WO2022116675A1

WO2022116675A1 - Object detection method and apparatus, storage medium, and electronic device

Info

Publication number: WO2022116675A1
Application number: PCT/CN2021/122451
Authority: WO
Inventors: 骆磊; 黄晓庆
Original assignee: 达闼机器人股份有限公司
Priority date: 2020-12-02
Filing date: 2021-09-30
Publication date: 2022-06-09
Also published as: CN112584015B; CN112584015A

Abstract

The present disclosure relates to an object detection method and apparatus, a storage medium, and an electronic device, the method comprising: on the basis of first pixel information corresponding to a current detection area amongst a plurality of preset detection areas, determining first object features of an object to be detected, each preset detection area being an area composed of target pixel points on an image sensor; when the first object features meet an area switching condition corresponding to the current detection area, determining a target detection area other than the current detection area from the plurality of preset detection areas; and, on the basis of second pixel information corresponding to the target detection area, determining second object features of the object to be detected. In the present disclosure, the power consumption required for performing detection of the object to be detected is low, the cost of the object detection equipment is low, and the weight and volume of the object detection equipment are small. The current detection area can be switched and an appropriate target detection area can be selected for object detection, in order to reduce the power consumption of object detection whilst ensuring the precision of object detection.

Description

Object detection method, device, storage medium and electronic device

CROSS-REFERENCE TO RELATED APPLICATIONS

This disclosure claims the priority of a Chinese patent application entitled "Object Detection Method, Apparatus, Storage Medium, and Electronic Device" with application number 202011406181.X filed with the Chinese Patent Office on December 02, 2020, the entire contents of which are hereby incorporated by reference Incorporated in this disclosure.

technical field

The present disclosure relates to the technical field of object detection, and in particular, to an object detection method, apparatus, storage medium and electronic device.

Background technique

With the continuous progress of science and technology and the continuous development of robotics, various types of robots are widely used in many fields. In some specific application scenarios, the robot is usually required to have functions such as navigation, obstacle avoidance, and capture (for example, an intelligent sweeping robot), which requires the robot to be able to detect objects in the surrounding environment. In the related art, ultrasonic, infrared, laser radar and other sensing devices are mainly used as the navigation obstacle avoidance device of the robot, and object detection is realized through the navigation obstacle avoidance device. However, using these sensing devices as navigation and obstacle avoidance devices has various drawbacks. For example, ultrasonic and infrared sensing devices are relatively cheap, but can only detect objects at close range, and when the situation is complicated, the number of object detection failures will be relatively high. Although lidar can detect objects with high accuracy and long detection distance, it is expensive, consumes high power for active scanning, and its volume and weight are relatively large, so it is not suitable for most robots.

SUMMARY OF THE INVENTION

In order to solve the problems existing in the related art, the present disclosure provides an object detection method, apparatus, storage medium and electronic device.

In order to achieve the above object, according to a first aspect of the embodiments of the present disclosure, an object detection method is provided, which is applied to an object detection device, the device includes a lens and an image sensor, the lens includes a plurality of first microlenses and a plurality of For the second microlens, the field of view of the first microlens is greater than the field of view of the second microlens, and the method includes:

determining the first object feature of the object to be detected according to the first pixel information corresponding to the current detection area in the plurality of preset detection areas;

Wherein, each of the preset detection areas is an area composed of target pixels on the image sensor, the target pixels corresponding to each of the preset detection areas are different, and the target pixels include the first Pixel points, and/or second pixel points, the first pixel points are pixels included in the projection areas of the first microlenses on the image sensor, and the second pixel points are a plurality of pixel points included in the projection area of the second microlens on the image sensor, and the first pixel information is the pixel point information collected by the target pixel point corresponding to the current detection area;

In the case that the first object feature satisfies the area switching condition corresponding to the current detection area, determining a target detection area other than the current detection area from a plurality of the preset detection areas;

Determine the second object feature of the object to be detected according to second pixel information corresponding to the target detection area, where the second pixel information is pixel point information collected from the target pixel point corresponding to the target detection area .

