CN112053324A - Complex material volume measurement method based on deep learning - Google Patents
Complex material volume measurement method based on deep learning Download PDFInfo
- Publication number
- CN112053324A CN112053324A CN202010766575.XA CN202010766575A CN112053324A CN 112053324 A CN112053324 A CN 112053324A CN 202010766575 A CN202010766575 A CN 202010766575A CN 112053324 A CN112053324 A CN 112053324A
- Authority
- CN
- China
- Prior art keywords
- volume
- stack
- image
- deep learning
- complex material
- 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
- 239000011365 complex material Substances 0.000 title claims abstract description 26
- 238000000691 measurement method Methods 0.000 title claims abstract description 8
- 238000013135 deep learning Methods 0.000 title claims description 14
- 239000000463 material Substances 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 26
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000007547 defect Effects 0.000 abstract description 2
- 239000002893 slag Substances 0.000 abstract 2
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000010420 art technique Methods 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003818 cinder Substances 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- -1 earthwork Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Computational Linguistics (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computer Graphics (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a complex material volume measurement method based on depth learning, which is characterized in that a complex material stack object has no obvious characteristic point, a binocular vision camera is adopted to collect multi-angle visual field images above the stack, depth information of the images collected by a left camera and a right camera is subjected to fitting sampling through the relevance between the images, a three-dimensional model of a characteristic space of the images is restored, volume calculation is rapidly carried out, and the volume is recorded into a system. The binocular system overcomes the defect that a common industrial camera cannot acquire pile depth information, does not use an energy loss caused by the fact that a structured light technology measuring method and the like need to emit special modulating waves for measurement, is associated with a recording system, and links the volume rapid automatic measurement with the whole recording management system, so that the volume measurement and management of the pile of the complicated slag materials are intelligentized, the precision and the efficiency of the volume measurement of the earthwork are improved, a large amount of manpower and material resources are saved, and the volume measurement, the recording and management processes of the pile of the complicated slag materials are simple and convenient.
Description
Technical Field
The invention belongs to the field of volume measurement, and particularly relates to a complex material volume measurement method based on deep learning.
Background
At present, the traditional method for collecting the volume of the earthwork transported by the muck truck mainly adopts manual estimation and measurement, and the method has large workload and cannot dynamically measure the earthwork in real time. With the development of science and technology, the traditional manual estimation method cannot meet the requirements of the accuracy and the efficiency of the material volume measurement at present. Modern measurement technology requires high precision, high speed, good flexibility and universality, so that the research of new measurement technology is more and more emphasized by people. For different application requirements, various measuring devices have been developed in the prior art: the three-coordinate measuring machine adopts a traditional contact measuring head, and the measuring head is required to be in contact with the surface of an object during measurement, so that the measurement efficiency is greatly limited; the mechanical measuring arm adopts the measuring principle of a coordinate measuring machine, overcomes the defect of complex control of the coordinate measuring machine to a certain extent, but cannot be separated from manual operation in the measuring process, is difficult to finish manual measurement of a large stack body, and cannot meet the requirement of rapid measurement; the radar range finder mainly utilizes the characteristics of reflection, absorption and the like of an object to signals to enable the signals to be modulated by the object, then calculates the information of the measured object by analyzing the modulated signals, but the radar signals are limited by distance and obstacles, if the measuring distance is too long or an obstacle exists between a transmitter and the measured object, the transmitted signals of the radar are weakened, and the measuring precision and efficiency are greatly influenced. Although these devices are characterized, they are not only difficult to operate due to various factors, but also are only suitable for some specific occasions, are easily interfered by the outside, and cannot ensure the accuracy of volume calculation and measurement when used outdoors.
These prior art techniques have the following disadvantages:
1) the manual estimation of the volume of the complex material pile is low in efficiency, poor in precision, and many in restricted and influenced factors, and the deviation of the estimation result from the real volume is large due to interference factors;
2) in the traditional contact measuring head measuring method, the measuring head is required to be in contact with the surface of an object during measurement, so that the measuring efficiency and the application scene are greatly limited;
3) the method for transmitting the modulation signal (such as structured light and TOF technology) has higher requirements on application environment, more outdoor interference, unstable signal energy transmitted for a long time and uneven measurement effect;
4) the existing measuring method such as a contact head type measuring method cannot be completely automatic without manual work, has low working efficiency and cannot meet the speed and precision expected by practical application.
