CN107480645A - A kind of tower crane collision avoidance system and method based on pattern recognition technique - Google Patents
A kind of tower crane collision avoidance system and method based on pattern recognition technique Download PDFInfo
- Publication number
- CN107480645A CN107480645A CN201710718255.5A CN201710718255A CN107480645A CN 107480645 A CN107480645 A CN 107480645A CN 201710718255 A CN201710718255 A CN 201710718255A CN 107480645 A CN107480645 A CN 107480645A
- Authority
- CN
- China
- Prior art keywords
- image
- tower crane
- collision
- thing
- information
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66C—CRANES; LOAD-ENGAGING ELEMENTS OR DEVICES FOR CRANES, CAPSTANS, WINCHES, OR TACKLES
- B66C23/00—Cranes comprising essentially a beam, boom, or triangular structure acting as a cantilever and mounted for translatory of swinging movements in vertical or horizontal planes or a combination of such movements, e.g. jib-cranes, derricks, tower cranes
- B66C23/88—Safety gear
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20228—Disparity calculation for image-based rendering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
Abstract
Present invention relates particularly to a kind of tower crane collision avoidance system and method based on pattern recognition technique, is related to tower crane technical field, and the prompting includes：Image acquiring device, for obtaining image information；First image processor, for by carrying out binaryzation, filtering, rim detection, interest extracted region and collision thing extraction process to the image of acquisition, completing ranging, distance measurement result being sent into control processor；Second image processor, for by carrying out feature point detection and Stereo matching processing to the image of acquisition, completing ranging, distance measurement result being sent into control processor；Sensor group, for obtaining tower crane movable information；Control processor, for judging whether to collide according to distance measurement result and tower crane movable information；In the case where judging to collide, alarm command is sent；Warning device, for the alarm command alert sent according to control processor.Have the advantages that intelligence degree is high, accuracy is high and applicability is wide.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of tower crane anticollision system based on pattern recognition technique
System and method.
Background technology
Derrick crane is as widely used a kind of main construction machinery in China's building installation engineering, for high level
For construction, an even more indispensable important construction machinery.With widely using for tower crane, its safety problem is not yet
Hold ignore, secondly with City Building it is more and more intensive, the density of construction site tower crane is also increasing, and often enter away from
From cross-operation, taken place frequently between the collision and tower crane and building between tower crane during collision accident.
In the course of the work, the means of anticollision generally have two to existing tower crane：Manual control anticollision passes through
Sensor obtains movable information anticollision.Had higher requirements by operating technology of the manual control anticollision for operating personnel,
And have higher limitation, under some complex situations, the generation of collision is difficult to avoid that by manual control.
It is high by one compared to manual control anticollision intelligence degree by way of sensor obtains movable information anticollision
A bit, after but due to sensors for data information, the operation that artificial manipulation carries out anticollision is needed also exist for.Easily occur artificial
Collision accident caused by operational error occurs.
Therefore, a kind of system, method or device for being capable of automatic anticollision is studied, the decision process of collision weeds out people
For subjective factor, go in various complex situations, will be greatly reduced because human operational error caused by collide thing
Therefore occur.
The content of the invention
It is an object of the invention to provide the tower crane collision avoidance system based on pattern recognition technique, the system can pass through image
Knowledge obtains colliding the distance between thing and tower crane otherwise, in conjunction with the movable information of tower crane, judges whether to collide simultaneously
Alarm is sent, has the advantages that intelligence degree is high, accuracy is high and applicability is wide.
Present invention also offers a kind of tower crane collision-proof method based on pattern recognition technique, this method has corresponding excellent
Point.
The technical solution adopted by the present invention is as follows：
A kind of tower crane collision avoidance system based on pattern recognition technique, it is characterised in that the system includes：
Image acquiring device, for obtaining image information；
First image processor, for by carrying out binaryzation, filtering, rim detection, interest region to the image of acquisition
Extraction and collision thing extraction process, complete ranging, distance measurement result are sent into control processor；
Second image processor, for by carrying out feature point detection and Stereo matching processing to the image of acquisition, completing
Ranging, distance measurement result is sent to control processor；
Sensor group, for obtaining tower crane movable information；
Control processor, for judging whether to collide according to distance measurement result and tower crane movable information；Judging meeting
In the case of colliding, alarm command is sent；
Warning device, for the alarm command alert sent according to control processor.
Further, described image acquisition device is monocular and/or binocular image acquisition device.
Further, the system also includes：
Display device, the tower crane that the image information obtained for display image acquisition device, sensor group obtain move letter
The alarm command that breath and control processor are sent；
Data communication equipment, for completing the data communication put between collision system and exterior terminal.
Further, the sensor group includes：
Weight sensor, obtain lift heavy information；
Air velocity transducer, obtain wind speed information；
Amplitude sensor, for obtaining dolly amplitude information；
Height sensor, for obtaining tower crane elevation information；
Angle of revolution sensor, for obtaining big boom slew information.