Optionally, the first object feature includes a first distance between the object to be detected and the object detection device, and a first size and a first moving speed of the object to be detected; the region switching conditions include the following: Any of the conditions:

The first size is smaller than a first size threshold corresponding to the current detection area, or the first size is greater than or equal to a second size threshold corresponding to the current detection area, and the second size threshold is greater than the first size threshold size threshold;

The first distance is greater than the first distance threshold corresponding to the current detection area, or the first distance is less than or equal to the second distance threshold corresponding to the current detection area, and the second distance threshold is smaller than the first distance threshold distance threshold;

The first moving speed is less than the first speed threshold corresponding to the current detection area, or the first moving speed is greater than or equal to the second speed threshold corresponding to the current detection area, and the second speed threshold is greater than the first speed threshold.

Optionally, the method further includes:

In the case that the first object feature does not satisfy the region switching condition corresponding to the current detection region, the first object feature is used as the second object feature.

Optionally, the preset detection area includes a large field of view detection area, a small field of view detection area and a full-lens detection area, and the target pixel corresponding to the large field of view detection area includes the first pixel. The target pixel point corresponding to the small field of view detection area includes the second pixel point, and the all-lens detection area includes the large field of view detection area and the small field of view detection area.

Optionally, the number of the target pixels corresponding to the all-lens detection area is greater than the small field of view detection area, and the number of the target pixels corresponding to the small field of view detection area is greater than the large field of view. detection area.

According to a second aspect of the embodiments of the present disclosure, there is provided an object detection apparatus, which is applied to an object detection device, the device includes a lens and an image sensor, the lens includes a plurality of first microlenses and a plurality of second microlenses, The angle of view of the first microlens is greater than the angle of view of the second microlens, and the device includes:

a processing module, configured to determine the first object feature of the object to be detected according to the first pixel information corresponding to the current detection area in the plurality of preset detection areas;

a determination module, configured to determine a target detection area other than the current detection area from a plurality of the preset detection areas when the first object feature satisfies the area switching condition corresponding to the current detection area;

The processing module is further configured to determine a second object feature of the object to be detected according to second pixel information corresponding to the target detection area, where the second pixel information is the target corresponding to the target detection area The pixel point information collected by the pixel point.

Optionally, the processing module is further configured to use the first object feature as the second object feature when the first object feature does not satisfy the region switching condition corresponding to the current detection region.

According to a third aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the steps of the object detection method provided in the first aspect.

According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic device, comprising:

a memory on which a computer program is stored;

A processor, configured to execute the computer program in the memory, to implement the steps of the object detection method provided by the first aspect.

Through the above technical solutions, the present disclosure first determines the first object feature of the object to be detected by first pixel information collected according to the target pixel point corresponding to the current detection area in the plurality of preset detection areas, wherein each preset detection area is The area is an area composed of target pixels on the image sensor. The target pixels corresponding to each preset detection area are different. The target pixels include the first pixel and/or the second pixel. Under the condition that the area switching condition corresponding to the current detection area is satisfied, a target detection area other than the current detection area is determined from a plurality of preset detection areas, and the second pixel information is collected according to the target pixel points corresponding to the target detection area, A second object characteristic of the object to be detected is determined. The present disclosure divides a plurality of preset detection areas corresponding to different numbers of target pixel points through the first microlens and the second microlens, and determines the second object feature of the object to be detected by using the second pixel information corresponding to the target detection area , can realize the accurate detection of the object to be detected under the condition of low power consumption, and at the same time, the structure of the object detection device is simple, and the cost, weight and volume of the object detection device are reduced. In addition, the current detection area can be switched, and an appropriate target detection area can be selected for object detection, so as to reduce the power consumption of object detection while ensuring the object detection accuracy.

Other features and advantages of the present disclosure will be described in detail in the detailed description that follows.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification, and together with the following detailed description, are used to explain the present disclosure, but not to limit the present disclosure. In the attached image:

FIG. 1 is a flowchart of an object detection method according to an exemplary embodiment;

FIG. 2 is a schematic diagram of the field of view of a first microlens and a second microlens according to an exemplary embodiment;

FIG. 3 is a flowchart illustrating another object detection method according to an exemplary embodiment;

FIG. 4 is a schematic diagram showing the distribution of a first microlens and a second microlens according to an exemplary embodiment;

FIG. 5 is a block diagram of an object detection apparatus according to an exemplary embodiment;

Fig. 6 is a block diagram of an electronic device provided according to an exemplary embodiment.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as recited in the appended claims.