Disclosure of Invention
At present, the traditional method for calculating the volume of the material pile mainly adopts manual estimation and measurement, for example, when a muck vehicle enters a construction site, the muck vehicle stops for manual inspection, relevant personnel in a duty room or an entrance and exit gate records the license plate number, and then the earthwork transported by the muck vehicle is manually estimated; the method has the advantages of large workload, long time consumption, low efficiency and poor timeliness, and specific materials of the material body cannot be well observed and recorded. With the development of science and technology, the traditional manual estimation method cannot meet the current requirements on the accuracy and speed of the measurement of the volume of the complex material pile. The invention researches a quick, effective, simple and feasible complex material stack volume measuring method with low labor intensity based on machine vision, calculates the volume of the complex material stack, and adopts the following specific scheme:
a complex material volume measurement method based on deep learning comprises the following steps:
s1, collecting multi-angle visual field images above the pile body by using a binocular vision camera positioned above the pile body, and combining images collected by the two cameras to obtain a 2D image and 3D depth information of the pile body;
s2, carrying out data transmission on the binocular vision camera and the GPU embedded system, and transmitting the acquired image data to a GPU embedded system host;
s3, the GPU embedded system carries out image preprocessing on the collected image, combines the 2D image characteristics and the 3D depth information obtained by the two cameras, and then completes the three-dimensional reconstruction of the whole stack according to the camera calibration parameter information;
s4, performing region selection and interception on a pile image in the acquired image by using a feature point matching-based method through a deep learning network, performing fitting sampling on depth information of the selected region, completing calculation of the pile volume of the complex material and determining the material type in the image through GPU (graphics processing unit) accelerated operation, and meanwhile performing cloud database identification on the acquired image data to identify the current material type;
s5, comparing the specific material information of the material stack with the pre-stored material types, then corresponding the specific material information with the calculated volume value, and recording the volume value into the management system to complete the whole stack volume calculation and material type information acquisition process.
Furthermore, when the binocular vision camera is used for the first time, the distortion is manually eliminated, and then the image is collected above the material pile.
Further, in step S1, an annular guide rail is disposed around the stack to enclose the stack therein, a slider is disposed on the annular guide rail, the binocular vision camera is fixed on the slider through a swing arm, and the slider drives the binocular vision camera to perform a circle motion around the stack, so as to simultaneously capture two-angle view images above the stack.
Further, step S3 specifically includes:
s31, intercepting the heap image based on the feature point matching of the point cloud depth information, and then preprocessing the point cloud;
and S32, fitting and sampling the depth information of the selected area to complete the three-dimensional reconstruction of the whole stack.
Furthermore, the purpose of splicing and fusing the visual fields is achieved through the relevance between the two images or the parallax relation between the visual fields and the acceleration of a GPU (graphics processing unit) display card, and the 3D morphology of the target stack body characteristic space is restored.
Further, in step S5, the stack volume calculation and the medium determination are completed by extracting the calculated volume-related numerical information and the material medium characteristic information.
The invention has the advantages that:
(1) utilize the binocular camera to carry out the image acquisition of complicated material pile, can not only extract the depth information and the surface material information that the plane camera can't gather, still avoided the pile volume too big can't gather completely and the error that causes.
(2) The information collected by the binocular camera is subjected to fitting sampling through the preset deep learning network, the three-dimensional model of the complex material pile is restored, the volume calculation is carried out, the manual detection error is avoided, and the efficiency and the precision of the volume measurement of the complex material pile are greatly improved.