Further, described first image processor includes：
Binarization unit, for carrying out binary conversion treatment to the image information of acquisition；
Filter unit, for being filtered processing to the image information after binary conversion treatment；
Edge detection unit, for carrying out edge detection process to the image information after filtering process；
Interest area extracting unit, for the area where determination collision thing in the image information after edge detection process
Domain；
Thing extraction unit is collided, carries out colliding thing search for the region where thing is collided, then extraction collision thing；
First range cells, for the collision thing by being extracted from the region where collision thing, measure tower crane and collision
The distance between thing.
Further, second image processor includes：
Feature point detection unit, for carrying out feature point detection to the image information of acquisition；
Stereo matching unit, depth map is obtained for carrying out Stereo matching to the image information after feature point detection；
Second range cells, according to the depth map of acquisition, the distance between measurement tower crane and collision thing.
A kind of tower crane collision-proof method based on pattern recognition technique, it is characterised in that methods described includes：
Step S1：Avoidance pattern is selected, obtains image information and tower crane movable information；
Step S2.A：When image acquiring device is monocular image acquisition device, the first avoidance pattern is selected, to acquisition
Image information carries out binaryzation, filtering, rim detection, interest extracted region, the extraction of collision thing and ranging processing successively；
Step S2.B：When image acquiring device is binocular image acquisition device, the second avoidance pattern is selected, to acquisition
Image information carries out feature point detection, Stereo matching and ranging processing successively；
Step S3：According to distance measurement result and tower crane movable information, judge whether to collide.
Further, the image information of acquisition is carried out successively in the step S2.A binaryzation, filtering, rim detection,
The method of interest extracted region, the extraction of collision thing and ranging processing includes：
Step S2.A.1：Monocular image acquisition device obtains image information；Binary conversion treatment is carried out, obtains binary picture
Picture；
Step S2.A.2：Low-pass filtering treatment is carried out to binary image, eliminates noise；
Step S2.A.3：Carry out rim detection；
Step S2.A.4：Interest extracted region is carried out, 2 lines and vanishing point intersectional region formed at edge are to be defined as
Interest region；
Step S2.A.5：Search collision thing, to being scanned from bottom to up in the regional extent of road surface in image, certain a line gray scale
Exceed one's own profession 1/6 for 255 pixel, then it is doubtful to collide thing, current line is marked, then performs step S2.A.6；
Step S2.A.7：A window is set, totalling value is asked to the number of pixels that the window intermediate value is 255, to what is obtained
As a result judged, when obtained totalling value sum divided by window gross area area result is more than or equal to a certain percentage threshold
During value T, it is believed that mainly as caused by the presence of collision thing, the window intermediate value is that 255 pixel belongs to a part for collision thing,
This explanation has been detected by frontal collisions thing, can be marked with rectangle frame, and writes down level where rectangle frame lower edge
OK, foundation is provided for following ranging；If ratio is less than T, then it is assumed that the pixel that the window intermediate value is 255, which not belongs to, touches
Hit a part for thing；At this moment the next line of picture current line must be rejudged, now next line is by as current line
Reason；
Step S2.A.8：According to the collision thing of extraction, ranging processing is carried out, obtains the distance between tower crane and collision thing.
Further, in the step S2.A, feature point detection, solid are once carried out to image
The method of matching and ranging processing includes：
Step S2.B.1：Binocular image acquisition device extracts the first image, the characteristic point of the second image, construction feature respectively
Description；
Step S2.B.2：According to Feature Descriptor and epipolar-line constraint, the Feature Points Matching of completion left and right figure；The match is successful
Characteristic point be referred to as the strong point；
Step S2.B.3：In the first image, Delaunay triangles are built according to the strong point；
Step S2.B.4：Estimate the priori parallax of the first image all pixels point；
Step S2.B.5：Calculate the priori parallax d of each pixeliCorresponding cost error Ci, obtain the institute of current iteration
There is the minimum cost error C of the strong pointmin；
Step S2.B.6：It is control point to obtain more reliable match point, some control points that reliability arrangement is ranked forefront
It is arranged to the new strong point, renewal support point set and minimum cost error Cmin
Step S2.B.7：If being unsatisfactory for iteration stopping condition, return to S4 and be iterated calculating；Otherwise stop calculating, according to
S3 and S5 obtains the disparity computation of all pixels point；
Step S2.B.8：The each pixel of the image of disparity computation first each put according to the first image is in the second image
Match point；
Step S2.B.9：After completing matching, according to obtained depth map, the distance between tower crane and collision thing are obtained.
Compared with prior art, the beneficial effects of the invention are as follows：
1st, intelligence degree is high：The tower crane collision avoidance system and method intellectuality journey based on pattern recognition technique of the present invention
Degree is higher, whole process without artificially participating in, by two image processor automatic measurements go out tower crane and collide between thing away from
From with reference to tower crane movable information, real-time alert and result being shown, automatic anticollision can be fully achieved.
2nd, accuracy is high：The tower crane collision avoidance system and method based on pattern recognition technique of the present invention, is known using image
Collision thing is identified other technology, and accuracy is higher.First image processor works in the first avoidance pattern, the second figure
Picture processor works in the second avoidance pattern, by handling image, can obtain and measure collision thing and tower
The distance of machine, then the movable information of comprehensive tower crane, can easily draw the result that whether can send collision.
