CN113008376A - Temperature measurement method for infrared thermal imaging target tracking and capable of avoiding jitter interference - Google Patents
Temperature measurement method for infrared thermal imaging target tracking and capable of avoiding jitter interference Download PDFInfo
- Publication number
- CN113008376A CN113008376A CN202110133527.1A CN202110133527A CN113008376A CN 113008376 A CN113008376 A CN 113008376A CN 202110133527 A CN202110133527 A CN 202110133527A CN 113008376 A CN113008376 A CN 113008376A
- Authority
- CN
- China
- Prior art keywords
- target
- contour
- temperature
- curve
- thermal imaging
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000009529 body temperature measurement Methods 0.000 title claims abstract description 26
- 238000001931 thermography Methods 0.000 title claims abstract description 18
- 238000003708 edge detection Methods 0.000 claims abstract description 12
- 238000003384 imaging method Methods 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 241000270295 Serpentes Species 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000000418 atomic force spectrum Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
-
- 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
- G06T2207/10048—Infrared image
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Radiation Pyrometers (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a temperature measurement method and a temperature measurement system for infrared thermal imaging target tracking, which can avoid jitter interference, wherein the method comprises the following steps: s1: manually selecting a regular ROI area on the target image that is close to the target contour; s2: carrying out edge detection on the target in the ROI area, and extracting edge contour and texture details; acquiring a closed target contour from the edge contour by using a scanning filling method; s3: discretizing the initial curve with the target contour obtained in step S2 as the initial curve of the level set, and combining the discretized initial curve
The target image is iterated by using the active contour model based on the level set, and an accurate target area is obtained; s4: and counting the temperature values in the target area obtained in the step S3 to obtain the maximum temperature, the minimum temperature and the average temperature of the target. The invention can avoid using portable redWhen the temperature measuring equipment is externally used, the temperature measurement is invalid due to hand shaking; and the temperature measurement failure caused by the movement of the temperature measurement target can be avoided.
Description
Technical Field
The invention belongs to the technical field of optical parameter measurement, and particularly relates to a temperature measurement method and a temperature measurement system for infrared thermal imaging target tracking, which can avoid jitter interference.
Background
At present, the application of infrared thermal imaging for temperature measurement industry is more and more popular, and the measured target can be people, animals, vehicles, electric equipment and the like. Due to the irregular imaging shape of the temperature measurement target, a user of the thermal infrared imager is often required to manually set an imaging region of the measured target, which is generally called as a region of interest (ROI). The shape of the ROI is set to be generally in a rectangular shape, a circular shape, an oval shape, a polygonal shape and the like for a user to select. And then measuring parameter information such as the highest temperature, the lowest temperature, the average temperature and the like in the ROI area range.
Due to the fact that the imaging boundary of the target is irregular, after the regular ROI in a rectangular shape, a circular shape and an oval shape is manually set, the ROI generally comprises a partial background area, and therefore the real temperature of the target cannot be accurately reflected by parameters such as the highest temperature, the lowest temperature and the average temperature of the measured target. The polygonal ROI is manually set, and the measured target is surrounded by line segment connection, so that the target is difficult to be accurately matched with the edge of the target completely, burrs are easy to form, time is consumed for a long time, and efficiency is low. When the handheld infrared temperature measurement equipment is used, the temperature measurement target is easy to separate from the ROI area under the influence of hand shaking, great inconvenience is brought to use, and the accuracy of temperature measurement is influenced.
Disclosure of Invention
The invention aims to provide a temperature measuring method and a temperature measuring system for infrared thermal imaging target tracking, which can avoid jitter interference.
The invention tracks the target based on the ROI area setting and extracts the temperature by combining with the level set segmentation initialized by the target contour.