(3) Through the matching of the collected surface medium information of the stack body and the preset information in the library, the material medium is obtained and is input into the system, so that the stack body information is more perfect, the management and the input are more facilitated, and the volume measurement and management record bone of the whole stack body is simple and convenient.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flow chart of the present invention;
fig. 2 is a schematic diagram of the binocular vision camera of the present invention acquiring 2D images and 3D depth information of a stack.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art, that the present invention may be practiced without one or more of these specific details. In other instances, well-known features have not been described in order to avoid obscuring the invention.
In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The following detailed description of the preferred embodiments of the invention, however, the invention is capable of other embodiments in addition to those detailed.
At present, the most commonly applied method in the measurement method of applying machine vision to the volume of a material stack is generally the following two types: one is a measuring method based on monocular vision, and the other is a measuring method using a modulated wave technique. The application range of monocular vision is only limited to small-size or plane objects, and when the modulated wave technology is applied to a large material pile, the problems of long-distance signal energy loss and incapability of taking a full view of the material pile exist in the image acquisition process, and the limitations limit that the monocular vision and the modulated wave technology cannot measure the size of the large material pile outdoors. This patent adopts the binocular camera to gather the image of complicated material heap body top, uses the 3D appearance of binocular vision reduction complicated material heap body, utilizes the data that reachs after the reduction to calculate the heap body volume.
According to the invention, a binocular vision camera is adopted to collect multi-angle visual field images above a pile body according to the characteristic that a complicated material pile body target has no obvious characteristic point, depth information of the images collected by a left camera and a right camera is subjected to fitting sampling through the correlation between the images, a three-dimensional model of a characteristic space of the images is restored, volume calculation is rapidly carried out, the type of a medium is determined, and the medium is recorded into a system. The system automates and intelligentizes the volume measurement of the whole complex material pile, improves the precision and efficiency of the volume measurement of the complex material pile, saves a large amount of manpower and material resources, and makes the measurement and recording process become simple and convenient. Referring to fig. 1, the specific process is as follows:
and S1, pouring the materials (such as earthwork, coal cinder and the like) to gradually accumulate, and sending a signal by the photoelectric sensor to trigger the binocular camera to work after the materials stop pouring and the pile body is completely formed. The method comprises the steps that self-configuration initialization is carried out on a binocular camera based on pre-set parameters, distortion is manually eliminated during first use, then image acquisition is carried out on the upper portion of a material pile body, a 2D image and 3D depth information of the upper portion of the pile body are obtained, the 2D image is obtained by a left camera and a right camera respectively, and the 3D depth information is synthesized according to 2D;
s2, the binocular vision camera carries out data transmission with the GPU embedded system through a USB 3.0 interface, and the collected images are transmitted to an embedded system host;
s3, preprocessing the acquired image by the GPU embedded system, combining 2D image characteristics and 3D depth information acquired by the two cameras, finishing three-dimensional reconstruction of the whole stack according to camera calibration parameter information, wherein the specific principle of acquiring the depth information by the binocular camera is shown in figure 2, the left camera and the right camera acquire the image of the same point through different angles, and then synthesizing to obtain a 3D coordinate of the point;
s4, selecting and intercepting a heap image in the acquired image by using a feature point matching-based method through a deep learning network, then performing fitting sampling on depth information of the selected region, completing calculation of the volume of a complex material heap through GPU (graphics processing Unit) accelerated operation, and determining the material type in the image;
s5, comparing the specific material information of the material stack with the pre-stored material types, then corresponding the specific material information to the calculated volume value, and recording the volume value into a management system to complete the whole stack volume calculation and material type information acquisition process, thereby facilitating the management of the follow-up staff.
The invention realizes the automatic measurement and recording of the volume and the media type of the complex material pile, and aims at the problems of insufficient measurement precision and low efficiency caused by manual estimation and the deficiency of the prior art, a binocular camera is introduced into the pile volume detection and calculation to collect images above the complex material pile, the left camera and the right camera of the binocular camera simultaneously collect visual field images at two angles above the complex material pile, the purposes of splicing and fusing the visual fields are achieved by the relevance between two images or the parallax relation between the visual fields and combining the acceleration of a GPU display card, the 3D morphology of a target pile characteristic space is restored, the relevant numerical value information of the calculated volume and the material media characteristic information are extracted, and the pile volume calculation and the media determination are completed.
