatched, adjusts described match error threshold, proceeds coupling.
The present invention is by being weighted process to the parameter required for coupling, and the mode then in the matching process by setting up weak coupling storehouse or adjustment match error threshold adjusts matching range, improves the overall precision of coupling.
Accompanying drawing explanation
Exemplary embodiment of the present invention is more fully understood in the accompanying drawing from the detailed description hereinafter provided and different embodiments of the invention, but this should not be regarded as the present invention to be limited to specific embodiment, and should just in order to explain and understand.
Fig. 1 is the process flow diagram improving the method for matching precision in laser detection according to the embodiment of the present invention; And
Fig. 2 is the schematic block diagram improving the equipment of matching precision in laser detection according to the embodiment of the present invention.
Embodiment
Those of ordinary skill in the art will recognize, the following detailed description of described exemplary embodiment is only illustrative, and not be intended to be limited by any way.Other embodiments easily will be presented to and be benefited from this kind of technician of the present disclosure.Now, by the enforcement in detail with reference to exemplary embodiment as shown in some accompanying drawings.In detailed description throughout accompanying drawing and below, the identical Reference numeral of use is pointed out same or similar part.
Fig. 1 is the process flow diagram improving the method for matching precision in laser detection according to the embodiment of the present invention.
As shown in Figure 1, laser detection data is the characteristic parameter of the pedestrian drawn by laser detection.Should illustrate, for one by laser detection identify humanoid, give the essential characteristic parameter of this people in laser scanning data.These characteristic parameters carry out same person under double excitation scanning coupling after being provides data basis, and specifically, pedestrian's characteristic parameter can comprise the time, position, pedestrian level, pedestrian width etc. of pedestrian by laser scanning face.
In step 101, from pedestrian's characteristic parameter, select the characteristic parameter in order to weighting.Because the method for laser detection coupling is had nothing in common with each other, the parameter selecting to be weighted from characteristic parameter group is also had nothing in common with each other.Such as, if adopt the position of pedestrian and time to mate, then pedestrian position, pedestrian's time can be selected with pending weighting process, and if adopt pedestrian level, pedestrian's width mates, pedestrian level, pedestrian's width then can be selected with pending weighting process, like this.
In step 102, be weighted process to the characteristic parameter selected, the weights wherein for the distribution of each characteristic parameter are different.
In step 103, the characteristic parameter group after weighting is mated.
In step 104, for a characteristic parameter group unmatched in step 103, proceed coupling in weak coupling storehouse, this weak coupling storehouse sets up in advance.
In step 105, at step 104 or a characteristic parameter group unmatched, put it in weak coupling storehouse, the use of coupling after waiting until.
In addition, for there is the characteristic parameter group exceeding the schedule time in weak coupling storehouse, can mate each other; And the characteristic parameter group that remaining unmatches, can random arrangement match objects wherein.
The data that the match is successful in the process above, can continue on for other purposes after laser detection coupling.
Described above is a kind of method improving matching precision in laser detection according to the embodiment of the present invention, be to be understood that each step in the method is not be intended to limit the present invention, but various change can be had.Such as, the foundation in weak coupling storehouse is actually to adjust matching range, and to improve overall matching precision, and the adjustment of matching range can be taked various mode to realize.
Fig. 2 is the schematic block diagram improving the equipment of matching precision in laser detection according to the embodiment of the present invention.
As shown in Figure 2, equipment comprises parameter selecting module, weighting block, matching module and weak coupling library storage module.
Parameter selecting module receives pedestrian's characteristic parameter that laser detection draws, selects wherein to need the characteristic parameter treating weighting.Because the method for laser detection coupling is had nothing in common with each other, the parameter selecting to be weighted from characteristic parameter group is also had nothing in common with each other.Such as, if adopt the position of pedestrian and time to mate, then pedestrian position, pedestrian's time can be selected with pending weighting process, and if adopt pedestrian level, pedestrian's width mates, pedestrian level, pedestrian's width then can be selected with pending weighting process, like this.Then, parameter selecting module will select characteristic parameter weighted input module.
Weighting block is weighted process to the characteristic parameter selected, and the weights wherein for the distribution of each characteristic parameter are different.Then, weighting block will be weighted the characteristic parameter input matching module after process.
Matching module mates the characteristic parameter group after weighting, wherein, sets a match error threshold in advance and judges that whether coupling is successful.
