WO2022088544A1 - Following robot multi-target identification system and method based on coded thermal infrared marker - Google Patents
Following robot multi-target identification system and method based on coded thermal infrared marker Download PDFInfo
- Publication number
- WO2022088544A1 WO2022088544A1 PCT/CN2021/074877 CN2021074877W WO2022088544A1 WO 2022088544 A1 WO2022088544 A1 WO 2022088544A1 CN 2021074877 W CN2021074877 W CN 2021074877W WO 2022088544 A1 WO2022088544 A1 WO 2022088544A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- thermal
- mark
- thermal infrared
- heating wire
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000003550 marker Substances 0.000 title abstract 5
- 230000005855 radiation Effects 0.000 claims abstract description 102
- 238000010438 heat treatment Methods 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000003708 edge detection Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 13
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000001931 thermography Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 235000002566 Capsicum Nutrition 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 229920000049 Carbon (fiber) Polymers 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000004917 carbon fiber Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Definitions
- the invention relates to the technical field of robot target recognition, in particular to a multi-target recognition system and method of a following robot based on a coded thermal infrared mark.
- Target person recognition is the key to realize the task of following the walking robot.
- the existing target person recognition technology is still in the laboratory stage and cannot meet the application requirements of the walking robot in the real environment.
- the targets they follow will also increase accordingly.
- the existing target recognition methods of following robots are often suitable for a single target object, and for robots with multiple target people at the same time. The problem of autonomous identification has not yet achieved a satisfactory solution.
- a target recognition device and method for a walking robot based on thermal radiation signs and thermal infrared image recognition are proposed.
- the target recognition method based on thermal infrared images avoids the traditional color
- the image recognition method is easily affected by changes in ambient light, which can meet the application requirements in indoor and outdoor environments, and has good environmental adaptability.
- thermal imaging technology also has its drawbacks, such as the edge of infrared thermal imaging is relatively blurry, and the features are difficult to extract; it is easily affected by external factors such as the surface characteristics of the object and the wavelength of radiation, the thickness and direction of the navigator's clothes, and the clothes Materials all affect the brightness of an image. Therefore, human detection based on infrared thermal imaging is still a very challenging problem.
- the present disclosure proposes a multi-target recognition system and method for a follower robot based on a coded thermal infrared mark. Recognition of different targets by the robot.
- a multi-target recognition system for following robots based on encoded thermal infrared signs including:
- a heat radiation mark used for setting on the target to be identified, a plurality of heating wires are arranged in the heat radiation mark, and the heating wires are heated according to different coding rules;
- the thermal infrared image acquisition module is used to collect the thermal infrared image of the target to be identified and transmit it to the data processing module;
- the data processing module identifies the thermal radiation sign image from the thermal infrared image, identifies the encoding information of the thermal radiation sign according to the thermal radiation sign image, and identifies the target to be identified through the encoded information.
- the target to be identified is identified through the encoded information.
- an electronic device comprising a memory and a processor, and computer instructions stored on the memory and running on the processor, the computer instructions, when executed by the processor, complete a following robot based on an encoded thermal infrared sign The steps described in the multi-target recognition method.
- a computer-readable storage medium for storing computer instructions that, when executed by a processor, complete the steps described in the method for multi-target recognition of a follower robot based on an encoded thermal infrared mark.
- the present disclosure encodes the heating wire in the thermal radiation sign, so as to have multi-target recognition capability, and realizes the identification of different targets by the following robot according to the encoded information by identifying the encoded information of the thermal radiation sign heated according to the encoding rules.
- Embodiment 1 is a schematic structural diagram of Embodiment 1 of the present disclosure
- Fig. 2 is the identification flow chart of Embodiment 1 of the present disclosure
- Fig. 3 is the coding rule of heat radiation mark in the disclosed embodiment 1;
- FIG. 6 is an edge detection image extracted by Embodiment 1 of the present disclosure.
- FIG. 7 is the vertical edge pixel search rule of Embodiment 1 of the present disclosure.
- FIG. 9 is an image after the image of FIG. 8 is expanded three times in Embodiment 1 of the present disclosure.
- FIG. 10 is the embodiment of the present disclosure, which corrodes the image of FIG. 9 four times;
- FIG. 11 is an image of the area where the heat radiation mark is located according to Embodiment 1 of the present disclosure.
