CN111145191A - Run-length coding-based connected domain searching method and device - Google Patents
Run-length coding-based connected domain searching method and device Download PDFInfo
- Publication number
- CN111145191A CN111145191A CN201911384721.6A CN201911384721A CN111145191A CN 111145191 A CN111145191 A CN 111145191A CN 201911384721 A CN201911384721 A CN 201911384721A CN 111145191 A CN111145191 A CN 111145191A
- Authority
- CN
- China
- Prior art keywords
- run
- label
- labels
- blocks
- merging
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000002372 labelling Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 abstract description 9
- 238000004458 analytical method Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 239000000872 buffer Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- QHLFJSMAWAWVRU-UHFFFAOYSA-N n-(5-chloro-4-methyl-1,3-thiazol-2-yl)propanamide Chemical compound CCC(=O)NC1=NC(C)=C(Cl)S1 QHLFJSMAWAWVRU-UHFFFAOYSA-N 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention relates to the field of image processing, in particular to a run-length coding-based connected domain searching method and device. Carrying out run-length coding on the binarization pixel points in the image to obtain a plurality of run-length blocks; determining a temporary label of the current line run block according to the relative position relation of the adjacent two lines of run blocks; merging the equivalent labels according to the recorded equivalent label pairs to generate a merged lookup table; performing one-time traversal operation on all the run-length blocks in the current row by referring to the merging lookup table, replacing the temporary labels with corresponding values of the temporary labels in the merging lookup table, and determining the final labels of the run-length blocks; and updating the characteristic value of the connected domain represented by each final label. The method and the device calculate the characteristic parameters of each connected domain by finding out all the connected domains in the binary image, and provide analysis data for subsequent image identification processing. The invention realizes the search of the image connected domain by using a hardware mode, has simple design structure, occupies less storage resources and is easy to realize by hardware.
Description
Technical Field
The invention relates to the field of image processing, in particular to a run-length coding-based connected domain searching method and device.
Background
With the rapid development of integrated circuit technology and the increasing demand of people for intelligent video systems, high-resolution and high-speed camera shooting and acquisition become more and more common, and the requirement for real-time and accurate processing of high-speed video images is also increased. Connected domain searching is an important step in abstracting and refining image information in video image processing, and the speed of the connected domain searching often becomes a bottleneck of a video application system.
The connected domain is an image region composed of foreground pixels with the same pixel value and adjacent positions in an image, and the connected region contains characteristic information such as the size, shape and position of an object in the image and is the basis of analysis of all binary images. The purpose of the connected domain searching algorithm is to assign a unique label to a connected object in the image, mark all connected domains in the image, and calculate the characteristic information of each connected domain, including the area, the gravity center, the minimum circumscribed regular rectangle and the like. Therefore, the whole algorithm can be divided into two parts: index and eigenvalue calculations. The difficulty is the label, because the correct label is the premise of calculating the characteristic value, the way of connecting the labels of the objects also affects the way of calculating the characteristic value, and the shapes of the objects may be complex, and the labels which conflict with each other may be generated, and a mechanism for processing the conflicting labels is needed.
At present, most connected domain search algorithms are based on a general processor or a GPU platform and are realized by a software method, and the time delay of the connected domain search algorithms often cannot meet the high-speed real-time video processing requirement. For the widely applied label pair lookup table method, when the objects in the image are more and complicated, more label values are often needed, so the storage space of the lookup table is larger. When implemented in hardware, the worst case memory space needs to be taken into account.
Disclosure of Invention
The embodiment of the invention provides a run length coding-based connected domain searching method and device, which at least solve the technical problem that the processing speed of the existing connected domain searching algorithm is low.
According to an embodiment of the present invention, a run-length coding-based connected component searching method is provided, which includes the following steps:
carrying out run-length coding on the binarization pixel points in the image to obtain a plurality of run-length blocks;
determining a temporary label of the current line run block according to the relative position relation of the adjacent two lines of run blocks;
merging the equivalent labels according to the recorded equivalent label pairs to generate a merged lookup table;
performing one-time traversal operation on all the run-length blocks in the current row by referring to the merging lookup table, replacing the temporary labels with corresponding values of the temporary labels in the merging lookup table, and determining the final labels of the run-length blocks;
and updating the characteristic value of the connected domain represented by each final label.