The invention provides a temperature measurement method for infrared thermal imaging target tracking, which can avoid jitter interference, and comprises the following steps:
s1: manually selecting a regular ROI area on the target image that is close to the target contour;
s2: carrying out edge detection on the target in the ROI area, and extracting edge contour and texture details; acquiring a closed target contour from the edge contour by using a scanning filling method;
s3: taking the target contour obtained in the step S2 as an initial curve of a level set, discretizing the initial curve, combining the discretized initial curve C and a target image, and performing iteration by using an active contour model based on the level set to obtain an accurate target area;
s4: and counting the temperature values in the target area obtained in the step S3 to obtain the maximum temperature, the minimum temperature and the average temperature of the target.
Further, the ROI area is a rectangular frame.
Further, in step S2, edge detection is performed using a Canny edge detection operator to extract an edge contour of a single pixel.
Further, in step S2, a closed target contour is obtained from the edge contour by using a scan filling method, specifically:
utilizing a vertical scanning line to perform small scanning from top to bottom on the edge outline to obtain a vertical scanning filling result;
202: scanning the edge outline from left to right by using a horizontal scanning line to obtain a horizontal scanning filling result;
203: and carrying out logical OR operation on the vertical scanning filling result and the horizontal scanning filling result to obtain a closed target contour.
Further, in step S3, the iterating with the active contour model based on the level set specifically includes:
s301: traversing pixel points in the target image to obtain the shortest directed distance u (x, y) from each pixel point to the curve C, and obtaining the following formula (1):
in the formula (1), d [ (x, y), C ] represents the shortest distance from the pixel p (x, y) to the curve C, when the pixel p (x, y) is positioned in the curve C, the shortest directed distance is-d [ (x, y), C ], otherwise, d [ (x, y), C ];
s302: according to the gradient information of the target image and a preset speed function, enabling u (x, y) of each pixel point to evolve along the direction of energy minimization;
s303: according to the curve evolved in the substep S302, traversing the pixel point p (x, y) in the target image again, judging whether u (x, y) is zero or not, and if the u (x, y) is 0, storing the pixel point coordinate;
s304: acquiring all pixel points with u (x, y) being 0, and forming a curve, namely an accurate target contour;
the temperature measuring method of the invention also comprises the following steps:
s5: and (4) taking the closed target contour obtained in the step (S2) as an initial template for target tracking, detecting whether the target contour is consistent with the initial template or not in real time, if not, determining that the target position moves, repositioning the target by using a tracking technology, automatically determining an ROI (region of interest) area for the repositioned target image, and executing steps (S2) -S4 based on the new ROI area.
The invention provides a temperature measurement system for infrared thermal imaging target tracking, which can avoid jitter interference, and comprises:
a first module for manually selecting a regular ROI area on the target image that approximates the target contour;
the second module is used for carrying out edge detection on the target in the ROI area and extracting edge contour and texture details; acquiring a closed target contour from the edge contour by using a scanning filling method;
the third module is used for discretizing the initial curve by taking the target contour acquired by the second module as the initial curve of the level set, combining the discretized initial curve C and the target image, and performing iteration by using the active contour model based on the level set to acquire an accurate target region;
and the fourth module is used for counting the temperature values in the target area obtained by the third module to obtain the highest temperature, the lowest temperature and the average temperature of the target.
Compared with the prior art, the invention has the following characteristics and beneficial effects:
(1) if the existing ROI is set and selected to be in a regular shape, the boundary of a target is difficult to accurately define; if the polygon is adopted, the problems of complex operation, burr, long time consumption and the like exist. The method comprises the steps of firstly, limiting a range by a regular shape, carrying out target edge detection and extracting an initial contour, and acquiring the outer contour of a target by a scanning method to be used as the initial contour of a level set in order to avoid the situation that the edge of the outer contour of the target does not form a closed area; and then, the precise automatic positioning of the contour is realized by using a movable contour algorithm, the operation is simple, and the positioning is accurate. This ensures that the target temperature is accurately obtained, eliminating background temperature disturbances.
(2) The method can track the target in real time, update the accurate closed area of the target in time, and avoid the temperature measurement failure caused by hand shake when using the portable infrared temperature measurement equipment; and the temperature measurement failure caused by the movement of the temperature measurement target can be avoided.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of manual setting of a rectangular ROI in an embodiment;
FIG. 3 is a schematic diagram of a closed target profile according to an embodiment.