- FIG. 12 is a thermal radiation sign image extracted in Embodiment 1 of the present disclosure.
- FIG. 14 is a code recognition image confirmed in Embodiment 1 of the present disclosure.
- orientation or positional relationship is based on the orientation or positional relationship shown in the drawings, and is only a relational word determined for the convenience of describing the structural relationship of each component or element of the present disclosure, and does not specifically refer to any component or element in the present disclosure, and should not be construed as a reference to the present disclosure. public restrictions.
- a multi-target recognition system for a following robot based on a coded thermal infrared mark including:
- a heat radiation mark used for setting on the target to be identified, a plurality of heating wires are arranged in the heat radiation mark, and the heating wires are heated according to different coding rules;
- the thermal infrared image acquisition module is used to collect the thermal infrared image of the target to be identified and transmit it to the data processing module;
- the data processing module identifies the thermal radiation sign image from the thermal infrared image, identifies the encoding information of the thermal radiation sign according to the thermal radiation sign image, and identifies the target to be identified through the encoded information.
- the heat radiation mark uses binary rules to encode the heating wire.
- the encoded information carried by the thermal radiation mark corresponds to the target to be identified one-to-one.
- heating wires in the heat radiation sign are arranged in parallel and at equal intervals.
- the vertical edge and discrete edge of the edge detection image are eliminated, and the thermal radiation mark image is extracted from the edge detection image according to the largest area of the thermal radiation mark.
- the heating wire image and the unheated heating wire image in the heat radiation mark image are identified according to the pixel gray value, and the coding information of the heat radiation mark is determined according to the height information of the heated heating wire image and the unheated heating wire image in the vertical direction.
- the data processing module determines whether the image of the heated heating wire and the image of the unheated heating wire in the heat radiation sign image satisfy the shape constraint, and when the shape constraint is satisfied, the height in the vertical direction of the image of the heated heating wire and the image of the unheated heating wire is determined according to the shape constraint.
- the information determines the encoded information of the thermal radiation signature.
- the multi-target recognition system for following robots based on coded thermal infrared marks includes a thermal radiation mark 1 worn by the target to be identified, and a plurality of parallel carbon fiber heating wires are arranged in the thermal radiation mark. Heating is carried out according to different coding rules, and then the thermal infrared camera can obtain gray-scale images with obvious differences in characteristics, and further extract the mutually independent coding information carried by different thermal radiation marks through image processing, so as to realize the identification of different targets.
- the heating wire in the heat radiation mark is encoded by binary rules, as shown in Figure 3, the coding rule is explained by taking the heat radiation mark containing 5 heating wires as an example, the top heating wire and the bottom heating wire are used as the heat radiation mark
- the boundary determination mark is always in the heating state, and the 3 heating wires inside are heated according to the binary coding rule, which has a total of 8 combinations from 0 to 7, that is, if the number is 0, all heating wires will not be heated.
- the number is 1, only the bottom heating wire is heated, when the number is 2, only the middle heating wire is heated, ..., when the number is 7, all the three heating wires are heated.
- This method can realize the multi-feature distinction of the same thermal radiation sign, so it can meet the requirements of robot identification under the condition of multi-target human existence.
- Figure 3 shows the thermal infrared images of the targets to be identified, numbered 0, 2, 5, and 7, corresponding to the thermal radiation sign composed of 5 heating wires obtained by the thermal infrared camera when the above coding rules are used. It can be seen from Figure 3 that the heating The rear heating wire is clearly distinguished from the surrounding environment, which proves the feasibility of the identification scheme.
- median filtering is mainly used to remove the salt and pepper noise brought by the optical acquisition system in the barcode image, because when there is strong salt and pepper noise interference in the image, the gray value corresponding to these interference points and the gray value of the adjacent pixels There is a big difference in the degree value, so by sorting and removing the median value, the gray value of these interference points is changed to be similar to the gray value of some adjacent pixels, so as to achieve the effect of removing noise.