Further, the characteristic value of the connected component represented by the final label includes the minimum circumscribed rectangle coordinate of the connected component.
Further, the run-length coding is carried out on the binarization pixel points in the image, and the obtaining of a plurality of run-length blocks comprises the following steps:
and carrying out run length coding on the binarization pixel points of each line in the image.
Further, the determining the temporary label of the current line run block according to the relative position relationship of the two adjacent line run blocks includes:
carrying out temporary labeling on the run-length blocks of each line;
and determining the temporary label of the current line run block according to the position relation of the current line run block and the previous line run block, and simultaneously generating an equivalent label list and a merging lookup table.
Further, the determining the temporary label of the current line run block according to the relative position relationship of the two adjacent line run blocks further comprises:
and arranging the smaller labels in the equivalent label list from small to large to generate a new equivalent label list.
Further, merging the equivalent labels according to the equivalent label pairs of the records, and generating a merged lookup table includes:
and according to the new equivalent label list, carrying out merging updating on the corresponding values in the merging lookup table to generate a new merging lookup table.
Further, merging the equivalent labels according to the equivalent label pairs of the records, and generating a merged lookup table further includes:
and processing the new combined lookup table, eliminating an overlarge label value, redistributing the labels and generating an updated combined lookup table.
Further, performing a traversal operation on all the run blocks in the current row with reference to the merge lookup table, replacing the temporary labels with their corresponding values in the merge lookup table, and determining the final labels of the run blocks includes:
and performing traversal operation once on all the run blocks in the current row by referring to the updated merging lookup table, replacing the temporary labels with corresponding values of the temporary labels in the updated merging lookup table, determining the final labels of the run blocks, and caching the run blocks with the final labels in a duplicate mode.
Further, the determining the temporary label of the current line run block according to the relative position relationship of the two adjacent line run blocks further comprises:
and traversing the labels in the characteristic value list of the previous line, if the validity of the labels in the current line is found to be 0, intercepting the connected domain, and caching the characteristic values.
According to another embodiment of the present invention, there is provided a run-length coding-based connected component searching apparatus, including:
the run-length coding module is used for carrying out run-length coding on the binarization pixel points in the image to obtain a plurality of run-length blocks;
the mark temporary setting module is used for determining a temporary mark of the current line run block according to the relative position relation of the adjacent two lines of run blocks;
the label merging module is used for merging the equivalent labels according to the recorded equivalent label pairs to generate a merging lookup table;
the mark finalizing module is used for executing one-time traversal operation on all the run blocks in the current row by referring to the merging lookup table, replacing the temporary mark with the corresponding value of the temporary mark in the merging lookup table and determining the final mark of the run block;
and the characteristic value updating module is used for updating the characteristic value of the connected domain represented by each final label.
According to the run-length coding-based connected domain searching method and device, all connected domains in the binary image are searched, the characteristic parameters of all connected domains are calculated, and analysis data are provided for subsequent image identification processing. Compared with the prior art which uses a software method, the device of the invention has the advantages of simple design structure, less occupied storage resources and easy hardware realization. The method and the device are suitable for hardware products of image processing applications such as security systems, traffic monitoring, license plate recognition and the like.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a run-length coding-based connected domain searching method according to the present invention;
FIG. 2 is a preferred flowchart of the run-length coding-based connected component searching method of the present invention;
FIG. 3 is a block diagram of a run-length coding-based connected domain searching apparatus according to the present invention;
FIG. 4 is a diagram showing the read-write relationship of each sub-module to the cache unit in the present invention;
fig. 5 is a design diagram of a master state machine in a connected domain lookup master control module according to the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Aiming at the current situation and the problems, the invention adopts a run-length coding-based connected domain searching method and a run-length coding-based connected domain searching device, and is realized by hardware circuit design through Verilog HDL. The circuit architecture can effectively improve the speed of searching the connected domain and reduce the occupation of storage resources.