The above description is of the preferred embodiment of the invention. It is to be understood that the invention is not limited to the particular embodiments described above, in that devices and structures not described in detail are understood to be implemented in a manner common in the art; those skilled in the art can make many possible variations and modifications to the disclosed embodiments, or modify equivalent embodiments to equivalent variations, without departing from the spirit of the invention, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (6)
1. A complex material volume measurement method based on deep learning is characterized by comprising the following steps:
s1, collecting multi-angle visual field images above the pile body by using a binocular vision camera positioned above the pile body, and combining images collected by the two cameras to obtain a 2D image and 3D depth information of the pile body;
s2, carrying out data transmission on the binocular vision camera and the GPU embedded system, and transmitting the acquired image data to a GPU embedded system host;
s3, the GPU embedded system carries out image preprocessing on the collected image, combines the 2D image characteristics and the 3D depth information obtained by the two cameras, and then completes the three-dimensional reconstruction of the whole stack according to the camera calibration parameter information;
s4, selecting and intercepting a heap image in the acquired image by using a feature point matching-based method through a deep learning network, then performing fitting sampling on depth information of the selected region, completing calculation of the volume of a complex material heap through GPU (graphics processing Unit) accelerated operation, and determining the material type in the image;
s5, comparing the specific material information of the material stack with the pre-stored material types, then corresponding the specific material information with the calculated volume value, and recording the volume value into the management system to complete the whole stack volume calculation and material type information acquisition process.
2. The method for measuring the volume of the complex material based on the deep learning as claimed in claim 1, wherein when the binocular vision camera is used for the first time, the distortion is manually eliminated, and then the image is collected above the material pile.
3. The method for measuring the volume of a complex material based on deep learning of claim 2, wherein in step S1, an annular guide rail is disposed around the stack to enclose the stack therein, a slide block is disposed on the annular guide rail, the binocular vision camera is fixed on the slide block through a swing arm, and the slide block drives the binocular vision camera to perform a circular motion around the stack, so as to simultaneously acquire the view images at two angles above the stack.
4. The complex material volume measurement method based on deep learning of claim 1, wherein the step S3 specifically includes:
s31, intercepting the heap image based on the feature point matching of the point cloud depth information, and then preprocessing the point cloud;
and S32, fitting and sampling the depth information of the selected area to complete the three-dimensional reconstruction of the whole stack.
5. The method for measuring the volume of the complex material based on the deep learning as claimed in claim 4, wherein the purpose of splicing and fusing the visual fields is achieved by the aid of correlation between two images or the parallax relation between the visual fields and the acceleration of a GPU (graphics processing unit) display card, and the 3D morphology of the feature space of the target stack body is restored.