- Median filtering is a nonlinear smoothing method to reduce edge blur. Its basic idea is as follows: set up a one-dimensional sequence f 1 , f 2 , f 3 ,..., f n , take the window length as m, for one The median filter is performed on the dimensional sequence, that is, m numbers f iv ,...,f i-1 ,f 1 ,f i+1 ...,f i+v are successively extracted from the sequence. The m numbers are sorted according to the size of their values, and the middle number is taken as the filter output, that is:
- Step 2 Edge Detection
- the gradients on the edge points of the heating wire are consistent, the color reflectance on both sides of the heating wire edge is very different, and the edges are relatively dense.
- the above features can be processed by extracting the pixels with obvious features and large amount of information in the filtered thermal infrared image by means of edge detection, thereby reducing the amount of calculation and improving the efficiency of the algorithm.
- Common edge detection algorithms include Prewitts operator, Roberts operator, Soble operator, Canny operator and other classic edge detection operators. Since the heating wire is basically in a horizontal state when moving with the human body, the Prewitts operator is more conducive to thermal radiation. Edge extraction of logos.
- the Prewitt operator is a differential operator for image edge detection. Its principle is to use the difference generated by the pixel gray value in a specific area to achieve edge detection.
- the Prewitt operator uses a 3*3 template to calculate the pixel values in the area, so the edge detection results are more obvious in the horizontal and vertical directions.
- Prewitt operator is suitable for identifying images with more noise and grayscale gradient.
- FIG. 6 is an edge detection image after edge extraction is performed by using the Prewitt operator.
- the original edge information of the above-mentioned edge detection image contains a lot of edge data irrelevant to the thermal radiation sign, such as the edge information of the target person's body and the edge information of other objects, etc. These edges will introduce unnecessary interference information to the subsequent processing. Use certain filtering operations to eliminate redundant edge data.
- Step 4 Eliminate Discrete Edges
- Step 5 Extract the thermal radiation sign image
- Fig. 11 Since the connected area shown in Fig. 11 is the result of expanding the edge image 3 times and then eroding it 4 times, expanding once more on the basis of Fig. 11 is the edge area of the thermal radiation mark. 12 shows the thermal radiation sign image.
- Step 6 Identification of bright and dark stripes
- the bright stripes refer to the image of the heated heating wire
- the dark stripes refer to the image of the unheated heating wire.
- the number of pixels L (L 1 , L 2 , ..., L i ) contained in each bright stripe in the vertical direction and the pixels corresponding to the dark stripes are counted in the column image where the central pixel of the thermal radiation sign area is located in the order from top to bottom.
- the number D (D 1 , D 2 , . . . , D i ), and the mean value A of the number of pixels included in the bright stripes and the pixel synthesis T of all stripes are calculated.
- the average value of the pixel heights occupied by the above bright stripes in the vertical direction is proportional to the overall pixel height of the heat radiation sign, so it is considered that the above stripe information satisfies the heat radiation when the following formula is satisfied Logo shape condition constraints.
- the encoding information Num of the current thermal radiation sign can be obtained according to the height information of the bright and dark stripes in the vertical direction and using the following formula.
- the data processing module identifies the target to be identified through the encoded information.
- This embodiment is aimed at the blurred edge of infrared thermal imaging, which is difficult to extract features, and is easily affected by external factors such as the surface characteristics of the object and the wavelength of radiation, which are faced in the field of target recognition based on thermal infrared images. All materials will affect the inherent problems such as the brightness of the image.
- the invention provides a multi-target recognition system for following robots based on encoded thermal infrared signs. Differentiate from the background.
- the heating wire in the thermal radiation sign is encoded in binary form, so that it has the ability of multi-target recognition. Steps such as edge, extraction of thermal radiation sign images, bright and dark stripe identification, morphological constraints, thermal radiation mark image confirmation, and coding recognition can accurately identify thermal radiation marks and extract their coding information, so as to realize the recognition of the target by the robot.
- a multi-target recognition method for following robots based on encoded thermal infrared signs including:
- the target to be identified is identified through the encoded information.
- the heating wire edge detection is performed on the filtered thermal infrared image, and the image after edge detection is obtained;
- the vertical edge and discrete edge of the image after edge detection are eliminated, and the thermal radiation mark image is extracted from the image after edge detection according to the largest area of the thermal radiation mark.