Example 1
According to an embodiment of the present invention, a run-length coding-based connected component searching method is provided, referring to fig. 1, including the following steps:
s101: carrying out run-length coding on the binarization pixel points in the image to obtain a plurality of run-length blocks;
s102: determining a temporary label of the current line run block according to the relative position relation of the adjacent two lines of run blocks;
s103: merging the equivalent labels according to the recorded equivalent label pairs to generate a merged lookup table;
s104: performing one-time traversal operation on all the run-length blocks in the current row by referring to the merging lookup table, replacing the temporary labels with corresponding values of the temporary labels in the merging lookup table, and determining the final labels of the run-length blocks;
s105: and updating the characteristic value of the connected domain represented by each final label.
According to the run-length coding-based connected domain searching method, all connected domains in the binary image are searched, the characteristic parameters of all connected domains are calculated, and analysis data are provided for subsequent image identification processing. The method has simple design structure, occupies less storage resources and is easy to realize hardware. The method is suitable for hardware products of image processing applications such as security systems, traffic monitoring, license plate recognition and the like.
The following describes the run-length coding-based connected component searching method in detail by using a specific embodiment.
The invention discloses a run-length coding-based connected domain searching method, which is a real-time connected domain analysis method for single scanning. Firstly, run-length coding is carried out on a binarization pixel point; then temporarily determining labels according to the relative position relationship of two adjacent lines of run blocks, and merging the equivalent labels according to the label equivalent pairs recorded in the run coding process; and finally, updating the characteristic values, namely the minimum circumscribed rectangular coordinates (Xmin, Xmax, Ymin and Ymax), of the connected domains represented by each label. The specific process flow is shown in fig. 2.
Run-length encoding refers to processing of consecutive pixels in each row (or each column) of an image as a whole. Each segment of pixel point is called a run block, and is positioned by recording a start coordinate, an end coordinate and a line number. And judging whether the pixel points are communicated or not, wherein the relative positions of each run block and the run block in the previous row only need to be compared. If a certain run block is not connected with the previous run block, setting a new label for the run block; if the run block is connected with one run block of the previous line, setting the same reference number; if the run block is connected to a plurality of run blocks in the previous row, the situation of label collision may occur, and specific analysis needs to be performed for different situations.
Example 2
According to another embodiment of the present invention, there is provided a run-length coding-based connected component searching apparatus, referring to fig. 3, including:
the run-length coding module 201 is configured to perform run-length coding on the binarization pixel points in the image to obtain a plurality of run-length blocks;
a mark provisional module 202, configured to determine a provisional mark of the current line run block according to a relative position relationship between two adjacent line run blocks;
a label merging module 203, configured to merge equivalent labels according to the recorded equivalent label pairs to generate a merging lookup table;
a mark final module 204, configured to perform a traversal operation on all the run blocks in the current row with reference to the merge lookup table, replace the temporary mark with a corresponding value in the merge lookup table, and determine a final mark of the run block;
and the characteristic value updating module 205 is used for updating the characteristic value of the connected domain represented by each final label.
The run-length coding-based connected domain searching device in the embodiment of the invention calculates the characteristic parameters of each connected domain by searching all connected domains in the binary image, and provides analysis data for subsequent image identification processing. Compared with the prior art which uses a software method, the device of the invention has the advantages of simple design structure, less occupied storage resources and easy hardware realization. The device is suitable for hardware products of image processing applications such as security systems, traffic monitoring, license plate recognition and the like.
The following describes in detail the run-length coding-based connected component searching apparatus according to the present invention with specific embodiments.
Based on the principle and flow of the method, the invention provides a hardware circuit design scheme, namely a run-length coding-based connected domain searching device in a preferred embodiment. As shown in fig. 4, the device mainly includes 10 sub-modules, such as a connected domain searching main control module, a run length encoding module, a first line processing module, a label adjacent determination module, a connected domain intercepting module, an equivalent list sorting module, a label merging module, a label re-allocation module, a label final determination module, and a feature value calculation module, and 9 cache units, such as FIFO1, FIFO2, FIFO3, FIFO4, MGLUT, EQLIST, TZLIST1, TZLIST2, and uarm.
As shown in fig. 4, the main control module (main _ ctrl) for searching the connected domain mainly has the function of controlling the flow of searching the connected domain and managing the read-write access of each cache unit by each of the other sub-modules.
And the run coding module (running coding) reads the binarization pixel points of each line stored in the binarization pixel cache unit (PFIFO), performs run coding, and caches the obtained run blocks into the FIFO 1.