3rd, applicability is wide：The tower crane collision avoidance system based on pattern recognition technique of the present invention is single in image acquiring device
During mesh, the image information of acquisition can be handled by the first image processor；, can when image acquiring device is binocular
To be handled by the second image processor the image information of acquisition.Relatively simple, the environment in tower crane local environment situation
In the case that middle collision thing is less, directly handled using the first image processor；It is more multiple in environmental aspect described in tower crane
It is miscellaneous, two images are obtained using binocular image acquisition device, recycle the second image processor to be handled, it is as a result more accurate
Really.For different situations, the system has preferable applicability.The tower crane anticollision side based on pattern recognition technique of the present invention
Method has the advantages of same.
Brief description of the drawings
Fig. 1 is a kind of system structure diagram of tower crane collision avoidance system based on pattern recognition technique of the present invention；
Fig. 2 is a kind of the first image processor structure of tower crane collision avoidance system based on pattern recognition technique of the present invention
Schematic diagram；
Fig. 3 is a kind of the second image processor structure of tower crane collision avoidance system based on pattern recognition technique of the present invention
Schematic diagram；
Fig. 4 is a kind of method structural representation of tower crane collision-proof method based on pattern recognition technique of the present invention.
Wherein, S10- image acquiring devices, the image processors of S11- first, the image processors of S12- second, S13- sensings
Device group, S14- control processors, S15- display devices, S16- data communication equipments, S17- warning devices, S20- binaryzation lists
Member, S21- filter units, S22- edge detection units, S23- interest area extracting units, S24- collision thing extraction units, S25-
First range cells, S31- feature point detection units, S32- Stereo matching units, the range cells of S33- second, S41- steps
S1, S42- step S2.A, S43- step S2.B, S44- step S3.
Embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Generally exist
The component of the embodiment of the present invention described and illustrated in accompanying drawing can be configured to arrange and design with a variety of herein.Cause
This, the detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit claimed invention below
Scope, but it is merely representative of the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not doing
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent accompanying drawing in individual accompanying drawing.Meanwhile the present invention's
In description, term " first ", " second " etc. are only used for distinguishing description, and it is not intended that instruction or hint relative importance.
The embodiment of the present invention 1 provides a kind of tower crane collision avoidance system based on pattern recognition technique, and system construction drawing is such as
Shown in Fig. 1, the structure chart of the first image processor is as shown in Fig. 2 the structure chart of the second image processor is as shown in Figure 3：
A kind of tower crane collision avoidance system based on pattern recognition technique, it is characterised in that the system includes：
Image acquiring device, for obtaining image information；
First image processor, for by carrying out binaryzation, filtering, rim detection, interest region to the image of acquisition
Extraction and collision thing extraction process, complete ranging, distance measurement result are sent into control processor；
Second image processor, for by carrying out feature point detection and Stereo matching processing to the image of acquisition, completing
Ranging, distance measurement result is sent to control processor；
Sensor group, for obtaining tower crane movable information；
Control processor, for judging whether to collide according to distance measurement result and tower crane movable information；Judging meeting
In the case of colliding, alarm command is sent；
Warning device, for the alarm command alert sent according to control processor.
Further, described image acquisition device is monocular and/or binocular image acquisition device.
Specifically, after monocular image acquisition device obtains image information, it is sent to the first image processor and is handled；It is double
After mesh image acquiring device obtains image information, it is sent to the second image processor and is handled.
Further, the system also includes：
Display device, the tower crane that the image information obtained for display image acquisition device, sensor group obtain move letter
The alarm command that breath and control processor are sent；
Data communication equipment, for completing the data communication put between collision system and exterior terminal.
The display device can be display；The data communication equipment is：Wireless data communication device and/or wired
Data communication equipment.
Further, the sensor group includes：
Weight sensor, obtain lift heavy information；
Air velocity transducer, obtain wind speed information；
Amplitude sensor, for obtaining dolly amplitude information；
Height sensor, for obtaining tower crane elevation information；
Angle of revolution sensor, for obtaining big boom slew information.
Specifically, the weight sensor at least one；The air velocity transducer at least one；The amplitude sensing
Device at least one；The height sensor at least one；The angle of revolution sensor at least one.
Further, described first image processor includes：
Binarization unit, for carrying out binary conversion treatment to the image information of acquisition；
Filter unit, for being filtered processing to the image information after binary conversion treatment；
Edge detection unit, for carrying out edge detection process to the image information after filtering process；
Interest area extracting unit, for the area where determination collision thing in the image information after edge detection process
Domain；
Thing extraction unit is collided, carries out colliding thing search for the region where thing is collided, then extraction collision thing；
First range cells, for the collision thing by being extracted from the region where collision thing, measure tower crane and collision
The distance between thing.