- the heating wire curve and the unheated heating wire curve in the heat radiation mark image are identified according to the pixel gray value, and the encoding information of the heat radiation mark is determined according to the height information of the heated heating wire curve and the unheated heating wire curve in the vertical direction.
- an electronic device which includes a memory and a processor, and computer instructions stored in the memory and executed on the processor.
- the computer instructions are executed by the processor, the based on the The steps described in the multi-target recognition method of the following robot with encoded thermal infrared signs.
- a computer-readable storage medium for storing computer instructions, and when the computer instructions are executed by a processor, the multi-target identification method for a following robot based on an encoded thermal infrared mark disclosed in Embodiment 2 is completed the steps described.
- the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
- computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
- These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
- the apparatus implements the functions specified in the flow or flows of the flowcharts and/or the block or blocks of the block diagrams.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
Description
Claims (10)
- 基于编码热红外标志的跟随机器人多目标识别系统,其特征在于,包括:The following robot multi-target recognition system based on coded thermal infrared mark is characterized in that, it includes:热辐射标志,设置在待识别目标上,所述热辐射标志中布置多根发热丝,发热丝按照不同的编码规则进行加热;The heat radiation mark is arranged on the target to be identified, and a plurality of heating wires are arranged in the heat radiation mark, and the heating wires are heated according to different coding rules;热红外图像采集模块,用于采集待识别目标的热红外图像并传送至数据处理模块;The thermal infrared image acquisition module is used to collect the thermal infrared image of the target to be identified and transmit it to the data processing module;数据处理模块,从热红外图像中识别热辐射标志图像,根据热辐射标志图像识别热辐射标志的编码信息,通过编码信息对待识别目标进行识别。The data processing module identifies the thermal radiation sign image from the thermal infrared image, recognizes the encoding information of the thermal radiation sign according to the thermal radiation sign image, and identifies the target to be identified through the encoded information.
- 如权利要求1所述的基于编码热红外标志的跟随机器人多目标识别系统,其特征在于,热辐射标志采用二进制规则对发热丝进行编码。The multi-target recognition system for following robots based on coded thermal infrared marks according to claim 1, wherein the thermal radiation marks use binary rules to encode the heating wire.
- 如权利要求1所述的基于编码热红外标志的跟随机器人多目标识别系统,热辐射标志中的发热丝平行等间距布置。The multi-target recognition system for following robots based on coded thermal infrared marks as claimed in claim 1, wherein the heating wires in the thermal radiation marks are arranged in parallel and at equal intervals.
- 如权利要求1所述的基于编码热红外标志的跟随机器人多目标识别系统,数据处理模块从热红外图像中识别热辐射标志图像的具体过程为:The following robot multi-target recognition system based on the coded thermal infrared mark as claimed in claim 1, the specific process that the data processing module identifies the thermal radiation mark image from the thermal infrared image is:对热红外图像进行滤波处理;Filter the thermal infrared image;对滤波处理后的热红外图像进行发热丝边缘提取,获取边缘检测图像;Extract the edge of the heating wire on the filtered thermal infrared image to obtain the edge detection image;消除边缘检测图像的竖向边缘和离散边缘,并根据热辐射标志所处区域面积最大,从边缘检测图像中提取热辐射标志图像。The vertical edge and discrete edge of the edge detection image are eliminated, and the thermal radiation mark image is extracted from the edge detection image according to the largest area of the thermal radiation mark.
- 如权利要求1所述的基于编码热红外标志的跟随机器人多目标识别系统,数据处理模块根据热辐射标志图像识别热辐射标志编码信息的具体过程为:The following robot multi-target recognition system based on coded thermal infrared marks as claimed in claim 1, the specific process that the data processing module recognizes the thermal radiation mark coding information according to the thermal radiation mark image is:根据像素灰度值识别热辐射标志图像中加热发热丝图像和未加热发热丝图像,根据加热发热丝图像和未加热发热丝图像竖直方向上的高度信息确定热辐射标志的编码信息。The heating wire image and the unheated heating wire image in the heat radiation mark image are identified according to the pixel gray value, and the encoding information of the heat radiation mark is determined according to the height information of the heated heating wire image and the unheated heating wire image in the vertical direction.