Detailed Description
The method comprises the steps of firstly limiting a range by a regular shape, detecting a target edge and extracting an initial contour, and acquiring the outer contour of a target by a scanning method to be used as the initial contour of a level set in order to avoid the situation that the edge of the outer contour of the target does not form a closed area; and then, the precise automatic positioning of the contour is realized by using a movable contour algorithm, the operation is simple, and the positioning is accurate. This ensures that the target temperature is accurately obtained, eliminating background temperature disturbances. The method of the invention is adopted to track the target in real time, and update the precise closed area of the target in time, thus avoiding the temperature measurement failure caused by hand shake when using the portable infrared temperature measurement equipment; and the temperature measurement failure caused by the movement of the temperature measurement target can be avoided.
Embodiments of the present invention will be described below with reference to the accompanying drawings.
The temperature measuring method for infrared thermal imaging target tracking comprises the following specific steps:
s1: the target profile is initialized.
Based on the target imaging dimensions, a regularly shaped ROI template is manually selected that approximates the target imaging profile, defining an initial region of the target that includes the entire target within the initial region. The initial region in this embodiment is a rectangular box, as shown in fig. 2.
S2: and carrying out edge detection on the image in the initial region, and extracting the details of the contour and the texture. Specifically, Canny edge detection operators can be used for extracting imaging continuous single-pixel edge profiles. Because infrared thermal imaging may lack a complete closed contour due to gradual temperature change in a scene, in order to make the contour of a target form a closed region, a scanning filling method is used to obtain the closed target contour from an edge contour as an initial curve of a level set.
The specific process of extracting the target contour by the scanning filling method is as follows:
201: vertical scanning and filling:
and scanning a polygon formed by a plurality of line segments connected end to end from top to bottom by using a vertical scanning line, wherein the polygon is an edge profile extracted by using an edge insulation detection algorithm. Each vertical scan line creates a series of intersections with certain edges of the polygon. And (4) gradually ordering the intersection points according to the abscissa, and taking two intersection points with the same abscissa as a pair after ordering as two end points of a vertical line segment. And when all the columns are scanned, obtaining a vertical scanning line segment set, namely a vertical scanning filling result.
202: horizontal scanning and filling:
referring to substep 201, scanning a polygon formed by a plurality of line segments connected end to end from left to right by using a horizontal scanning line, gradually ordering intersection points according to a vertical coordinate, and pairing two intersection points with the same vertical coordinate after ordering to be used as two end points of one horizontal line segment respectively; and when all the lines are scanned, obtaining a horizontal scanning line segment set, namely a horizontal scanning filling result.
203: and performing logical OR operation on the vertical scanning filling result and the horizontal scanning filling result to obtain a closed target contour, and taking the target contour as an initial curve of the horizontal set.
S3: and (5) iterating the target contour extracted in the step (S2) by using the active contour model based on the level set to obtain an accurate target area. The step makes use of multiple iterations to make the contour boundary tightly surround the target, forming a closed and accurate target area.
The active contour model is a segmentation method based on an energy functional, and the basic idea is as follows: the method comprises the steps of expressing a target contour by using a continuous curve, defining an energy functional so that an independent variable of the energy functional comprises the curve, converting a segmentation process into a minimum value process for solving the energy functional, and solving an Euler equation corresponding to the function, wherein the position of the curve when the energy reaches the minimum is the position of the target contour. The active contour model includes a parametric active contour model represented by a Snake model and a level set-based collective active contour model. The Snake model has the following defects: (1) the segmentation result is sensitive to the position and shape of the initial curve; (2) a recessed region where the target is difficult to segment; (3) easy convergence to local extrema; (4) the spectrum structure change of the force curve graph cannot be flexibly realized. Because the shape of the infrared thermal imaging temperature measurement target is not fixed, the phenomena of profile depression, uneven temperature distribution and the like exist, a level set-based integrated movable profile model is selected.