The first line processing module (first line _ proc) marks the first line run block, caches the marked run block into the FIFO2, and writes the characteristic value information of the first line run block into the characteristic value list TZLIST 1.
The mark temporary determination module (label _ determn) determines the temporary mark of the current line run block according to the position relationship between the current line run block and the previous line run block, and buffers the run blocks with the determined temporary mark into the FIFO 3. An equivalent label list (EQLIST) and a merge look-up table (MGLUT) are generated simultaneously.
And a connected domain intercepting module (conndm _ extract) for traversing the label in the feature value list TZLIST1 of the previous line, intercepting the connected domain if the validity of the label in the current line is 0, and caching the feature value into the uarm.
And the equivalent list sorting module (EQlist _ sort) arranges the smaller labels in the equivalent label list in the order from small to large to generate a new equivalent label list (EQLIST).
And a label merging module (label _ merge) for merging and updating the corresponding values in the merging lookup table according to the new equivalent label list to generate a new merging lookup table (MGLUT).
And a label re-allocation module (label _ re-allocation) for processing the combined lookup table, eliminating the overlarge label value, re-allocating the label and generating a new combined lookup table (MGLUT).
The mark finalization module (label _ finalize) performs a traversal operation on all the run blocks of the current line, refers to the merge lookup table, replaces the temporary mark with its corresponding value, completes the final determination of the run block mark, and buffers in "duplicate" into the FIFOs 2 and 4. It also creates a feature value list TZLIST2 and sets initial values.
And the characteristic value calculating module (tzvalue _ cal) calculates the characteristic value information (namely the minimum circumscribed rectangle coordinates Xmin, Xmax, Ymin and Ymax) of each label connected domain in real time according to the TZLIST1, the MGLUT and the information in the TZLIST2 and the FIFO 4.
FIFO 1: and caching the temporarily unnumbered run-length blocks obtained by the run-length coding.
FIFO2 and FIFO 4: the cache determines the run-length blocks of the final index, which are duplicates. The FIFO2 provides run block information for the previous line for the run block comparison process. The FIFO4 provides run block information for the current line for the feature value computation process.
FIFO 3: and caching the run blocks with the determined temporary labels in the current line.
MGLUT: and combining the lookup tables and recording the validity and the corresponding value of the label.
EQLIST: list of equivalent labels, record equivalent label pairs.
TZLIST 1: the feature value list1 records feature value information of the first line or the previous line.
TZLIST 2: and a feature value list2 for recording feature value information of the current line.
uRAM: and caching the intercepted characteristic value information of the connected domain.
The design of the master state machine in the connected domain lookup master module is shown in fig. 5. FIG. 5 is a state machine transition diagram of a detailed logic design, which also shows the overall flow of image connected domain search.
"FSM _ IDLE" in the oval box in FIG. 5 represents the IDLE state;
"WAIT _ BINARIZ _ CMPT" represents a state of waiting for completion of the binarization operation;
"RUNCODING" means run-length coding state;
"FIRSTLINE _ PROC" indicates the leading line processing state;
"LABEL _ detarmn" indicates a LABEL temporary determination state;
"CONNDM _ EXTRACT" represents a connected domain interception state;
"EQLIST _ SORT" represents the equivalent label list ordering state;
"LABEL _ MERGE" indicates a LABEL MERGE state;
"LABEL _ reconfiguration" indicates a LABEL reallocation state;
"LABEL _ fine" indicates the LABEL finalization state;
"TZVALUE _ CAL" represents a feature value calculation state;
"FSM _ FINISH" represents the state machine end state.
These are all states defined in the state machine; while the parameter or quantity relational expression above each arrow in fig. 5 is a condition for each state transition, and the logic code thereof is written by using one or more of general programming languages, which is not limited herein.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described system embodiments are merely illustrative, and for example, a division of a unit may be a logical division, and an actual implementation may have another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units or modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A run-length coding-based connected domain searching method is characterized by comprising the following steps:
carrying out run-length coding on the binarization pixel points in the image to obtain a plurality of run-length blocks;
determining a temporary label of the current line run block according to the relative position relation of the adjacent two lines of run blocks;
merging the equivalent labels according to the recorded equivalent label pairs to generate a merged lookup table;
performing one-time traversal operation on all the run-length blocks in the current row by referring to the merging lookup table, replacing the temporary labels with corresponding values of the temporary labels in the merging lookup table, and determining the final labels of the run-length blocks;
and updating the characteristic value of the connected domain represented by each final label.