- 如权利要求5所述的基于编码热红外标志的跟随机器人多目标识别系统,数据处理模块判断热辐射标志图像中加热发热丝图像和未加热发热丝图像是否满足形态约束,当满足形态约束时,根据加热发热丝图像和未加热发热丝图像竖直方向上的高度信息确定热辐射标志的编码信息。The multi-target recognition system for following robots based on coded thermal infrared marks as claimed in claim 5, wherein the data processing module judges whether the heated heating wire image and the unheated heating wire image in the thermal radiation mark image satisfy the morphological constraint, and when the morphological constraint is satisfied, The encoding information of the heat radiation mark is determined according to the height information of the heated heating wire image and the unheated heating wire image in the vertical direction.
- 基于编码热红外标志的跟随机器人多目标识别方法,其特征在于,包括:The multi-target recognition method for following robots based on coded thermal infrared signs is characterized in that, comprising:采集待识别目标的热红外图像;Collect thermal infrared images of the target to be identified;从热红外图像中识别热辐射标志图像;Identify thermal radiation signature images from thermal infrared images;根据热辐射标志图像识别热辐射标志的编码信息;Identify the coded information of the heat radiation mark according to the heat radiation mark image;通过编码信息对待识别目标进行识别。The target to be identified is identified through the encoded information.
- 如权利要求7所述的基于编码热红外标志的跟随机器人多目标识别方法,其特征在于,根据热辐射标志图像识别热辐射标志编码信息的具体过程为:The multi-target identification method of a following robot based on a coded thermal infrared mark as claimed in claim 7, wherein the specific process of recognizing the encoded information of the thermal radiation mark according to the thermal radiation mark image is:根据像素灰度值识别热辐射标志图像中加热发热丝曲线和未加热发热丝曲线,根据加热发热丝曲线和未加热发热丝曲线竖直方向上的高度信息确定热辐射标志的编码信息。The heating wire curve and the unheated heating wire curve in the heat radiation mark image are identified according to the pixel gray value, and the encoding information of the heat radiation mark is determined according to the height information of the heated heating wire curve and the unheated heating wire curve in the vertical direction.
- 一种电子设备,包括存储器和处理器以及存储在存储器上并在处理器上运行的计算机指令,所述计算机指令被处理器运行时,完成权利要求7-8任一项所述的基于编码热红外标志的跟随机器人多目标识别方法所述的步骤。An electronic device, comprising a memory, a processor, and computer instructions stored in the memory and running on the processor, when the computer instructions are executed by the processor, the encoding-based heat-based coding of any one of claims 7-8 is completed. The steps are described in the multi-target recognition method of the following robot of the infrared mark.
- 一种计算机可读存储介质,用于存储计算机指令,所述计算机指令被处理器执行时,完成权利要求7-8任一项所述的基于编码热红外标志的跟随机器人多目标识别方法所述的步骤。A computer-readable storage medium for storing computer instructions, when the computer instructions are executed by the processor, the method for identifying multiple targets of a following robot based on a coded thermal infrared mark according to any one of claims 7-8 is completed. A step of.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021368390A AU2021368390B2 (en) | 2020-10-29 | 2021-02-02 | Multi-target recognition system and method for follow-up robot based on coded thermal infrared mark |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011181170.6A CN112287831B (en) | 2020-10-29 | 2020-10-29 | Following robot multi-target identification system and method based on coded thermal infrared mark |
CN202011181170.6 | 2020-10-29 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022088544A1 true WO2022088544A1 (en) | 2022-05-05 |
Family
ID=74352388
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/074877 WO2022088544A1 (en) | 2020-10-29 | 2021-02-02 | Following robot multi-target identification system and method based on coded thermal infrared marker |
Country Status (3)
Country | Link |
---|---|
CN (1) | CN112287831B (en) |
AU (1) | AU2021368390B2 (en) |
WO (1) | WO2022088544A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112287831B (en) * | 2020-10-29 | 2022-11-04 | 齐鲁工业大学 | Following robot multi-target identification system and method based on coded thermal infrared mark |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110298334A (en) * | 2019-07-05 | 2019-10-01 | 齐鲁工业大学 | Tracking robot multi-targets recognition device based on infrared image processing |
CN110320523A (en) * | 2019-07-05 | 2019-10-11 | 齐鲁工业大学 | Follow the target locating set and method of robot |
CN111354011A (en) * | 2020-05-25 | 2020-06-30 | 江苏华丽智能科技股份有限公司 | Multi-moving-target information capturing and tracking system and method |