The curve motion process in the level set method is based on the geometric measurement parameters of the curve, and the curve evolution theory is applied to image segmentation. The level set function is smooth and is initialized to the symbol distance function SDF. Assuming that C (t ═ 0) is the initialization curve and t denotes time, the level set function phi (x, y, t ═ 0) at time zero (i.e., the SDF function) is:
φ(x,y,t＝0)＝sign(x,y,C(t＝0))·dist(x,y,C(t＝0)) (1)
in formula (1), sign (x, y, C (t ═ 0)) is a sign function taking a value of +1 or-1, and if the point (x, y) is outside C (t ═ 0), sign (x, y, C (t ═ 0)) + 1; internally, sign (x, y, C (t-0)) -1; dist (x, y, C (t ═ 0)) represents the shortest distance of the point (x, y) to the initial curve C (t ═ 0).
Calculating the SDF function involves two steps: it is determined whether the point (x, y) is inside or outside the initial curve C (t ═ 0), and the shortest distance from the point (x, y) to the initial curve is calculated.
The present invention uses a discrete grid form to represent the level set phi (x, y, t). Let the interval of the discrete grid be h and the time step be Δ t, the level set function at the grid point (i, j) at n time is recorded as φ (ix, jy, n Δ t), which is abbreviated as
The evolution equation is discretized as:
in formula (2):
representing the level set function at grid point (i, j) at time n + 1;
representing the value of a velocity function at the grid point (i, j) at time n, the velocity function being used to control the velocity at which the curve approaches the target;
the gradient at grid point (i, j) is represented.
For equation (2), a preferential difference method can be used to solve.
The level set method needs to give an initial curve C (t ═ 0), and the closed target profile curve obtained by the scan filling method in step S2 is already close to the boundary profile of the target, so that the level set iteration speed can be increased by improving the method for initializing the profile curve. The profile curve is converted to a level set function, which can be defined as:
and calculating each pixel point p (x, y) of the image, and calculating the shortest distance d from the p (x, y) to the curve C, wherein if the pixel point p is positioned in the curve C, the directed distance is-d, and otherwise, the directed distance is d. Thus, each pixel point is traversed, and each pixel point can obtain the corresponding directed distance u (x, y).
The specific steps will be provided below:
inputting before segmentation: given a discrete initial curve C (i.e., the closed target contour extracted in step S2), the image T to be segmented; and (3) outputting: the result curve C' is segmented.
Calculating the shortest directed distance u (x, y) from each pixel point to a discrete curve C according to a level set function formula (see formula (3));
evolving u (x, y) according to information such as image gradient and the like, so that the u (x, y) evolves along the direction of energy minimization, in short, the u (x, y) evolves along the direction of energy minimization by updating the u (x, y) value of each pixel point;
and thirdly, traversing each pixel point (x, y) according to the evolution result of the second step, and judging whether the function value of the level set is zero or not. If u (x, y) is equal to 0, the pixel point is a point on the curve C', and the coordinates (x, y) of the pixel point are saved;
and fourthly, obtaining all pixel points with u (x, y) being 0, namely forming an image segmentation result curve C'.
S4: and (4) counting the temperature value of the target area within the contour curve obtained in the step (3) to obtain the highest temperature, the lowest temperature and the average temperature which truly reflect the target.
S5: and (4) taking the closed target contour obtained in the step (S2) as an initial template for target tracking, detecting whether the target contour is consistent with the initial template in real time, if not, determining that the target position moves, using the template contour to track, repositioning the target, automatically determining a new ROI (region of interest), and then executing the steps (S2) -S4.