2. The run-length coding-based connected component searching method of claim 1, wherein the characteristic value of the connected component represented by the final label comprises the minimum bounding rectangle coordinate of the connected component.
3. The run-length coding-based connected domain searching method according to claim 1, wherein the run-length coding of the binarized pixel points in the image to obtain a plurality of run-length blocks comprises:
and carrying out run length coding on the binarization pixel points of each line in the image.
4. The run-length-coding-based connected component search method according to claim 3, wherein said determining the temporary label of the current row run block according to the relative position relationship between two adjacent rows of run blocks comprises:
carrying out temporary labeling on the run-length blocks of each line;
and determining the temporary label of the current line run block according to the position relation of the current line run block and the previous line run block, and simultaneously generating an equivalent label list and a merging lookup table.
5. The run-length-coding-based connected component search method according to claim 4, wherein said determining the temporary label of the current row run block according to the relative position relationship between two adjacent row run blocks further comprises:
and arranging the smaller labels in the equivalent label list from small to large to generate a new equivalent label list.
6. The run-length coding-based connected component search method of claim 5, wherein said merging equivalent labels according to the recorded equivalent label pairs to generate a merged look-up table comprises:
and according to the new equivalent label list, carrying out merging updating on the corresponding values in the merging lookup table to generate a new merging lookup table.
7. The run-length coding-based connected component search method of claim 6, wherein said merging equivalent labels according to the recorded equivalent label pairs to generate a merged look-up table further comprises:
and processing the new combined lookup table, eliminating an overlarge label value, redistributing the labels and generating an updated combined lookup table.
8. The run-length coding-based connected domain searching method of claim 7, wherein the performing a traversal operation with reference to the merged look-up table for all the run-length blocks in the current row, replacing the temporary labels with their corresponding values in the merged look-up table, and determining the final labels of the run-length blocks comprises:
and performing traversal operation once on all the run blocks in the current row by referring to the updated merging lookup table, replacing the temporary labels with corresponding values of the temporary labels in the updated merging lookup table, determining the final labels of the run blocks, and caching the run blocks with the final labels in a duplicate mode.
9. The run-length-coding-based connected component search method according to claim 4, wherein said determining the temporary label of the current row run block according to the relative position relationship between two adjacent row run blocks further comprises:
and traversing the labels in the characteristic value list of the previous line, if the validity of the labels in the current line is found to be 0, intercepting the connected domain, and caching the characteristic values.
10. A run-length coding-based connected component searching device is characterized by comprising:
the run-length coding module is used for carrying out run-length coding on the binarization pixel points in the image to obtain a plurality of run-length blocks;
the mark temporary setting module is used for determining a temporary mark of the current line run block according to the relative position relation of the adjacent two lines of run blocks;
the label merging module is used for merging the equivalent labels according to the recorded equivalent label pairs to generate a merging lookup table;
the mark finalizing module is used for executing one-time traversal operation on all the run blocks in the current row by referring to the merging lookup table, replacing the temporary mark with the corresponding value of the temporary mark in the merging lookup table and determining the final mark of the run block;
and the characteristic value updating module is used for updating the characteristic value of the connected domain represented by each final label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911384721.6A CN111145191A (en) | 2019-12-28 | 2019-12-28 | Run-length coding-based connected domain searching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911384721.6A CN111145191A (en) | 2019-12-28 | 2019-12-28 | Run-length coding-based connected domain searching method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111145191A true CN111145191A (en) | 2020-05-12 |
Family