Further, second image processor includes：
Feature point detection unit, for carrying out feature point detection to the image information of acquisition；
Stereo matching unit, depth map is obtained for carrying out Stereo matching to the image information after feature point detection；
Second range cells, according to the depth map of acquisition, the distance between measurement tower crane and collision thing.
The embodiment of the present invention 2 provides a kind of tower crane collision-proof method based on pattern recognition technique, and method flow diagram is such as
Shown in Fig. 4：
A kind of tower crane collision-proof method based on pattern recognition technique, it is characterised in that methods described includes：
Step S1：Avoidance pattern is selected, obtains image information and tower crane movable information；
Step S2.A：When image acquiring device is monocular image acquisition device, the first avoidance pattern is selected, to acquisition
Image information carries out binaryzation, filtering, rim detection, interest extracted region, the extraction of collision thing and ranging processing successively；
Step S2.B：When image acquiring device is binocular image acquisition device, the second avoidance pattern is selected, to acquisition
Image information carries out feature point detection, Stereo matching and ranging processing successively；
Step S3：According to distance measurement result and tower crane movable information, judge whether to collide.
Specifically, in step S1 select avoidance pattern method for：It is artificial to input avoidance pattern by external input device
Instruct control processor；The avoidance mode instruction is sent to various pieces in system and performed by control processor.
Specifically, image information is obtained by image acquiring device in step S1；Tower crane is obtained by sensor group to move
Information.
Specifically, step S2.A can be performed by the first image processor；Step S2.B can be by the second image at
Device is managed to perform；Step S3 can be performed by control processor.
Further, the image information of acquisition is carried out successively in the step S2.A binaryzation, filtering, rim detection,
The method of interest extracted region, the extraction of collision thing and ranging processing includes：
Step S2.A.1：Monocular image acquisition device obtains image information；Binary conversion treatment is carried out, obtains binary picture
Picture；
Step S2.A.2：Low-pass filtering treatment is carried out to binary image, eliminates noise；
Step S2.A.3：Carry out rim detection；
Step S2.A.4：Interest extracted region is carried out, 2 lines and vanishing point intersectional region formed at edge are to be defined as
Interest region；
Step S2.A.5：Search collision thing, to being scanned from bottom to up in the regional extent of road surface in image, certain a line gray scale
Exceed one's own profession 1/6 for 255 pixel, then it is doubtful to collide thing, current line is marked, then performs step S2.A.6；
Step S2.A.6：A window is set, totalling value is asked to the number of pixels that the window intermediate value is 255, to what is obtained
As a result judged, when obtained totalling value sum divided by window gross area area result is more than or equal to a certain percentage threshold
During value T, it is believed that mainly as caused by the presence of collision thing, the window intermediate value is that 255 pixel belongs to a part for collision thing,
This explanation has been detected by frontal collisions thing, can be marked with rectangle frame, and writes down level where rectangle frame lower edge
OK, foundation is provided for following ranging；If ratio is less than T, then it is assumed that the pixel that the window intermediate value is 255, which not belongs to, touches
Hit a part for thing；At this moment the next line of picture current line must be rejudged, now next line is by as current line
Reason；
Step S2.A.7：According to the collision thing of extraction, ranging processing is carried out, obtains the distance between tower crane and collision thing.
Specifically, step S2.A.1 can be performed by binarization unit；Step S2.A.2 can be held by filter unit
OK；Step S2.A.3 can be performed by edge detection unit；Step S2.A.4 can be held by interest area extracting unit
OK；Step S2.A.5 and S2.A.6 can be performed by colliding thing extraction unit；Step S2.A.7 can pass through the first ranging list
Member performs.
Further, in the step S2.A, feature point detection, solid are once carried out to image
The method of matching and ranging processing includes：
Step S2.B.1：Binocular image acquisition device extracts the first image, the characteristic point of the second image, construction feature respectively
Description；
Step S2.B.2：According to Feature Descriptor and epipolar-line constraint, the Feature Points Matching of completion left and right figure；The match is successful
Characteristic point be referred to as the strong point；
Step S2.B.3：In the first image, Delaunay triangles are built according to the strong point；
Step S2.B.4：Estimate the priori parallax of the first image all pixels point；
Step S2.B.5：Calculate the priori parallax d of each pixeliCorresponding cost error Ci, obtain the institute of current iteration
There is the minimum cost error C of the strong pointmin；
Step S2.B.6：It is control point to obtain more reliable match point, some control points that reliability arrangement is ranked forefront
It is arranged to the new strong point, renewal support point set and minimum cost error Cmin
Step S2.B.7：If being unsatisfactory for iteration stopping condition, return to S4 and be iterated calculating；Otherwise stop calculating, according to
S3 and S5 obtains the disparity computation of all pixels point；
Step S2.B.8：The each pixel of the image of disparity computation first each put according to the first image is in the second image
Match point；
Step S2.B.9：After completing matching, according to obtained depth map, the distance between tower crane and collision thing are obtained.
Specifically, step S2.B.1 can pass through the execution of feature point detection unit；Step S2.B.2, step S2.B.3,
Step S2.B.4, step S2.B.5, step S2.B.6, step S2.B.7, step S2.B.8 can be held by Stereo matching unit
OK；Step S2.B.9 can be performed by the second range cells.