Before introducing the object detection method, apparatus, storage medium, and electronic device provided by the present disclosure, the application scenarios involved in the various embodiments of the present disclosure are first introduced. The application scenario is to use object detection equipment to detect objects to be detected in the surrounding environment. Wherein, the object detection device may be provided on the terminal device, and the object detection device may include a lens and an image sensor. The image sensor is located on the side corresponding to the image-side surface of the lens, and has an imaging surface facing the image-side surface. The imaging surface is composed of multiple pixels. The lens and the image sensor can be completely fitted together, or they can be separated by a certain interval. the distance. The lens can be a flat lens or a curved lens, and the image sensor can be a CMOS (English: Complementary Metal-Oxide-Semiconductor, Chinese: Complementary Metal Oxide Semiconductor) sensor, or a CCD (English: Charge-coupled Device, Chinese: Charge Coupled Device) element), or any other photosensitive sensor, which is not specifically limited in the present disclosure. The terminal device may be, for example, a terminal device such as a smart robot, a smart phone, a tablet computer, a smart watch, and a smart bracelet.

Fig. 1 is a flow chart of an object detection method according to an exemplary embodiment. As shown in FIG. 1, applied to an object detection device, the device includes a lens and an image sensor, the lens includes a plurality of first microlenses and a plurality of second microlenses, and the field angle of the first microlens is larger than that of the second microlens the field of view, the method may include the following steps:

Step 101: Determine a first object feature of an object to be detected according to the first pixel information corresponding to the current detection area in the plurality of preset detection areas.

Wherein, each preset detection area is an area composed of target pixels on the image sensor, the target pixels corresponding to each preset detection area are different, and the target pixels include first pixels and/or second pixels , the first pixel is the pixel included in the projection area of the plurality of first microlenses on the image sensor, the second pixel is the pixel included in the projection area of the plurality of second microlenses on the image sensor, and the first pixel The information is the pixel point information collected by the target pixel point corresponding to the current detection area.

For example, in order to avoid the shortcomings of using ultrasonic, infrared, lidar and other sensing devices for object detection, a new sensing device can be constructed through lenses and image sensors for object detection. Specifically, first, the lens may be divided into a plurality of first microlenses and a plurality of second microlenses arranged in a grid format. For example, a plurality of first micro-lenses and a plurality of second micro-lenses in a mesh format can be formed on the lens by photolithography (or other techniques), or a plurality of first micro-lenses in a mesh format can be formed on the lens by a layer of nano-film a microlens and a plurality of second microlenses.

Wherein, each first microlens corresponds to one or more first pixels on the image sensor, and the first pixels corresponding to each first microlens are the pixels included in the projection area of the first microlens on the image sensor point. When a certain first microlens captures the object to be detected, imaging is performed on the first pixel point corresponding to the first microlens. Each second microlens corresponds to one or more second pixels on the image sensor, and the second pixels corresponding to each second microlens are pixels included in the projection area of the second microlens on the image sensor. When a second microlens captures the object to be detected, it will image on the second pixel point corresponding to the second microlens. The FOV (English: Field of View, Chinese: Field of View) of the first microlens is greater than the FOV of the second microlens, as shown in FIG. 2 , the dotted line in FIG. 2 is the FOV of the first microlens, and the The solid line is the FOV of the second microlens.

Then, the imaging surface of the image sensor can be divided into a plurality of preset detection areas according to the type of pixel points (first pixel point or second pixel point), and each preset detection area can be an area composed of target pixel points . The target pixels corresponding to each preset detection area are different, and the number of target pixels is different. The target pixels may include the first pixel and/or the second pixel, that is, the target pixel corresponding to the preset detection area may Only the first pixel is included, only the second pixel may be included, or both the first pixel and the second pixel may be included. When the object detection device detects the object to be detected, a preset detection area may be selected from a plurality of preset detection areas as the current detection area, and the first pixel information collected by the target pixel points corresponding to the current detection area, Calculate the first object feature of the object to be detected. The first pixel information may include the pixel value of each target pixel corresponding to the current detection area, and the first object feature may include the first distance between the object to be detected and the object detection device, and the first size and first movement of the object to be detected. speed. Wherein, for a specific implementation manner of calculating the first object feature according to the first pixel information, reference may be made to the manner described in the related art, which will not be described in detail here.

Step 102 , in the case that the first object feature satisfies the area switching condition corresponding to the current detection area, determine a target detection area other than the current detection area from a plurality of preset detection areas.