CN112287831A (en) * | 2020-10-29 | 2021-01-29 | 齐鲁工业大学 | Following robot multi-target identification system and method based on coded thermal infrared mark |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN208402864U (en) * | 2018-06-25 | 2019-01-22 | 龙勇 | Unmanned plane warm-blooded animal based on thermal imaging monitors system |
CN110834132B (en) * | 2019-11-28 | 2021-07-09 | 西南交通大学 | Method for manufacturing aluminum alloy flange arc fuse wire additive on bottom of ellipsoidal box |
-
2020
- 2020-10-29 CN CN202011181170.6A patent/CN112287831B/en active Active
-
2021
- 2021-02-02 WO PCT/CN2021/074877 patent/WO2022088544A1/en active Application Filing
- 2021-02-02 AU AU2021368390A patent/AU2021368390B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110298334A (en) * | 2019-07-05 | 2019-10-01 | 齐鲁工业大学 | Tracking robot multi-targets recognition device based on infrared image processing |
CN110320523A (en) * | 2019-07-05 | 2019-10-11 | 齐鲁工业大学 | Follow the target locating set and method of robot |
CN111354011A (en) * | 2020-05-25 | 2020-06-30 | 江苏华丽智能科技股份有限公司 | Multi-moving-target information capturing and tracking system and method |
CN112287831A (en) * | 2020-10-29 | 2021-01-29 | 齐鲁工业大学 | Following robot multi-target identification system and method based on coded thermal infrared mark |
Also Published As
Publication number | Publication date |
---|---|
AU2021368390B2 (en) | 2024-03-28 |
CN112287831B (en) | 2022-11-04 |
CN112287831A (en) | 2021-01-29 |
AU2021368390A1 (en) | 2023-06-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111104943B (en) | Color image region-of-interest extraction method based on decision-level fusion | |
CN110264448B (en) | Insulator fault detection method based on machine vision | |
CN104061907B (en) | The most variable gait recognition method in visual angle based on the coupling synthesis of gait three-D profile | |
CN112819094B (en) | Target detection and identification method based on structural similarity measurement | |
CN105574488B (en) | It is a kind of to be taken photo by plane the pedestrian detection method of infrared image based on low latitude | |
CN107253485A (en) | Foreign matter invades detection method and foreign matter intrusion detection means | |
CN107369159B (en) | Threshold segmentation method based on multi-factor two-dimensional gray level histogram | |
CN110097596B (en) | Object detection system based on opencv | |
CN107491730A (en) | A kind of laboratory test report recognition methods based on image procossing | |
CN106600625A (en) | Image processing method and device for detecting small-sized living thing | |
CN104123554B (en) | SIFT image characteristic extracting methods based on MMTD | |
CN109559324A (en) | A kind of objective contour detection method in linear array images | |
CN103870808A (en) | Finger vein identification method | |
Xu et al. | Real-time pedestrian detection based on edge factor and Histogram of Oriented Gradient | |
CN107315012A (en) | Composite polycrystal-diamond end face collapses the intelligent detecting method at angle | |
CA2454091A1 (en) | Chromatin segmentation | |
CN111967288A (en) | Intelligent three-dimensional object identification and positioning system and method | |
CN103198319A (en) | Method of extraction of corner of blurred image in mine shaft environment | |
CN112950589A (en) | Dark channel prior defogging algorithm of multi-scale convolution neural network | |
WO2022088544A1 (en) | Following robot multi-target identification system and method based on coded thermal infrared marker | |
Rajput et al. | Using radon transform to recognize skewed images of vehicular license plates | |
CN105528795B (en) | A kind of infrared face dividing method using annular shortest path | |
CN115147450B (en) | Moving target detection method and detection device based on motion frame difference image | |
Pooja et al. | Image segmentation: A survey | |
Chen et al. | Illumination processing in face recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21884288 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021368390 Country of ref document: AU Date of ref document: 20210202 Kind code of ref document: A |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21884288 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 21.11.2023) |