Weak coupling library storage module, for setting up weak coupling storehouse wherein.For in first time characteristic parameter group unmatched in matching module, with the characteristic parameter group in weak coupling storehouse for scope proceeds coupling.In brief, be exactly selected to read all characteristic parameter groups in weak coupling storehouse, in order to mate with a characteristic parameter group unmatched by matching module.If the characteristic parameter group matched with it so still cannot be found, then the characteristic parameter group this cannot mated stored in weak coupling storehouse, the use of coupling after waiting until.
In addition, for there is the characteristic parameter group exceeding the schedule time in weak coupling storehouse, can mate each other; And the characteristic group that remaining unmatches, can random arrangement match objects wherein.
The data that the match is successful in the process above, can continue on for other purposes after laser detection coupling.
The practical function in weak coupling storehouse has been described in the describing of Fig. 1, therefore be to be understood that, weak coupling library storage module in Fig. 2 is only for adjusting a kind of implementation of match error threshold, and it is not be intended to limit the present invention, but can have other replacement form.It will be appreciated by those skilled in the art that and the module of the adjustment being used for realizing match error threshold can be referred to as matching range adjusting module.
Although illustrate and described specific embodiments of the present invention, but under the prerequisite not deviating from exemplary embodiment of the present invention and more broad aspect thereof, those skilled in the art obviously can make changes and modifications based on teaching herein.Such as, weak coupling storehouse can not be adopted, but adjust matching range when to unmatch by adjustment match error threshold, re-start coupling, until the match is successful; Corresponding with it, equipment of the present invention can carry out alternative weak coupling library storage module with a match error threshold adjusting module, for carrying out above-mentioned matching range adjustment.Therefore, appended claim is intended to all this kind of true spirits of exemplary embodiment of the present invention and the change of scope and change of not deviating to be included within its scope.
Claims (4)
1. in laser detection, improve a method for matching precision, comprising:
In laser detection data, select the parameter needing to carry out mating, described needs carry out the parameter constitutive characteristic parameter group of mating;
According to matching condition, from described characteristic parameter group, select the characteristic parameter in order to weighting, be weighted process to described characteristic parameter, the weights wherein distributing to each characteristic parameter are different; Match objects is searched between characteristic parameter group after weighting; Wherein, the characteristic parameter set in matching condition selects the characteristic parameter in order to weighting identical with described from described characteristic parameter group; Wherein, determine whether characteristic parameter group mates according to the match error threshold preset;
For a characteristic parameter group unmatched, adjust its matching range, proceed coupling;
Wherein, for a characteristic parameter group unmatched, adjust its matching range, the step proceeding to mate comprises:
To a characteristic parameter group unmatched, in weak coupling storehouse, search match objects, wherein said weak coupling storehouse is set up in advance;
By in weak coupling storehouse or a characteristic parameter group unmatched put into described weak coupling storehouse;
Exist in described weak coupling storehouse between the characteristic parameter group exceeding the schedule time and search match objects, for the characteristic parameter group that remaining unmatches, be mutually appointed as coupling at random.
2. method according to claim 1, wherein, for a characteristic parameter group unmatched, adjusts its matching range, and the step proceeding to mate also comprises:
To a characteristic parameter group unmatched, adjust described match error threshold, proceed coupling.
3. in laser detection, improve an equipment for matching precision, comprising:
Parameter selecting module, for selecting the parameter needing to carry out mating in laser detection data, described needs carry out the parameter constitutive characteristic parameter group of mating;
Weighting block, for according to matching condition, from described parameter group, select the characteristic parameter in order to weighting, be weighted process to described characteristic parameter, the weights wherein distributing to each characteristic parameter are different; Wherein, the characteristic parameter set in matching condition selects the characteristic parameter in order to weighting identical with described from described characteristic parameter group;
Matching module, for searching match objects between the characteristic parameter group after weighting; Wherein, determine whether characteristic parameter group mates according to the match error threshold preset;
Matching range adjusting module, for for a characteristic parameter group unmatched, adjusts its matching range, proceeds coupling;
Wherein, described matching range adjusting module comprises:
Weak coupling library storage module, for setting up weak coupling storehouse wherein;
Wherein, to a characteristic parameter group unmatched, in weak coupling storehouse, match objects is searched; By in weak coupling storehouse or a characteristic parameter group unmatched stored in described weak coupling storehouse;
Exist in described weak coupling storehouse between the characteristic parameter group exceeding the schedule time and search match objects, for the characteristic parameter group that remaining unmatches, be mutually appointed as coupling at random.