For example, when the object to be detected is detected by the target pixels corresponding to different preset detection areas, the number of target pixels used is different, and the data amount of pixel information collected by the target pixels is different, which will lead to Target pixels corresponding to different preset detection areas have different resolution and power consumption for detecting the object to be detected. Wherein, the greater the number of target pixel points corresponding to the preset detection area, the higher the resolving power of detecting the object to be detected, and the higher the power consumption of detecting the object to be detected at the same time. The resolving power can reflect the performance of detecting the object to be detected. The higher the resolving power, the better the performance of detecting the object to be detected, that is, the higher the detection accuracy of the object to be detected.

Therefore, the area switching conditions corresponding to each preset detection area can be preset, so that when the object detection device detects the object to be detected through the target pixel point corresponding to each preset detection area, it can determine that the preset detection area is to be detected. Whether the resolving power of the object for detection is insufficient or the resolving power is excessive. The area switching condition corresponding to each preset detection area may be set according to the distance range between the object to be detected and the object detection device that can be detected by the preset detection area, as well as the size range and moving speed range of the object to be detected. When the first object feature satisfies the area switching condition corresponding to the current detection area, it means that the resolution power to detect the object to be detected by the target pixel point corresponding to the current detection area is insufficient or excessive, and the current detection area needs to be switched. When it is determined that the resolution of the target pixel corresponding to the current detection area to detect the object to be detected is insufficient, a preset detection area with a higher resolution may be selected from a plurality of preset detection areas as the target detection area (that is, select the target pixel point more preset detection areas) to detect objects to be detected. When it is determined that the resolution power of the target pixel corresponding to the current detection area to detect the object to be detected is excessive, a preset detection area with a smaller resolution can be selected from a plurality of preset detection areas as the target detection area to perform the detection of the object to be detected. Detection, that is, selecting a preset detection area with a smaller number of target pixels to detect the object to be detected, thereby reducing the power consumption of detecting the object to be detected. By switching the current detection area to the target detection area, the power consumption of object detection can be reduced while ensuring the object detection performance (detection accuracy), so as to meet the needs of different scenarios.

Step 103: Determine the second object feature of the object to be detected according to the second pixel information corresponding to the target detection area, where the second pixel information is pixel point information collected from the target pixel point corresponding to the target detection area.

In this step, the second object feature of the object to be detected may be calculated according to the second pixel information collected from the target pixel point corresponding to the target detection area. The second object characteristic may include a second distance of the object to be detected from the object detection device, and a second size and a second moving speed of the object to be detected. For a specific implementation manner of calculating the second object feature according to the second pixel information, reference may be made to the manner described in the related art, which will not be described in detail here.

To sum up, the present disclosure first determines the first object feature of the object to be detected by first pixel information collected according to the target pixel point corresponding to the current detection area in the plurality of preset detection areas, wherein each preset detection area The area is an area composed of target pixels on the image sensor. The target pixels corresponding to each preset detection area are different. The target pixels include the first pixel and/or the second pixel. Under the condition that the area switching condition corresponding to the current detection area is satisfied, a target detection area other than the current detection area is determined from a plurality of preset detection areas, and the second pixel information is collected according to the target pixel points corresponding to the target detection area, A second object characteristic of the object to be detected is determined. The present disclosure divides a plurality of preset detection areas corresponding to different numbers of target pixel points through the first microlens and the second microlens, and determines the second object feature of the object to be detected by using the second pixel information corresponding to the target detection area , can realize the accurate detection of the object to be detected under the condition of low power consumption, and at the same time, the structure of the object detection device is simple, and the cost, weight and volume of the object detection device are reduced. In addition, the current detection area can be switched, and an appropriate target detection area can be selected for object detection, so as to reduce the power consumption of object detection while ensuring the object detection accuracy.

Fig. 3 is a flowchart showing another object detection method according to an exemplary embodiment. As shown in Figure 3, the method further includes the following steps:

Step 104 , in the case that the first object feature does not satisfy the region switching condition corresponding to the current detection region, the first object feature is used as the second object feature.

For example, in the case that the first object feature does not meet the area switching condition corresponding to the current detection area, it means that the resolution power of detecting the object to be detected through the target pixel point corresponding to the current detection area meets the requirements, and the resolution power is not excessive, There is no need to switch the current detection area. The first object feature can be directly used as the second object feature.

Optionally, the first object feature includes a first distance between the object to be detected and the object detection device, and a first size and a first moving speed of the object to be detected, and the area switching condition may include any of the following conditions:

1) The first size is smaller than the first size threshold corresponding to the current detection area, or the first size is greater than or equal to the second size threshold corresponding to the current detection area, and the second size threshold is greater than the first size threshold.