The embodiment of the present invention 3 provides a kind of tower crane collision avoidance system based on pattern recognition technique, and system construction drawing is such as
Shown in Fig. 1, the structure chart of the first image processor as shown in Fig. 2 the structure chart of the second image processor as shown in figure 3, method
Flow chart is as shown in Figure 4：
A kind of tower crane collision avoidance system based on pattern recognition technique, it is characterised in that the system includes：
Image acquiring device, for obtaining image information；
First image processor, for by carrying out binaryzation, filtering, rim detection, interest region to the image of acquisition
Extraction and collision thing extraction process, complete ranging, distance measurement result are sent into control processor；
Second image processor, for by carrying out feature point detection and Stereo matching processing to the image of acquisition, completing
Ranging, distance measurement result is sent to control processor；
Sensor group, for obtaining tower crane movable information；
Control processor, for judging whether to collide according to distance measurement result and tower crane movable information；Judging meeting
In the case of colliding, alarm command is sent；
Warning device, for the alarm command alert sent according to control processor.
Further, described image acquisition device is monocular and/or binocular image acquisition device.
Specifically, after monocular image acquisition device obtains image information, it is sent to the first image processor and is handled；It is double
After mesh image acquiring device obtains image information, it is sent to the second image processor and is handled.
Further, the system also includes：
Display device, the tower crane that the image information obtained for display image acquisition device, sensor group obtain move letter
The alarm command that breath and control processor are sent；
Data communication equipment, for completing the data communication put between collision system and exterior terminal.
The display device can be display；The data communication equipment is：Wireless data communication device and/or wired
Data communication equipment.
Further, the sensor group includes：
Weight sensor, obtain lift heavy information；
Air velocity transducer, obtain wind speed information；
Amplitude sensor, for obtaining dolly amplitude information；
Height sensor, for obtaining tower crane elevation information；
Angle of revolution sensor, for obtaining big boom slew information.
Specifically, the weight sensor at least one；The air velocity transducer at least one；The amplitude sensing
Device at least one；The height sensor at least one；The angle of revolution sensor at least one.
Further, described first image processor includes：
Binarization unit, for carrying out binary conversion treatment to the image information of acquisition；
Filter unit, for being filtered processing to the image information after binary conversion treatment；
Edge detection unit, for carrying out edge detection process to the image information after filtering process；
Interest area extracting unit, for the area where determination collision thing in the image information after edge detection process
Domain；
Thing extraction unit is collided, carries out colliding thing search for the region where thing is collided, then extraction collision thing；
First range cells, for the collision thing by being extracted from the region where collision thing, measure tower crane and collision
The distance between thing.
Further, second image processor includes：
Feature point detection unit, for carrying out feature point detection to the image information of acquisition；
Stereo matching unit, depth map is obtained for carrying out Stereo matching to the image information after feature point detection；
Second range cells, according to the depth map of acquisition, the distance between measurement tower crane and collision thing.
A kind of tower crane collision-proof method based on pattern recognition technique, it is characterised in that methods described includes：
Step S1：Avoidance pattern is selected, obtains image information and tower crane movable information；
Step S2.A：When image acquiring device is monocular image acquisition device, the first avoidance pattern is selected, to acquisition
Image information carries out binaryzation, filtering, rim detection, interest extracted region, the extraction of collision thing and ranging processing successively；
Step S2.B：When image acquiring device is binocular image acquisition device, the second avoidance pattern is selected, to acquisition
Image information carries out feature point detection, Stereo matching and ranging processing successively；
Step S3：According to distance measurement result and tower crane movable information, judge whether to collide.
Specifically, in step S1 select avoidance pattern method for：It is artificial to input avoidance pattern by external input device
Instruct control processor；The avoidance mode instruction is sent to various pieces in system and performed by control processor.
Specifically, image information is obtained by image acquiring device in step S1；Tower crane is obtained by sensor group to move
Information.
Specifically, step S2.A can be performed by the first image processor；Step S2.B can be by the second image at
Device is managed to perform；Step S3 can be performed by control processor.
Further, the image information of acquisition is carried out successively in the step S2.A binaryzation, filtering, rim detection,
The method of interest extracted region, the extraction of collision thing and ranging processing includes：
Step S2.A.1：Monocular image acquisition device obtains image information；Binary conversion treatment is carried out, obtains binary picture
Picture；
Step S2.A.2：Low-pass filtering treatment is carried out to binary image, eliminates noise；
Step S2.A.3：Carry out rim detection；
Step S2.A.4：Interest extracted region is carried out, 2 lines and vanishing point intersectional region formed at edge are to be defined as
Interest region；
Step S2.A.5：Search collision thing, to being scanned from bottom to up in the regional extent of road surface in image, certain a line gray scale
Exceed one's own profession 1/6 for 255 pixel, then it is doubtful to collide thing, current line is marked, then performs step S2.A.6；
Step S2.A.6：A window is set, totalling value is asked to the number of pixels that the window intermediate value is 255, to what is obtained
As a result judged, when obtained totalling value sum divided by window gross area area result is more than or equal to a certain percentage threshold
During value T, it is believed that mainly as caused by the presence of collision thing, the window intermediate value is that 255 pixel belongs to a part for collision thing,
This explanation has been detected by frontal collisions thing, can be marked with rectangle frame, and writes down level where rectangle frame lower edge
OK, foundation is provided for following ranging；If ratio is less than T, then it is assumed that the pixel that the window intermediate value is 255, which not belongs to, touches
Hit a part for thing；At this moment the next line of picture current line must be rejudged, now next line is by as current line
Reason；
Step S2.A.7：According to the collision thing of extraction, ranging processing is carried out, obtains the distance between tower crane and collision thing.