6. The complex material volume measuring method based on deep learning of claim 1, wherein in step S4, the stack volume calculation and the medium determination are completed by extracting the calculation volume-related numerical information and the material medium characteristic information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010766575.XA CN112053324A (en) | 2020-08-03 | 2020-08-03 | Complex material volume measurement method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010766575.XA CN112053324A (en) | 2020-08-03 | 2020-08-03 | Complex material volume measurement method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112053324A true CN112053324A (en) | 2020-12-08 |
Family
ID=73602052
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010766575.XA Pending CN112053324A (en) | 2020-08-03 | 2020-08-03 | Complex material volume measurement method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112053324A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112581478A (en) * | 2020-12-15 | 2021-03-30 | 上海电机学院 | Centroid-based road center line extraction method |
CN114136232A (en) * | 2021-11-19 | 2022-03-04 | 中国神华能源股份有限公司哈尔乌素露天煤矿 | Material accumulation form measuring method and system |
CN115018903A (en) * | 2022-08-10 | 2022-09-06 | 安维尔信息科技(天津)有限公司 | Method and system for calculating volume of stock pile in stock yard |
CN115311592A (en) * | 2022-04-02 | 2022-11-08 | 清华大学 | Job site material safety evaluation system based on computer vision technology |
CN116129365A (en) * | 2023-04-18 | 2023-05-16 | 天津美腾科技股份有限公司 | Method and system for detecting particle materials on conveying equipment |
CN116665139A (en) * | 2023-08-02 | 2023-08-29 | 中建八局第一数字科技有限公司 | Method and device for identifying volume of piled materials, electronic equipment and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101936761A (en) * | 2009-06-30 | 2011-01-05 | 宝山钢铁股份有限公司 | Visual measuring method of stockpile in large-scale stock ground |
CN104299125A (en) * | 2014-11-05 | 2015-01-21 | 常熟合正企业管理咨询有限公司 | Enterprise material warehousing system |
US9495764B1 (en) * | 2016-03-21 | 2016-11-15 | URC Ventures, Inc. | Verifying object measurements determined from mobile device images |
CN107514869A (en) * | 2016-06-17 | 2017-12-26 | 九阳股份有限公司 | The information input method and intelligent refrigerator of a kind of intelligent refrigerator |
CN108876855A (en) * | 2018-05-28 | 2018-11-23 | 哈尔滨工程大学 | A kind of sea cucumber detection and binocular visual positioning method based on deep learning |
CN109308693A (en) * | 2018-08-29 | 2019-02-05 | 北京航空航天大学 | By the target detection and pose measurement list binocular vision system of a ptz camera building |
CN109731794A (en) * | 2019-01-17 | 2019-05-10 | 上海电机学院 | Cillin bottle automatic cleaning system and method based on machine vision |
CN110260801A (en) * | 2019-05-13 | 2019-09-20 | 平安科技(深圳)有限公司 | Method and apparatus for measuring volume of material |
CN110321836A (en) * | 2019-07-01 | 2019-10-11 | 芜湖启迪睿视信息技术有限公司 | A kind of conveying material detection method based on image and laser point cloud atlas |
CN110726996A (en) * | 2019-11-25 | 2020-01-24 | 歌尔股份有限公司 | Depth module ranging method, depth camera and mobile terminal |
CN110738618A (en) * | 2019-10-14 | 2020-01-31 | 河海大学常州校区 | irregular windrow volume measurement method based on binocular camera |
CN111062254A (en) * | 2019-11-18 | 2020-04-24 | 厦门大学 | Method and device for evaluating bulk density of materials in loader bucket |
-
2020
- 2020-08-03 CN CN202010766575.XA patent/CN112053324A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101936761A (en) * | 2009-06-30 | 2011-01-05 | 宝山钢铁股份有限公司 | Visual measuring method of stockpile in large-scale stock ground |
CN104299125A (en) * | 2014-11-05 | 2015-01-21 | 常熟合正企业管理咨询有限公司 | Enterprise material warehousing system |
US9495764B1 (en) * | 2016-03-21 | 2016-11-15 | URC Ventures, Inc. | Verifying object measurements determined from mobile device images |
CN107514869A (en) * | 2016-06-17 | 2017-12-26 | 九阳股份有限公司 | The information input method and intelligent refrigerator of a kind of intelligent refrigerator |
CN108876855A (en) * | 2018-05-28 | 2018-11-23 | 哈尔滨工程大学 | A kind of sea cucumber detection and binocular visual positioning method based on deep learning |
CN109308693A (en) * | 2018-08-29 | 2019-02-05 | 北京航空航天大学 | By the target detection and pose measurement list binocular vision system of a ptz camera building |