2) The first distance is greater than the first distance threshold corresponding to the current detection area, or the first distance is less than or equal to the second distance threshold corresponding to the current detection area, and the second distance threshold is smaller than the first distance threshold.

3) The first moving speed is less than the first speed threshold corresponding to the current detection area, or the first moving speed is greater than or equal to the second speed threshold corresponding to the current detection area, and the second speed threshold is greater than the first speed threshold.

For example, the first size threshold is the minimum size of the object to be detected that can be detected in the current detection area, the first distance threshold is the maximum distance between the object to be detected and the object detection device that can be detected in the current detection area, and the first speed threshold is The minimum speed of the object to be detected that can be detected in the current detection area. When the first size is smaller than the first size threshold corresponding to the current detection area, the first distance is greater than the first distance threshold corresponding to the current detection area, and the first moving speed is smaller than the first speed threshold corresponding to the current detection area. , indicating that the target pixel corresponding to the current detection area has insufficient resolving power to detect the object to be detected, and the current detection area needs to be switched.

The second size threshold is the maximum size of the object to be detected that can be detected in the current detection area, the second distance threshold is the minimum distance between the object to be detected and the object detection device that can be detected in the current detection area, and the second speed threshold is the current detection area. The maximum speed of the object to be detected that can be detected. When the first size is greater than or equal to the second size threshold corresponding to the current detection area, the first distance is less than or equal to the second distance threshold corresponding to the current detection area, and the first moving speed is greater than or equal to the second speed threshold corresponding to the current detection area. When any of the conditions are satisfied, it means that the target pixel corresponding to the current detection area has excess resolving power to detect the object to be detected, and the current detection area needs to be switched.

Further, the shape and size of the first microlens and the second microlens may be the same or different.

In one scenario, the lens may be divided into a plurality of first microlenses and a plurality of second microlenses which are arranged in a grid format and have the same shape and size according to a preset arrangement. The preset arrangement can be, for example, that the first microlenses and the second microlenses are evenly distributed on the lens according to a certain ratio. The distribution of the micro-lens and the second micro-lens on the lens can be shown in Figure 4. The smallest square in Figure 4 corresponds to one pixel. The nine-square grid filled with shadows in Figure 4 is the first micro-lens. Figure 4 The nine-square grid surrounded by dotted lines is the second microlens.

Optionally, the preset detection area includes a large field of view detection area, a small field of view detection area and a full-lens detection area, the target pixel point corresponding to the large field of view detection area includes the first pixel point, and the small field of view detection area corresponds to The target pixel point includes the second pixel point, and the full-lens detection area includes a detection area with a large field of view and a detection area with a small field of view.

In another scenario, if the number of the first microlenses included on the lens is greater than the number of the second microlenses, the number of target pixels corresponding to the full-lens detection area is greater than the small field of view detection area, and the small field of view detects The number of target pixels corresponding to the area is larger than the detection area with a large field of view. Then the relationship between the resolution power of the detection area with large field of view, the detection area with small field of view and the full-lens detection area is: full-lens detection area > detection area with small field of view > detection area with large field of view, and the power consumption relationship is: : full-lens detection area < small field of view detection area < large field of view detection area.

The preset detection area includes a large field of view detection area, a small field of view detection area and a full-lens detection area, and the number of first microlenses on the lens is greater than the number of second microlenses. After startup, the user can manually select a preset detection area from the detection area with a large field of view, a detection area with a small field of view, and a full-lens detection area as the current detection area to detect the object to be detected. The method of automatic selection can also be adopted. For example, the detection area with a large field of view can be selected by default, and then the first pixel information of the target pixel corresponding to the detection area with a large field of view can be used to calculate the first object of the object to be detected. feature, and determine whether the feature of the first object satisfies the region switching condition corresponding to the detection region with a large field of view. If it is determined that the first size is smaller than the first size threshold corresponding to the detection area with a large field of view, the first distance is greater than the first distance threshold corresponding to the detection area with a large field of view, and the first moving speed is smaller than the first distance corresponding to the detection area with a large field of view. Any one of the speed thresholds is satisfied (at this time, the resolution of the target pixel corresponding to the detection area with a large field of view is insufficient to detect the object to be detected, and the appearance is that the pixel value of the adjacent target pixel has a large difference or pixel value. change too slowly), switch the detection area with a large field of view to a detection area with a small field of view.