Specifically, step S2.A.1 can be performed by binarization unit；Step S2.A.2 can be held by filter unit
OK；Step S2.A.3 can be performed by edge detection unit；Step S2.A.4 can be held by interest area extracting unit
OK；Step S2.A.5 and S2.A.6 can be performed by colliding thing extraction unit；Step S2.A.7 can pass through the first ranging list
Member performs.
Further, in the step S2.A, feature point detection, solid are once carried out to image
The method of matching and ranging processing includes：
Step S2.B.1：Binocular image acquisition device extracts the first image, the characteristic point of the second image, construction feature respectively
Description；
Step S2.B.2：According to Feature Descriptor and epipolar-line constraint, the Feature Points Matching of completion left and right figure；The match is successful
Characteristic point be referred to as the strong point；
Step S2.B.3：In the first image, Delaunay triangles are built according to the strong point；
Step S2.B.4：Estimate the priori parallax of the first image all pixels point；
Step S2.B.5：Calculate the priori parallax d of each pixeliCorresponding cost error Ci, obtain the institute of current iteration
There is the minimum cost error C of the strong pointmin；
Step S2.B.6：It is control point to obtain more reliable match point, some control points that reliability arrangement is ranked forefront
It is arranged to the new strong point, renewal support point set and minimum cost error Cmin
Step S2.B.7：If being unsatisfactory for iteration stopping condition, return to S4 and be iterated calculating；Otherwise stop calculating, according to
S3 and S5 obtains the disparity computation of all pixels point；
Step S2.B.8：The each pixel of the image of disparity computation first each put according to the first image is in the second image
Match point；
Step S2.B.9：After completing matching, according to obtained depth map, the distance between tower crane and collision thing are obtained.
Specifically, step S2.B.1 can pass through the execution of feature point detection unit；Step S2.B.2, step S2.B.3,
Step S2.B.4, step S2.B.5, step S2.B.6, step S2.B.7, step S2.B.8 can be held by Stereo matching unit
OK；Step S2.B.9 can be performed by the second range cells.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, can also pass through
Other modes are realized.Device embodiment described above is only schematical, for example, flow chart and block diagram in accompanying drawing
Show the device of multiple embodiments according to the present invention, method and computer program product architectural framework in the cards,
Function and operation.At this point, each square frame in flow chart or block diagram can represent the one of a module, program segment or code
Part, a part for the module, program segment or code include one or more and are used to realize holding for defined logic function
Row instruction.It should also be noted that at some as in the implementation replaced, the function that is marked in square frame can also with different from
The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially perform substantially in parallel, they are sometimes
It can perform in the opposite order, this is depending on involved function.It is it is also noted that every in block diagram and/or flow chart
The combination of individual square frame and block diagram and/or the square frame in flow chart, function or the special base of action as defined in performing can be used
Realize, or can be realized with the combination of specialized hardware and computer instruction in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need
Illustrate, herein, such as first and second or the like relational terms be used merely to by an entity or operation with
Another entity or operation make a distinction, and not necessarily require or imply between these entities or operation any this reality be present
The relation or order on border.Moreover, term " comprising ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that process, method, article or equipment including a series of elements not only include those key elements, but also including
The other element being not expressly set out, or also include for this process, method, article or the intrinsic key element of equipment.
In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including the key element
Process, method, other identical element also be present in article or equipment.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.It should be noted that：Similar label and letter exists
Similar terms is represented in following accompanying drawing, therefore, once being defined in a certain Xiang Yi accompanying drawing, is then not required in subsequent accompanying drawing
It is further defined and explained.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (9)
1. a kind of tower crane collision avoidance system based on pattern recognition technique, it is characterised in that the system includes：
Image acquiring device, for obtaining image information；
First image processor, for by carrying out binaryzation, filtering, rim detection, interest extracted region to the image of acquisition
With collision thing extraction process, ranging is completed, distance measurement result is sent to control processor；
Second image processor, for by carrying out feature point detection to the image of acquisition and Stereo matching is handled, completing ranging,
Distance measurement result is sent to control processor；
Sensor group, for obtaining tower crane movable information；
Control processor, for judging whether to collide according to distance measurement result and tower crane movable information；Judging to occur
In the case of collision, alarm command is sent；
Warning device, for the alarm command alert sent according to control processor.