Those skilled in the art will appreciate that, in the embodiments of the methods of the present invention, the sequence numbers of the steps are not used to limit the sequence of the steps, and it is within the scope of the present invention for those skilled in the art to change the sequence of the steps without inventive work. The examples described herein are intended to aid the reader in understanding the practice of the invention and it is to be understood that the scope of the invention is not limited to such specific statements and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (7)
1. The temperature measuring method capable of avoiding jitter interference for infrared thermal imaging target tracking is characterized by comprising the following steps:
s1: manually selecting a regular ROI area on the target image that is close to the target contour;
s2: carrying out edge detection on the target in the ROI area, and extracting edge contour and texture details; acquiring a closed target contour from the edge contour by using a scanning filling method;
s3: taking the target contour obtained in the step S2 as an initial curve of a level set, discretizing the initial curve, combining the discretized initial curve C and a target image, and performing iteration by using an active contour model based on the level set to obtain an accurate target area;
s4: and counting the temperature values in the target area obtained in the step S3 to obtain the maximum temperature, the minimum temperature and the average temperature of the target.
2. The method for measuring temperature of infrared thermal imaging target tracking capable of avoiding jitter interference as claimed in claim 1, wherein:
the regular ROI area is a rectangular frame.
3. The method for measuring temperature of infrared thermal imaging target tracking capable of avoiding jitter interference as claimed in claim 1, wherein:
in step S2, edge detection is performed using a Canny edge detection operator to extract an edge contour of a single pixel.
4. The method for measuring temperature of infrared thermal imaging target tracking capable of avoiding jitter interference as claimed in claim 1, wherein:
in step S2, a scanning filling method is used to obtain a closed target contour from the edge contour, specifically:
utilizing a vertical scanning line to perform small scanning from top to bottom on the edge outline to obtain a vertical scanning filling result;
202: scanning the edge outline from left to right by using a horizontal scanning line to obtain a horizontal scanning filling result;
203: and carrying out logical OR operation on the vertical scanning filling result and the horizontal scanning filling result to obtain a closed target contour.
5. The method for measuring temperature of infrared thermal imaging target tracking capable of avoiding jitter interference as claimed in claim 1, wherein:
in step S3, performing iteration using the active contour model based on the level set, specifically including:
s301: traversing pixel points in the target image to obtain the shortest directed distance u (x, y) from each pixel point to the curve C, and obtaining the following formula (1):
in the formula (1), d [ (x, y), C ] represents the shortest distance from the pixel p (x, y) to the curve C, when the pixel p (x, y) is positioned in the curve C, the shortest directed distance is-d [ (x, y), C ], otherwise, d [ (x, y), C ];
s302: according to the gradient information of the target image and a preset speed function, enabling u (x, y) of each pixel point to evolve along the direction of energy minimization;
s303: according to the curve evolved in the substep S302, traversing the pixel point p (x, y) in the target image again, judging whether u (x, y) is zero or not, and if the u (x, y) is 0, storing the pixel point coordinate;
s304: and acquiring all pixel points with u (x, y) ═ 0, and forming a curve, namely an accurate target contour.
6. The method for measuring temperature of infrared thermal imaging target tracking capable of avoiding jitter interference as claimed in claim 1, wherein:
further comprising:
s5: and (4) taking the closed target contour obtained in the step (S2) as an initial template for target tracking, detecting whether the target contour is consistent with the initial template or not in real time, if not, determining that the target position moves, repositioning the target by using a tracking technology, automatically determining an ROI (region of interest) area for the repositioned target image, and executing steps (S2) -S4 based on the new ROI area.