Then, through the first pixel information collected from the target pixel points corresponding to the detection area with small field of view, the first object feature of the object to be detected is recalculated, and it is judged whether the recalculated first object feature satisfies the area corresponding to the detection area with small field of view switch condition. If it is judged that the recalculated first size is smaller than the first size threshold corresponding to the small field of view detection area, the recalculated first distance is greater than the first distance threshold corresponding to the small field of view detection area, and the recalculated first moving speed is smaller than the small field of view Any one of the first speed thresholds corresponding to the angle detection area is satisfied (at this time, the target pixel corresponding to the small field of view detection area has insufficient resolving power to detect the object to be detected, and the appearance is that the pixel value difference between adjacent target pixel points larger), switch the detection area with small field of view to the full-lens detection area.

Then, the first object feature of the object to be detected is recalculated through the first pixel information collected from the target pixel point corresponding to the full-lens detection area, and it is judged whether the recalculated first object feature satisfies the area switching conditions corresponding to the full-lens detection area . If it is determined that the recalculated first size is greater than or equal to the second size threshold corresponding to the current detection area, the recalculated first distance is less than or equal to the second distance threshold corresponding to the current detection area, and the recalculated first moving speed is greater than or equal to Any one of the second velocity thresholds corresponding to the current detection area satisfies (at this time, the target pixels corresponding to the full-lens detection area have excessive resolving power to detect the object to be detected, and the appearance is that the difference in pixel values of adjacent target pixels is relatively high. small), switch the full-lens detection area to the small field of view detection area.

Fig. 5 is a block diagram of an object detection apparatus according to an exemplary embodiment. As shown in FIG. 5 , applied to an object detection device, the device includes a lens and an image sensor, the lens includes a plurality of first microlenses and a plurality of second microlenses, and the field angle of the first microlens is larger than that of the second microlens The field of view, the device 200 includes:

The processing module 201 is configured to determine the first object feature of the object to be detected according to the first pixel information corresponding to the current detection area in the plurality of preset detection areas.

The determining module 202 is configured to determine a target detection area other than the current detection area from a plurality of preset detection areas under the condition that the first object feature satisfies the area switching condition corresponding to the current detection area.

The processing module 201 is further configured to determine the second object feature of the object to be detected according to the second pixel information corresponding to the target detection area, where the second pixel information is pixel point information collected from the target pixel point corresponding to the target detection area.

Optionally, the first object feature includes a first distance between the object to be detected and the object detection device, and a first size and a first moving speed of the object to be detected. Region switching conditions include any of the following conditions:

1) The second size is smaller than the first size threshold corresponding to the current detection area, or the second size is greater than or equal to the second size threshold corresponding to the current detection area, and the second size threshold is greater than the first size threshold.

2) The second distance is greater than the first distance threshold corresponding to the current detection area, or the second distance is less than or equal to the second distance threshold corresponding to the current detection area, and the second distance threshold is smaller than the first distance threshold.

3) The second moving speed is less than the first speed threshold corresponding to the current detection area, or the second moving speed is greater than or equal to the second speed threshold corresponding to the current detection area, and the second speed threshold is greater than the first speed threshold.

Optionally, the processing module 201 is further configured to use the first object feature as the second object feature when the first object feature does not satisfy the region switching condition corresponding to the current detection region.

Optionally, the number of target pixels corresponding to the full-lens detection area is larger than that of the small field of view detection area, and the number of target pixels corresponding to the small field of view detection area is larger than the large field of view detection area.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

To sum up, the present disclosure first determines the first object feature of the object to be detected by first pixel information collected according to the target pixel point corresponding to the current detection area in the plurality of preset detection areas, wherein each preset detection area The area is an area composed of target pixels on the image sensor. The target pixels corresponding to each preset detection area are different. The target pixels include the first pixel and/or the second pixel. Under the condition that the area switching condition corresponding to the current detection area is satisfied, a target detection area other than the current detection area is determined from a plurality of preset detection areas, and the second pixel information is collected according to the target pixel points corresponding to the target detection area, A second object characteristic of the object to be detected is determined. The present disclosure divides a plurality of preset detection areas corresponding to different numbers of target pixel points through the first microlens and the second microlens, and determines the second object feature of the object to be detected through the second pixel information corresponding to the target detection area , can realize the accurate detection of the object to be detected under the condition of low power consumption, and at the same time, the structure of the object detection device is simple, and the cost, weight and volume of the object detection device are reduced. In addition, the current detection area can be switched, and an appropriate target detection area can be selected for object detection, so as to reduce the power consumption of object detection while ensuring the object detection accuracy.

FIG. 6 is a block diagram of an electronic device 700 according to an exemplary embodiment. As shown in FIG. 6 , the electronic device 700 may include: a processor 701 and a memory 702 . The electronic device 700 may also include one or more of a multimedia component 703 , an input/output (I/O) interface 704 , and a communication component 705 .

Wherein, the processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned object detection method. The memory 702 is used to store various types of data to support operations on the electronic device 700, such data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data, Such as contact data, messages sent and received, pictures, audio, video, and so on. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM for short), electrically erasable programmable read-only memory ( Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read-Only Memory (EPROM for short), Programmable Read-Only Memory (PROM for short), read-only Memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. Multimedia components 703 may include screen and audio components. Wherein the screen can be, for example, a touch screen, and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in memory 702 or transmitted through communication component 705 . The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, a button, and the like. These buttons can be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or more of them The combination is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module and so on.

In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), digital signal processors (Digital Signal Processor, DSP for short), digital signal processing devices (Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic components Implementation is used to implement the above object detection method.

In another exemplary embodiment, there is also provided a computer-readable storage medium comprising program instructions, the program instructions implementing the steps of the above-mentioned object detection method when executed by a processor. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to implement the above-mentioned object detection method.

The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details of the above-mentioned embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure. These simple modifications all fall within the protection scope of the present disclosure.

In addition, it should be noted that, the specific technical features described in the above-mentioned specific embodiments can be combined in any suitable manner unless they are inconsistent. In order to avoid unnecessary repetition, the present disclosure provides The combination method will not be specified otherwise.

In addition, the various embodiments of the present disclosure can also be arbitrarily combined, as long as they do not violate the spirit of the present disclosure, they should also be regarded as the contents disclosed in the present disclosure.

Example

1. An object detection method, applied to an object detection device, the device includes a lens and an image sensor, the lens includes a plurality of first microlenses and a plurality of second microlenses, the field of view of the first microlens The angle is greater than the field angle of the second microlens, and the method includes:

2. The method according to Embodiment 1, wherein the first object feature includes a first distance between the object to be detected and the object detection device, and a first size and a first moving speed of the object to be detected; The area switching condition includes any one of the following conditions:

3. The method according to Embodiment 1, further comprising:

4. The method according to any one of Embodiments 1 to 3, wherein the preset detection area includes a detection area with a large field of view, a detection area with a small field of view, and a full-lens detection area, and the large field of view The target pixel point corresponding to the angle detection area includes the first pixel point, the target pixel point corresponding to the small field-of-view detection area includes the second pixel point, and the full-lens detection area includes the large angle detection area. A viewing angle detection area and the small viewing angle detection area.

5. According to the method according to Embodiment 4, the number of the target pixels corresponding to the all-lens detection area is greater than that of the small field of view detection area, and the number of the target pixels corresponding to the small field of view detection area larger than the detection area of the large field of view.

6. An object detection device, applied to an object detection device, the device includes a lens and an image sensor, the lens includes a plurality of first microlenses and a plurality of second microlenses, the field of view of the first microlens The angle is greater than the field angle of the second microlens, and the device includes:

7. The apparatus according to Embodiment 6, wherein the first object characteristic includes a first distance between the object to be detected and the object detection device, and a first size and a first moving speed of the object to be detected; The area switching condition includes any one of the following conditions:

8. The apparatus according to Embodiment 6, wherein the processing module is further configured to use the first object feature as the second object feature.

9. A computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the steps of the method described in any one of Embodiments 1 to 5.

10. An electronic device comprising:

a memory on which a computer program is stored;

A processor, configured to execute the computer program in the memory, to implement the steps of the method in any one of Embodiments 1 to 5.

Claims

An object detection method, characterized in that it is applied to an object detection device, the device includes a lens and an image sensor, the lens includes a plurality of first microlenses and a plurality of second microlenses, and the first microlens has a The angle of view is greater than the angle of view of the second microlens, and the method includes:

determining the first object feature of the object to be detected according to the first pixel information corresponding to the current detection area in the plurality of preset detection areas;

Wherein, each of the preset detection areas is an area composed of target pixels on the image sensor, the target pixels corresponding to each of the preset detection areas are different, and the target pixels include the first Pixel points, and/or second pixel points, the first pixel points are the pixel points included in the projection area of the first microlenses on the image sensor, and the second pixel points are a plurality of all the pixel points. The pixel points included in the projection area of the second microlens on the image sensor, and the first pixel information is the pixel point information collected by the target pixel point corresponding to the current detection area;

In the case that the first object feature satisfies the area switching condition corresponding to the current detection area, determining a target detection area other than the current detection area from a plurality of the preset detection areas;

Determine the second object feature of the object to be detected according to second pixel information corresponding to the target detection area, where the second pixel information is pixel point information collected from the target pixel point corresponding to the target detection area .
The method of claim 1, wherein the first object characteristic includes a first distance between the object to be detected and the object detection device, and a first size and a first movement of the object to be detected Speed; the zone switching condition includes any of the following conditions:

The first size is smaller than a first size threshold corresponding to the current detection area, or the first size is greater than or equal to a second size threshold corresponding to the current detection area, and the second size threshold is greater than the first size threshold size threshold;

The first distance is greater than the first distance threshold corresponding to the current detection area, or the first distance is less than or equal to the second distance threshold corresponding to the current detection area, and the second distance threshold is smaller than the first distance threshold distance threshold;

The first moving speed is less than the first speed threshold corresponding to the current detection area, or the first moving speed is greater than or equal to the second speed threshold corresponding to the current detection area, and the second speed threshold is greater than the first speed threshold.
The method according to claim 1, wherein the method further comprises:

In the case that the first object feature does not satisfy the region switching condition corresponding to the current detection region, the first object feature is used as the second object feature.
The method according to any one of claims 1-3, wherein the preset detection area includes a large field of view detection area, a small field of view detection area and an all-lens detection area, and the large field of view detection area The target pixel point corresponding to the detection area includes the first pixel point, the target pixel point corresponding to the small field-of-view detection area includes the second pixel point, and the full-lens detection area includes the large viewing area. The field angle detection area and the small field angle detection area.
The method according to claim 4, wherein the number of the target pixels corresponding to the all-lens detection area is greater than that of the small field of view detection area, and the target pixels corresponding to the small field of view detection area The number of points is larger than the detection area of the large field of view.
An object detection device is characterized in that it is applied to an object detection device, the device includes a lens and an image sensor, the lens includes a plurality of first microlenses and a plurality of second microlenses, and the first microlens has a The angle of view is greater than the angle of view of the second microlens, and the device includes:

a processing module, configured to determine the first object feature of the object to be detected according to the first pixel information corresponding to the current detection area in the plurality of preset detection areas;

Wherein, each of the preset detection areas is an area composed of target pixels on the image sensor, the target pixels corresponding to each of the preset detection areas are different, and the target pixels include the first Pixel points, and/or second pixel points, the first pixel points are the pixel points included in the projection area of the first microlenses on the image sensor, and the second pixel points are a plurality of all the pixel points. The pixel points included in the projection area of the second microlens on the image sensor, and the first pixel information is the pixel point information collected by the target pixel point corresponding to the current detection area;

a determination module, configured to determine a target detection area other than the current detection area from a plurality of the preset detection areas when the first object feature satisfies the area switching condition corresponding to the current detection area;

The processing module is further configured to determine a second object feature of the object to be detected according to second pixel information corresponding to the target detection area, where the second pixel information is the target corresponding to the target detection area The pixel point information collected by the pixel point.
The apparatus according to claim 6, wherein the first object characteristic includes a first distance between the object to be detected and the object detection device, and a first size and a first movement of the object to be detected Speed; the zone switching condition includes any of the following conditions:

The first size is smaller than a first size threshold corresponding to the current detection area, or the first size is greater than or equal to a second size threshold corresponding to the current detection area, and the second size threshold is greater than the first size threshold size threshold;

The first distance is greater than the first distance threshold corresponding to the current detection area, or the first distance is less than or equal to the second distance threshold corresponding to the current detection area, and the second distance threshold is smaller than the first distance threshold distance threshold;

The first moving speed is less than the first speed threshold corresponding to the current detection area, or the first moving speed is greater than or equal to the second speed threshold corresponding to the current detection area, and the second speed threshold is greater than the first speed threshold.
The device according to claim 6, wherein the processing module is further configured to convert the first object into feature as the second object feature.
A computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the steps of the method according to any one of claims 1-5 are implemented.
An electronic device, comprising:

a memory on which a computer program is stored;

A processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-5.