2. the tower crane collision avoidance system based on pattern recognition technique as claimed in claim 1, it is characterised in that described image obtains
It is monocular and/or binocular image acquisition device to take device.
3. the tower crane based on image recognition technology puts collision system as claimed in claim 2, it is characterised in that the system is also
Including：
Display device, for display image acquisition device obtain image information, sensor group obtain tower crane movable information and
The alarm command that control processor is sent；
Data communication equipment, for completing the data communication put between collision system and exterior terminal.
4. the tower crane collision avoidance system based on image recognition technology as claimed in claim 2, it is characterised in that the sensor
Group includes：
Weight sensor, for obtaining lift heavy information；
Air velocity transducer, for obtaining wind speed information；
Amplitude sensor, for obtaining dolly amplitude information；
Height sensor, for obtaining tower crane elevation information；
Angle of revolution sensor, for obtaining big boom slew information.
5. the tower crane collision avoidance system based on image recognition technology as claimed in claim 4, it is characterised in that first figure
As processor includes：
Binarization unit, for carrying out binary conversion treatment to the image information of acquisition；
Filter unit, for being filtered processing to the image information after binary conversion treatment；
Edge detection unit, for carrying out edge detection process to the image information after filtering process；
Interest area extracting unit, for the region where determination collision thing in the image information after edge detection process；
Thing extraction unit is collided, carries out colliding thing search for the region where thing is collided, then extraction collision thing；
First range cells, for by the collision thing that extracts from the region where collision thing, measurement tower crane and collision thing it
Between distance.
6. the tower crane collision avoidance system based on image recognition technology as claimed in claim 4, it is characterised in that second figure
As processor includes：
Feature point detection unit, for carrying out feature point detection to the image information of acquisition；
Stereo matching unit, depth map is obtained for carrying out Stereo matching to the image information after feature point detection；
Second range cells, according to the depth map of acquisition, the distance between measurement tower crane and collision thing.
7. a kind of tower crane collision-proof method based on pattern recognition technique, it is characterised in that methods described includes：
Step S1：Avoidance pattern is selected, obtains image information and tower crane movable information；
Step S2.A：When image acquiring device is monocular image acquisition device, the first avoidance pattern is selected, to the image of acquisition
Information carries out binaryzation, filtering, rim detection, interest extracted region, the extraction of collision thing and ranging processing successively；
Step S2.B：When image acquiring device is binocular image acquisition device, the second avoidance pattern is selected, to the image of acquisition
Information carries out feature point detection, Stereo matching and ranging processing successively；
Step S3：According to distance measurement result and tower crane movable information, judge whether to collide.
8. the tower crane collision avoidance system based on pattern recognition technique as claimed in claim 7, it is characterised in that the step
The image information of acquisition is carried out successively in S2.A binaryzation, filtering, rim detection, interest extracted region, the extraction of collision thing and
The method of ranging processing includes：
Step S2.A.1：Monocular image acquisition device obtains image information；Binary conversion treatment is carried out, obtains binary image；
Step S2.A.2：Low-pass filtering treatment is carried out to binary image, eliminates noise；
Step S2.A.3：Carry out rim detection；
Step S2.A.4：Interest extracted region is carried out, 2 lines and vanishing point intersectional region formed at edge are to be defined as interest
Region；
Step S2.A.5：Search collision thing, to being scanned from bottom to up in the regional extent of road surface in image, certain a line gray scale is 255
Pixel exceed one's own profession 1/6, then it is doubtful for collision thing, mark current line, then perform step S2.A.6；
Step S2.A.7：A window is set, totalling value is asked to the number of pixels that the window intermediate value is 255, to obtained result
Judged, when obtained totalling value sum divided by window gross area area result is more than or equal to a certain percentage threshold T
When, it is believed that mainly as caused by the presence of collision thing, the window intermediate value is that 255 pixel belongs to a part for collision thing, this
Illustrate to have been detected by frontal collisions thing, can be marked with rectangle frame, and write down horizontal line where rectangle frame lower edge,
Foundation is provided for following ranging；If ratio is less than T, then it is assumed that the pixel that the window intermediate value is 255 not belongs to collision thing
A part；At this moment the next line of picture current line must be rejudged, now next line is handled as current line；
Step S2.A.8：According to the collision thing of extraction, ranging processing is carried out, obtains the distance between tower crane and collision thing.