7. Can avoid temperature measurement system that infrared thermal imaging target of shake disturbed tracks, characterized by includes:
a first module for manually selecting a regular ROI area on the target image that approximates the target contour;
the second module is used for carrying out edge detection on the target in the ROI area and extracting edge contour and texture details; acquiring a closed target contour from the edge contour by using a scanning filling method;
the third module is used for discretizing the initial curve by taking the target contour acquired by the second module as the initial curve of the level set, combining the discretized initial curve C and the target image, and performing iteration by using the active contour model based on the level set to acquire an accurate target region;
and the fourth module is used for counting the temperature values in the target area obtained by the third module to obtain the highest temperature, the lowest temperature and the average temperature of the target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110133527.1A CN113008376B (en) | 2021-02-01 | 2021-02-01 | Temperature measurement method and system capable of avoiding jitter interference for infrared thermal imaging target tracking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110133527.1A CN113008376B (en) | 2021-02-01 | 2021-02-01 | Temperature measurement method and system capable of avoiding jitter interference for infrared thermal imaging target tracking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113008376A true CN113008376A (en) | 2021-06-22 |
| CN113008376B CN113008376B (en) | 2023-08-11 |
Family
ID=76385460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110133527.1A Active CN113008376B (en) | 2021-02-01 | 2021-02-01 | Temperature measurement method and system capable of avoiding jitter interference for infrared thermal imaging target tracking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113008376B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103575405A (en) * | 2012-07-24 | 2014-02-12 | 弗卢克公司 | Thermal imaging camera with graphical temperature plot |
| CN106023155A (en) * | 2016-05-10 | 2016-10-12 | 电子科技大学 | Online object contour tracking method based on horizontal set |
| US20170374296A1 (en) * | 2016-06-23 | 2017-12-28 | Fluke Corporation | Thermal anomaly detection |
| CN109900363A (en) * | 2019-01-02 | 2019-06-18 | 平高集团有限公司 | A kind of object infrared measurement of temperature method and apparatus based on contours extract |
-
2021
- 2021-02-01 CN CN202110133527.1A patent/CN113008376B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103575405A (en) * | 2012-07-24 | 2014-02-12 | 弗卢克公司 | Thermal imaging camera with graphical temperature plot |
| CN106023155A (en) * | 2016-05-10 | 2016-10-12 | 电子科技大学 | Online object contour tracking method based on horizontal set |
| US20170374296A1 (en) * | 2016-06-23 | 2017-12-28 | Fluke Corporation | Thermal anomaly detection |
| CN109900363A (en) * | 2019-01-02 | 2019-06-18 | 平高集团有限公司 | A kind of object infrared measurement of temperature method and apparatus based on contours extract |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113008376B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7843448B2 (en) | Identification of occluded edge regions from 3D point data | |
| CN113538671B (en) | Map generation method, map generation device, storage medium and processor | |
| CN108280852B (en) | Door and window point cloud shape detection method and system based on laser point cloud data | |
| CN113139453A (en) | Orthoimage high-rise building base vector extraction method based on deep learning | |
| CN111027118A (en) | Actual measurement actual quantity task point searching and task dispatching method and system | |
| CN105957107A (en) | Pedestrian detecting and tracking method and device | |
| CN112818925A (en) | Urban building and crown identification method | |
| US20230267593A1 (en) | Workpiece measurement method, workpiece measurement system, and program | |
| US20230047211A1 (en) | Method and system for automatic characterization of a three-dimensional (3d) point cloud | |
| CN109671084B (en) | Method for measuring shape of workpiece | |
| CN116399302B (en) | Method for monitoring dynamic compaction settlement in real time based on binocular vision and neural network model | |
| EP2791865B1 (en) | System and method for estimating target size | |
| CN113008376A (en) | Temperature measurement method for infrared thermal imaging target tracking and capable of avoiding jitter interference | |
| CN114549780B (en) | Intelligent detection method for large complex component based on point cloud data | |
| CN116051537A (en) | Crop plant height measurement method based on monocular depth estimation | |
| Nguyen et al. | Scan profiles based method for segmentation and extraction of planar objects in mobile laser scanning point clouds | |
| CN112598738A (en) | Figure positioning method based on deep learning | |
| Chen et al. | An improved Snake model for refinement of LiDAR-derived building roof contours using aerial images | |
| Kaess et al. | MCMC-based multiview reconstruction of piecewise smooth subdivision curves with a variable number of control points | |
| CN110555826A (en) | three-dimensional point cloud feature extraction method based on local outlier factors | |
| Shen et al. | Fast RGBD-ICP with bionic vision depth perception model | |
| CN116452586B (en) | Automatic butt welding quality detection system for tunnel small guide pipe residual materials | |
| CN115222771B (en) | Target tracking method and device | |
| CN102997865A (en) | Method for measuring steel plates | |
| EP4280158A1 (en) | Method for detecting an object based on monocular camera, electronic device, and non-transitory storage medium storing the method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |