CN210091196U

CN210091196U - Object recognition device

Info

Publication number: CN210091196U
Application number: CN201920867438.8U
Authority: CN
Inventors: 刘康德; 胡美峰; 张艳霞; 孔刚; 龚潇
Original assignee: Shenzhen Hongdian Technologies Corp
Current assignee: Shenzhen Hongdian Technologies Corp
Priority date: 2019-06-06
Filing date: 2019-06-06
Publication date: 2020-02-18
Anticipated expiration: 2029-06-06

Abstract

The utility model discloses an object recognition device relates to discernment technical field. The device comprises an object to be identified, an image acquisition module for acquiring an image of the object to be identified, and an identification module for identifying the object to be identified, wherein the output end of the image acquisition module is connected with the input end of the identification module; the image acquisition module sends the acquired image of the object to be recognized to the recognition module, a special pattern is printed on the object to be recognized, and the recognition module recognizes the object to be recognized according to the special pattern. The utility model discloses a collection printing has the waiting of special pattern to discern the object image to discerning the image, utilizing the different waiting of different special pattern discernment object. Compared with the prior art, additional hardware such as NFC or RFID is not added, the cost is low, the requirement on an identification algorithm is low, the applicability is wide, and good economic and social benefits are achieved.

Description

Object recognition device

Technical Field

The utility model belongs to the technical field of the identification technique and specifically relates to an object recognition device is related to.

Background

The need for object identification is quite extensive in practical applications, such as in automated production lines where identification is required, and in unmanned containers where identification is required. The current methods mainly comprise the following steps:

the first method comprises the following steps: and acquiring images through a camera and carrying out identification through an image identification algorithm. The identification mode has strict requirements on the position of the camera, and an object needing to be identified can be shot, and the success rate is reduced if the object is shielded.

And the second method comprises the following steps: the method is realized by strictly placing objects according to preset positions and relatively simple algorithm judgment. The recognition mode has relatively high misrecognition rate, corresponding algorithm training and convergence are required in the lead-in period, and repeated work is more during object replacement.

And the third is that: reading and identifying by sticking NFC or RFID or the like on the object. The identification method has high identification accuracy, but the NFC or RFID identification card increases the cost and has a limited reading range.

While there are many ways in which identification can be achieved, there is no effective solution for accurate object identification in a relatively low cost manner.

SUMMERY OF THE UTILITY MODEL

The present invention aims at solving at least one of the technical problems in the related art to a certain extent. For this reason, it is an object of the present invention to provide an object recognition apparatus capable of accurately recognizing an object to be recognized in a relatively low-cost manner.

The utility model adopts the technical proposal that:

an object recognition device comprises an object to be recognized, an image acquisition module for acquiring an image of the object to be recognized, and a recognition module for recognizing the object to be recognized, wherein the output end of the image acquisition module is connected with the input end of the recognition module;

the image acquisition module sends the acquired image of the object to be recognized to the recognition module, a special pattern is printed on the object to be recognized, and the recognition module recognizes the object to be recognized according to the special pattern.

Furthermore, the identification module comprises a microprocessor, and the output end of the image acquisition module is connected with the input end of the microprocessor.

Furthermore, the special patterns are made of reflective materials.

Further, the device also comprises an illumination module, wherein the illumination module is used for illuminating the object to be identified.

Furthermore, the device also comprises a light collection module, wherein the output end of the light collection module is connected with the input end of the identification module, and the light collection module is used for collecting the reflected light of the light irradiated on the object to be identified.

Further, the light collection module comprises a light sensor, the identification module further comprises an amplifier, an output end of the light sensor is connected with an input end of the amplifier, and an output end of the amplifier is connected with an input end of the microprocessor.

Further, the lighting module includes an LED lamp.

Further, the image acquisition module comprises a camera, and the output end of the camera is connected with the input end of the identification module.

The utility model has the advantages that:

the utility model discloses a collection printing has the waiting of special pattern to discern the object image to discerning the image, utilizing the different waiting of different special pattern discernment object. Compared with the prior art, additional hardware such as NFC or RFID is not added, the cost is low, the requirement on an identification algorithm is low, the applicability is wide, and good economic and social benefits are achieved.

Drawings

Fig. 1 is a schematic structural diagram of an embodiment of an object recognition device according to the present invention;

fig. 2 is a schematic structural diagram of another embodiment of an object recognition device according to the present invention.

Detailed Description

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.

Example 1

The present embodiment provides an object recognition apparatus. As shown in fig. 1, the device comprises an object to be identified, an image acquisition module for acquiring an image of the object to be identified, and an identification module for identifying the object to be identified. The output end of the image acquisition module is connected with the input end of the identification module.

The image acquisition module sends the image of the object to be identified to the identification module, and the identification module can identify the object to be identified according to the special pattern due to the fact that the special pattern is printed on the object to be identified.

The object recognition device provided by the embodiment is mainly applied to the unmanned goods shelf, and a user can freely pick and place objects when selecting the objects. The device sends the identification module through gathering the object image on the goods shelves, because the printing has different special pattern on the object of difference, consequently can accurately discern the object type on the goods shelves. In addition, it is also possible to detect the presence of objects on the shelves (i.e. whether they are taken or moved out of the acquisition range by the user) by recognizing the acquired images. Compared with the prior art, additional hardware such as NFC or RFID is not added, the cost is low, the requirement on the identification algorithm is low due to the fact that the image identification algorithm is mature, and the applicability is wide.

In this embodiment, the image acquisition module includes the camera, and the output of camera is connected with identification module's input.

In this embodiment, the identification module includes a microprocessor, and an output terminal of the image acquisition module is connected to an input terminal of the microprocessor.

Example 2

Based on a further improvement of embodiment 1, as shown in fig. 2, in this embodiment, the special pattern is made of a reflective material and is printed on the object to be identified.

Different colors have different reflectivities, an extreme example being black absorbing all colors and white reflecting all colors. When light irradiates the surface of the object to be identified, the special pattern printed on the object to be identified is made of a reflective material, so that light reflection can occur after irradiation.

Based on the above principle, in order to improve the recognition accuracy, the present embodiment recognizes the object by using the intensity of the reflected light in addition to the recognition of the above-described special pattern. Specifically, the object recognition device provided by this embodiment further includes an illumination module and a light collection module. The light collection module is used for collecting reflected light of the light irradiated on the object to be identified. The output end of the light collection module is connected with the input end of the identification module.

In this embodiment, the light collection module includes a light sensor. The light sensor converts the collected reflected light into an electric signal and sends the electric signal to the identification module. In order to better process the electric signal, the identification module further comprises an amplifier for amplifying the electric signal, the output end of the optical sensor is connected with the input end of the amplifier, and the output end of the amplifier is connected with the input end of the microprocessor.

Because the different colours of waiting to discern the special pattern of printing on the object are different, therefore the reflectivity is different, and the reflectivity is reflection light intensity/incident light intensity, and if the light intensity that lighting module sent is unchangeable, incident light intensity is unchangeable promptly, then the intensity of the reflection light of different objects is also different. The reflected light of different intensity passes through light sensor collection, converts the reflected light of different intensity into the signal of telecommunication, sends identification module. Different electrical signals represent different objects, an amplifier in the identification module amplifies the electrical signals and then sends the amplified electrical signals to a microprocessor, the microprocessor processes the amplified electrical signals, and different objects can be identified by detecting the size of the electrical signals.

In this embodiment, the lighting module includes an LED lamp, and may be disposed inside the above-mentioned unmanned aerial vehicle shelf. Preferably, the LED lamp adopts an infrared LED lamp, and the light emitted by the infrared LED lamp is stronger, so that the reflection and light collection can be enhanced.

It should be noted here that if the intensity of the light emitted from the LED lamp is not changed, and the reflectance is equal to the reflected light intensity/incident light intensity, and the reflectance is not changed for the printed pattern made of a general reflective material, the intensity of the reflected light is not changed, and thus the object can be accurately identified. However, in some objects packaged by special materials (such as polymer materials), the wavelength and reflectivity of the reflected light may change, and the intensity of the reflected light may also change, which may cause false recognition. For example, the following steps are carried out: the wavelength of the light emitted by the LED lamp is A (fixed), the object B can be identified as the object B ', the object C can be identified as the object C', and the judgment can be more accurate by combining the identification of the special pattern.

Because the object recognition device of the embodiment utilizes light reflection, the camera does not necessarily need to shoot the object to be recognized, so that the requirement on the position of the camera is not strict, and the false recognition caused by lens shielding and the like is avoided.

While the preferred embodiments of the present invention have been described, the present invention is not limited to the embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and such equivalent modifications or substitutions are intended to be included within the scope of the present invention as defined by the appended claims.

Claims

1. An object recognition device is characterized by comprising an object to be recognized, an image acquisition module for acquiring an image of the object to be recognized, and a recognition module for recognizing the object to be recognized, wherein the output end of the image acquisition module is connected with the input end of the recognition module;

2. An object recognition device according to claim 1, wherein the recognition module comprises a microprocessor, and wherein the output of the image capture module is connected to the input of the microprocessor.

3. The object identifying device of claim 2, wherein the special pattern is made of a reflective material.

4. An object recognition device according to claim 3, wherein the device further comprises an illumination module for illuminating the object to be recognized.

5. An object recognition device according to claim 4, further comprising a light collection module, wherein an output end of the light collection module is connected to an input end of the recognition module, and the light collection module is configured to collect reflected light of the light irradiated on the object to be recognized.

6. An object recognition device according to claim 5, wherein the light collection module comprises a light sensor, the recognition module further comprising an amplifier, an output of the light sensor being coupled to an input of the amplifier, and an output of the amplifier being coupled to an input of the microprocessor.

7. An object recognition device according to claim 4, wherein the illumination module comprises an LED lamp.

8. An object recognition device according to any one of claims 1 to 7, wherein the image capture module comprises a camera, and an output of the camera is connected to an input of the recognition module.