CN109731794A (en) * | 2019-01-17 | 2019-05-10 | 上海电机学院 | Cillin bottle automatic cleaning system and method based on machine vision |
CN110260801A (en) * | 2019-05-13 | 2019-09-20 | 平安科技(深圳)有限公司 | Method and apparatus for measuring volume of material |
CN110321836A (en) * | 2019-07-01 | 2019-10-11 | 芜湖启迪睿视信息技术有限公司 | A kind of conveying material detection method based on image and laser point cloud atlas |
CN110738618A (en) * | 2019-10-14 | 2020-01-31 | 河海大学常州校区 | irregular windrow volume measurement method based on binocular camera |
CN111062254A (en) * | 2019-11-18 | 2020-04-24 | 厦门大学 | Method and device for evaluating bulk density of materials in loader bucket |
CN110726996A (en) * | 2019-11-25 | 2020-01-24 | 歌尔股份有限公司 | Depth module ranging method, depth camera and mobile terminal |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112581478A (en) * | 2020-12-15 | 2021-03-30 | 上海电机学院 | Centroid-based road center line extraction method |
CN114136232A (en) * | 2021-11-19 | 2022-03-04 | 中国神华能源股份有限公司哈尔乌素露天煤矿 | Material accumulation form measuring method and system |
CN115311592A (en) * | 2022-04-02 | 2022-11-08 | 清华大学 | Job site material safety evaluation system based on computer vision technology |
CN115311592B (en) * | 2022-04-02 | 2023-06-23 | 清华大学 | Construction site material safety evaluation system based on computer vision technology |
CN115018903A (en) * | 2022-08-10 | 2022-09-06 | 安维尔信息科技(天津)有限公司 | Method and system for calculating volume of stock pile in stock yard |
CN116129365A (en) * | 2023-04-18 | 2023-05-16 | 天津美腾科技股份有限公司 | Method and system for detecting particle materials on conveying equipment |
CN116129365B (en) * | 2023-04-18 | 2023-08-15 | 天津美腾科技股份有限公司 | Method and system for detecting particle materials on conveying equipment |
CN116665139A (en) * | 2023-08-02 | 2023-08-29 | 中建八局第一数字科技有限公司 | Method and device for identifying volume of piled materials, electronic equipment and storage medium |
CN116665139B (en) * | 2023-08-02 | 2023-12-22 | 中建八局第一数字科技有限公司 | Method and device for identifying volume of piled materials, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112053324A (en) | Complex material volume measurement method based on deep learning | |
CN100487724C (en) | Quick target identification and positioning system and method | |
CN103424112B (en) | A kind of motion carrier vision navigation method auxiliary based on laser plane | |
CN103644896B (en) | A kind of engineering geological mapping method based on 3 D laser scanning | |
CN108733053A (en) | A kind of Intelligent road detection method based on robot | |
CN105678288A (en) | Target tracking method and device | |
CN105225482A (en) | Based on vehicle detecting system and the method for binocular stereo vision | |
CN104899855A (en) | Three-dimensional obstacle detection method and apparatus | |
CN104034733A (en) | Service life prediction method based on binocular vision monitoring and surface crack image recognition | |
CN101794349A (en) | Experimental system and method for augmented reality of teleoperation of robot | |
CN104715471A (en) | Target positioning and tracking method and device | |
CN103198477A (en) | Apple fruitlet bagging robot visual positioning method | |
CN105760846A (en) | Object detection and location method and system based on depth data | |
CN110136186A (en) | A kind of detection target matching method for mobile robot object ranging | |
Zhao et al. | Reconstruction of textured urban 3D model by fusing ground-based laser range and CCD images | |
CN104570764A (en) | Verification platform for airborne target indicating system | |
CN107504917A (en) | A kind of three-dimensional dimension measuring method and device | |
CN108957024A (en) | A kind of method, apparatus and electronic equipment of tachometric survey | |
CN103759724A (en) | Indoor navigation method based on decorative lighting characteristic and system | |
CN113160292B (en) | Laser radar point cloud data three-dimensional modeling device and method based on intelligent mobile terminal | |
CN101793530B (en) | Method for measuring decoupling factor of optical fiber gyro | |
CN109708570A (en) | Information collection and analysis method and device for face structural plane | |
CN115859081A (en) | Visual detection method and device for pipeline | |
CN113487726B (en) | Motion capture system and method | |
Kornilova et al. | Evops benchmark: evaluation of plane segmentation from RGBD and LiDAR data |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201208 |
|
RJ01 | Rejection of invention patent application after publication |