4. equipment according to claim 3, wherein, described matching range adjusting module also comprises:
Match error threshold adjusting module, for a characteristic parameter group unmatched, adjusts described match error threshold, proceeds coupling.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201010547507.0A CN102467669B (en) | 2010-11-17 | 2010-11-17 | Method and equipment for improving matching precision in laser detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201010547507.0A CN102467669B (en) | 2010-11-17 | 2010-11-17 | Method and equipment for improving matching precision in laser detection |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102467669A CN102467669A (en) | 2012-05-23 |
CN102467669B true CN102467669B (en) | 2015-11-25 |
Family
ID=46071288
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201010547507.0A Active CN102467669B (en) | 2010-11-17 | 2010-11-17 | Method and equipment for improving matching precision in laser detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102467669B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1302460C (en) * | 2000-08-21 | 2007-02-28 | 曼德斯必德技术公司 | Method for noise robust classification in speech coding |
CN1949245A (en) * | 2006-11-09 | 2007-04-18 | 上海大学 | Personal face matching method based on limited multiple personal face images |
CN100434932C (en) * | 2006-07-06 | 2008-11-19 | 上海交通大学 | Collaborative work of multiple lidars, and dat processing method |
CN101369279A (en) * | 2008-09-19 | 2009-02-18 | 江苏大学 | Detection method for academic dissertation similarity based on computer searching system |
-
2010
- 2010-11-17 CN CN201010547507.0A patent/CN102467669B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1302460C (en) * | 2000-08-21 | 2007-02-28 | 曼德斯必德技术公司 | Method for noise robust classification in speech coding |
CN100434932C (en) * | 2006-07-06 | 2008-11-19 | 上海交通大学 | Collaborative work of multiple lidars, and dat processing method |
CN1949245A (en) * | 2006-11-09 | 2007-04-18 | 上海大学 | Personal face matching method based on limited multiple personal face images |
CN101369279A (en) * | 2008-09-19 | 2009-02-18 | 江苏大学 | Detection method for academic dissertation similarity based on computer searching system |
Also Published As
Publication number | Publication date |
---|---|
CN102467669A (en) | 2012-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102192830B1 (en) | Method for acquiring bounding box corresponding to an object in an image by using convolutional neural network including tracking network and computing device using the same | |
KR101994737B1 (en) | Wireless charging apparatus and method for the same | |
CN104200351B (en) | Logistics management system and positioning method based on RFID rapid positioning | |
CN107315795B (en) | The instance of video search method and system of joint particular persons and scene | |
US20170115396A1 (en) | Object detection system | |
CN102831129B (en) | Retrieval method and system based on multi-instance learning | |
CN104461877B (en) | Method for testing software and software testing device | |
CN107220505A (en) | Child development capability assessment method and device | |
CN105989084A (en) | Question answering method and device | |
CN104903753A (en) | System, method and program product for automatically matching new members of a population with analogous members | |
CN106126668A (en) | A kind of image characteristic point matching method rebuild based on Hash | |
CN102467669B (en) | Method and equipment for improving matching precision in laser detection | |
CN103500017B (en) | A kind of many of photoelectricity interaction module identifies and tracking | |
CN101501711A (en) | Learning data set optimization method for signal identification device and signal identification device capable of optimizing the learning data set | |
Bentley et al. | Using a variational autoencoder to learn valid search spaces of safely monitored autonomous robots for last-mile delivery | |
US9489780B2 (en) | Method for processing data | |
CN100574218C (en) | A kind of method of setting up artificial distinct network | |
CA3155999A1 (en) | Systems and methods for auditing assets | |
CN111027589A (en) | Multi-division target detection algorithm evaluation system and method | |
US9208402B2 (en) | Face matching for mobile devices | |
CN103761636B (en) | Steel coil allocating method and device | |
CN110571825A (en) | Static synchronous compensator model parameter identification method and system | |
CN105868394A (en) | Method for APP classification based on WEB and log information and device thereof | |
CN108363410A (en) | Flight control method, device and the unmanned plane of unmanned plane | |
CN107741959A (en) | A kind of pseudo- static URL recognition methods and system based on machine learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CP02 | Change in the address of a patent holder |
Address after: 100193 2 / F, block B, qianfang building, 27 Zhongguancun Software Park, 8 Dongbeiwang West Road, Haidian District, Beijing Patentee after: CHINA TRANSINFO TECHNOLOGY Corp. Address before: 100191 9th floor, Weishi building, 39 Xueyuan Road, Haidian District, Beijing Patentee before: CHINA TRANSINFO TECHNOLOGY Corp. |
|
CP02 | Change in the address of a patent holder |