ID=70521311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911384721.6A Pending CN111145191A (en) | 2019-12-28 | 2019-12-28 | Run-length coding-based connected domain searching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111145191A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724406A (en) * | 2020-07-14 | 2020-09-29 | 苏州精濑光电有限公司 | Region communication merging method, device, equipment and medium |
| CN112069852A (en) * | 2020-09-07 | 2020-12-11 | 凌云光技术股份有限公司 | Low-quality two-dimensional code information extraction method and device based on run-length coding |
| CN112270704A (en) * | 2020-10-26 | 2021-01-26 | 吉林大学 | Star point mass center extraction method based on data linked list structure |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680531A (en) * | 2015-02-28 | 2015-06-03 | 西安交通大学 | Connection flux statistical information extraction method and VLSI structure |
| CN105719296A (en) * | 2016-01-21 | 2016-06-29 | 天津大学 | High speed binary connected domain marking method based on address-event expression |
| CN108062759A (en) * | 2018-01-25 | 2018-05-22 | 华中科技大学 | A kind of more pixel-parallel labeling methods and system for being used to mark bianry image |
-
2019
- 2019-12-28 CN CN201911384721.6A patent/CN111145191A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680531A (en) * | 2015-02-28 | 2015-06-03 | 西安交通大学 | Connection flux statistical information extraction method and VLSI structure |
| CN105719296A (en) * | 2016-01-21 | 2016-06-29 | 天津大学 | High speed binary connected domain marking method based on address-event expression |
| CN108062759A (en) * | 2018-01-25 | 2018-05-22 | 华中科技大学 | A kind of more pixel-parallel labeling methods and system for being used to mark bianry image |
Non-Patent Citations (2)
| Title |
|---|
| 刘奇琦 等: "一种二值图像连通区域标记的新方法" * |
| 王凯 等: "基于FPGA的快速连通区域标记算法的设计与实现" * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724406A (en) * | 2020-07-14 | 2020-09-29 | 苏州精濑光电有限公司 | Region communication merging method, device, equipment and medium |
| CN111724406B (en) * | 2020-07-14 | 2023-12-08 | 苏州精濑光电有限公司 | Regional communication merging method, device, equipment and medium |
| CN112069852A (en) * | 2020-09-07 | 2020-12-11 | 凌云光技术股份有限公司 | Low-quality two-dimensional code information extraction method and device based on run-length coding |
| CN112069852B (en) * | 2020-09-07 | 2023-12-12 | 凌云光技术股份有限公司 | Low-quality two-dimensional code information extraction method and device based on run-length coding |
| CN112270704A (en) * | 2020-10-26 | 2021-01-26 | 吉林大学 | Star point mass center extraction method based on data linked list structure |
| CN112270704B (en) * | 2020-10-26 | 2024-02-20 | 苏州吉天星舟空间技术有限公司 | Star point centroid extraction method based on data linked list structure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145191A (en) | Run-length coding-based connected domain searching method and device | |
| JP5854802B2 (en) | Image processing apparatus, image processing method, and computer program | |
| Klaiber et al. | A resource-efficient hardware architecture for connected component analysis | |
| GB2542131B (en) | Graphics processing method and system for processing sub-primitives | |
| CN101236661A (en) | System and method for managing grain data in computer | |
| GB2542133A (en) | Graphics processing method and system for processing sub-primitives | |
| CN111985456B (en) | Video real-time identification, segmentation and detection architecture | |
| US6654495B1 (en) | Method and apparatus for removing ruled lines | |
| CN108108734A (en) | A kind of licence plate recognition method and device | |
| CA3164081A1 (en) | Video processing method and device based on deep learning | |
| Wang et al. | U-HRnet: delving into improving semantic representation of high resolution network for dense prediction | |
| Kowalczyk et al. | Real-time FPGA implementation of parallel connected component labelling for a 4K video stream | |
| CN109508571A (en) | A kind of empty localization method, device, electronic equipment and storage medium | |
| CN106780415A (en) | A kind of statistics with histogram circuit and multimedia processing system | |
| CN113516739B (en) | Animation processing method and device, storage medium and electronic equipment | |
| JPS63298485A (en) | Image processor | |
| CN111538677A (en) | Data processing method and device | |
| CN108197164A (en) | Business data storage method and device | |
| CN112052859B (en) | License plate accurate positioning method and device in free scene | |
| CN111695685B (en) | On-chip storage system and method for graph neural network application | |
| CN106055487A (en) | Method and system for realizing acceleration of storage systems through partitioned coloring | |
| CN113516738A (en) | Animation processing method and device, storage medium and electronic equipment | |
| CN114756369B (en) | CPU-GPU data synchronization method and device using C + + compiler | |
| JP2001188675A (en) | Data transfer device | |
| CN115809207B (en) | Address marking method and device in Cache, graphic processing system and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200512 |