9. the tower crane collision avoidance system based on pattern recognition technique as claimed in claim 7, it is characterised in that the step
In S2.A, the method for feature point detection, Stereo matching and ranging processing is once carried out to image to be included：
Step S2.B.1：Binocular image acquisition device extracts the first image, the characteristic point of the second image, construction feature description respectively
Son；
Step S2.B.2：According to Feature Descriptor and epipolar-line constraint, the Feature Points Matching of completion left and right figure；The spy that the match is successful
Sign point is referred to as the strong point；
Step S2.B.3：In the first image, Delaunay triangles are built according to the strong point；
Step S2.B.4：Estimate the priori parallax of the first image all pixels point；
Step S2.B.5：Calculate the priori parallax d of each pixeliCorresponding cost error Ci, obtain all of current iteration
The minimum cost error C of support pointmin；
Step S2.B.6：It is control point to obtain more reliable match point, and some control points that reliability arrangement ranks forefront are set
For the new strong point, renewal support point set and minimum cost error Cmin
Step S2.B.7：If being unsatisfactory for iteration stopping condition, return to S4 and be iterated calculating；Otherwise stop calculating, according to S3 and
S5 obtains the disparity computation of all pixels point；
Step S2.B.8：Of each pixel of the image of disparity computation first each put according to the first image in the second image
With point；
Step S2.B.9：After completing matching, according to obtained depth map, the distance between tower crane and collision thing are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710718255.5A CN107480645A (en) | 2017-08-21 | 2017-08-21 | A kind of tower crane collision avoidance system and method based on pattern recognition technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710718255.5A CN107480645A (en) | 2017-08-21 | 2017-08-21 | A kind of tower crane collision avoidance system and method based on pattern recognition technique |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107480645A true CN107480645A (en) | 2017-12-15 |
Family
ID=60600991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710718255.5A Withdrawn CN107480645A (en) | 2017-08-21 | 2017-08-21 | A kind of tower crane collision avoidance system and method based on pattern recognition technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107480645A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753894A (en) * | 2018-12-19 | 2019-05-14 | 国网北京市电力公司 | Alarm method and device |
| CN110414458A (en) * | 2019-08-01 | 2019-11-05 | 北京主线科技有限公司 | Localization method and device based on planar tags and template matching |
| CN111170161A (en) * | 2019-12-28 | 2020-05-19 | 王昆 | Mode setting system based on scene detection |
| CN117105097A (en) * | 2023-10-23 | 2023-11-24 | 杭州未名信科科技有限公司 | Intelligent tower crane control system, method and control equipment |
-
2017
- 2017-08-21 CN CN201710718255.5A patent/CN107480645A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753894A (en) * | 2018-12-19 | 2019-05-14 | 国网北京市电力公司 | Alarm method and device |
| CN110414458A (en) * | 2019-08-01 | 2019-11-05 | 北京主线科技有限公司 | Localization method and device based on planar tags and template matching |
| CN110414458B (en) * | 2019-08-01 | 2022-03-08 | 北京主线科技有限公司 | Positioning method and device based on matching of plane label and template |
| CN111170161A (en) * | 2019-12-28 | 2020-05-19 | 王昆 | Mode setting system based on scene detection |
| CN117105097A (en) * | 2023-10-23 | 2023-11-24 | 杭州未名信科科技有限公司 | Intelligent tower crane control system, method and control equipment |
| CN117105097B (en) * | 2023-10-23 | 2024-04-02 | 杭州未名信科科技有限公司 | Intelligent tower crane control system, method and control equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107480645A (en) | A kind of tower crane collision avoidance system and method based on pattern recognition technique | |
| Vu et al. | Multi-scale solution for building extraction from LiDAR and image data | |
| CN110443093B (en) | Intelligent-oriented infrared digital panoramic system and warehouse management method thereof | |
| CN106593534A (en) | Intelligent tunnel construction security monitoring system | |
| CN102768022B (en) | Tunnel surrounding rock deformation detection method adopting digital camera technique | |
| CN112395978A (en) | Behavior detection method and device and computer readable storage medium | |
| CN112883820B (en) | Road target 3D detection method and system based on laser radar point cloud | |
| CN106097755A (en) | For identifying the method parked place and/or vacate place | |
| CN102999886B (en) | Image Edge Detector and scale grating grid precision detection system | |
| CN101329402B (en) | Multi-dimension SAR image edge detection method based on improved Wedgelet | |
| CN108364466A (en) | A kind of statistical method of traffic flow based on unmanned plane traffic video | |
| CN111429698A (en) | Geological disaster early warning system | |
| CN112766069A (en) | Vehicle illegal parking detection method and device based on deep learning and electronic equipment | |
| CN104183142A (en) | Traffic flow statistics method based on image visual processing technology | |
| CN115392407B (en) | Non-supervised learning-based danger source early warning method, device, equipment and medium | |
| CN114495421B (en) | Intelligent open type road construction operation monitoring and early warning method and system | |
| CN116626706A (en) | Rail transit tunnel intrusion detection method and system | |
| CN114998855A (en) | Road edge line generation method and device, storage medium and computer equipment | |
| CN104331708B (en) | A kind of zebra crossing automatic detection analysis method and system | |
| CN104063884B (en) | The images steganalysis method being combined based on motion prediction with multi-template matching | |
| CN112734807A (en) | Method for automatically tracking plate blank on continuous casting roller way based on computer vision | |
| CN115830447A (en) | Intelligent supervision method, system and device for super high-rise building safety construction | |
| CN116579608A (en) | Safety prevention and control method and system for wind early warning period of road bridge station | |
| CN115289991B (en) | Subway track deformation monitoring method and device and electronic equipment | |
| CN114092805B (en) | Machine dog crack identification method based on building model |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171215 |