Search

EP-4024129-B1 - BUILDING MATERIAL IMAGE RECOGNITION AND ANALYSIS SYSTEM AND METHOD

EP4024129B1EP 4024129 B1EP4024129 B1EP 4024129B1EP-4024129-B1

Inventors

  • LIN, Dinghui

Dates

Publication Date
20260506
Application Date
20190830

Claims (12)

  1. A building material image recognition and analysis method, comprising a photographing unit (10) for acquiring a building material image, a structural feature recognition module (21) for recognizing at least one feature on the building material structure in the building material image, the feature on the building material structure is further compared with the building material structure stored in a building material database (30) for obtaining an actual size of the image feature, and obtaining a proportion of the feature on the building material structure to a building material in the building material image and calculating an actual size of the building material according to the proportion and the actual size of the image feature, wherein the building material image is further processed through a color recognition module (22) to recognize the color of the building material in the building material image.
  2. The building material image recognition and analysis method according to claim 1, wherein a color of the building material in the building material image is recognized for providing a correct color code of the building material.
  3. The building material image recognition and analysis method according to claim 1 further comprising a step of providing a building material positioning coordinate value.
  4. The building material image recognition and analysis method according to claim 3, wherein the building material positioning coordinate value is provided by a Bluetooth positioning, a GPS positioning, a Wi-Fi positioning, a RFID positioning, an infrared/laser positioning, a Zigbee positioning or a VWB positioning.
  5. The building material image recognition and analysis method according to claim 1 comprising a step, before acquiring the building material image, of projecting a plurality of light points to the building material to make the building material image comprise the plurality of light points.
  6. The building material image recognition and analysis method according to claim 5, wherein the plurality of light points are projected by a LIDAR, a laser measurement instrument, a multi-lens sensing module, a structured light sensing module, a 3D sensing module or a TOF sensing module.
  7. The building material image recognition and analysis method according to claim 5, wherein the plurality of light points are used as the image feature for recognizing to obtain the actual size of the image feature.
  8. A building material image recognition and analysis system, comprising a photographing unit (10) for photographing a building material for acquiring a building material image; and an image recognition unit (20), wherein the image recognition unit (20) is used for receiving the building material image, the image recognition unit (20) is provided with a structural feature recognition module (21) for recognizing at least one feature on the building material structure in the building material image, wherein the feature on the building material structure is further compared with the building material structure stored in a building material database (30), obtaining, according to at least one image feature in the building material image, an actual size of the image feature, and obtaining a proportion of the feature on the building material structure to the building material in the building material image and calculating an actual size of the building material according to the proportion and the actual size of the image feature, wherein the image recognition unit (20) further comprises a color recognition module (22) for recognizing the color of the building material in the building material image.
  9. The building material image recognition and analysis system according to claim 8, wherein the image recognition unit (20) is able to recognize a color of the building material in the building material image to provide a correct color code of the building material.
  10. The building material image recognition and analysis system according to claim 8 further comprising a light point projecting unit (60), wherein the light point projecting unit (60) is able to project a plurality of light points to the building material to make the building material image acquired by the photographing unit (10) comprise the plurality of light points.
  11. The building material image recognition and analysis system according to claim 10, wherein the light point projecting unit (60) is a LIDAR, a laser measurement instrument, a multi-lens sensing module, a structured light sensing module, a 3D sensing module or a TOF sensing module.
  12. The building material image recognition and analysis system according to claim 8 further comprising a positioning unit (50), wherein the positioning unit (50) is able to provide a building material positioning coordinate value.

Description

FIELD OF INVENTION The present disclosure is an image recognition technology, and in particular, is a building material image recognition and analysis system and a method thereof. BACKGROUND OF INVENTION Currently, before making building materials, it is necessary to obtain the space dimensions of the place where the building materials will be installed, and then make the matching building materials according to the aforementioned space dimensions. However, at present, the way to obtain the space dimensions of the building materials is to measure them in person at the installation site. When the installation site is far away, the costs of transportation and labor will be incurred due to the manual measurement method, thereby causing the cost of installation to stay high. Therefore, in order to overcome the above-mentioned problems, the invention patent No. I509213 of Taiwan, discloses a "method for acquiring a space size of door (window) installation using remote image", which mainly uses a size correction piece disposed on one side of the edge of a building material installation space, then acquire an image including the door (window) installation space and the size correction piece through an image capturing device, and then transmits the image to an image measurement system. The image measurement system is used to analyze the image to find out an image proportion relationship between the door (window) installation space and the size correction piece. An actual size of the door (window) installation space is calculated according to the image proportion relationship and an actual size of the size correction piece; however, this conventional technology still has the following drawbacks in use: 1. This conventional technology requires the placement of a size correction piece before acquiring an image. However, it has been found that it is often difficult to find a suitable size correction piece during measurement, thereby causing a bother to the measurement.2. This conventional technology cannot recognize the color of the building materials in the image, thereby causing the problem that the colors of the building materials produced are usually different.3. In addition, only the installation location is noted during photographing in the conventional technology, so there is often accompanied with a bother of the wrong installation location. In addition, The patent application WO 2019/114219 A1 discloses a mobile robot and control method and control system thereof, comprising: storage device 11 for storing location information, map information, control application, camera device 13 for getting environment image when mobile robot is moving, treatment unit 15 for executing the instructions in the storage device 11 to controlling the mobile robot, mobile system 17 connected with the treatment unit 15, wherein the mobile system 17 comprises traveling mechanism and driving mechanism. The patent discloses a mobile robot and control method and control system, the purpose of the the patent is to discloses a mobile robot and control method and control system for improving the mobile robot's detection accuracy of obstacles, the obstacle is flexible winding. The patent application DE 10 2008 002241 A1 discloses a method for image-based measurement of a room or a partial area of a room, the patent discloses a method for measuring room area. The patent application US 2018/293751 A1 discloses a measuring apparatus and corresponding measuring method, the patent discloses a measuring method: step 100 ,switching on the measuring apparatus 1, step 101, a sequence of images of the examination object 3 is then recorded by the measuring apparatus 1, step 102, robust features 9, step 103,by use of the robust features 9 extracted in step 102, in particular using descriptors for the robust features 9, corresponding image regions 11 among the images are then identified in a computer-aided manner and a 3D model, step 104, from the sequence of images recorded in step 101, precise features 13, step 105,the precise features are assigned among the images and their 3D coordinates are calculated, step 106, a set of precise features 13 is then selected from the precise features 13 detected in step 104, step 107, finally, the desired geometric variable h is calculated in a computer- aided manner in the 3D model from the set of precise features 13 that was selected in step 106, step 108, the method is ended, a further method step can be performed, in which the 3D model is scaled by a reference object and/or a distance measurement. The patent application WO 201 6/049536 A1 discloses a system and method for determining coating requirements, in the patent "Determine orientations of image files 48--Determine coordinate locations of pixels 50-Identify coatable surfaces and associated dimensions 52--Receive real-world coordinate data 54--Calculate real-world dimensions 56--Calculate surface areas 58". The patent actually discloses a method for determi