CN114114228A

CN114114228A - Method and device for detecting object in vehicle

Info

Publication number: CN114114228A
Application number: CN202010901248.0A
Authority: CN
Inventors: 邱子文; 孙根本; 林松青; 王志威; 周维成
Original assignee: Faurecia Clarion Electronics Xiamen Co Ltd
Current assignee: Faurecia Clarion Electronics Xiamen Co Ltd
Priority date: 2020-08-31
Filing date: 2020-08-31
Publication date: 2022-03-01
Also published as: DE102021122396A1

Abstract

The application discloses a method and a device for detecting an object in a vehicle, relates to the field of radar detection, and is used for reducing the probability of object detection errors in the vehicle and improving the detection accuracy. The in-vehicle object detection method includes: acquiring an object detection result, a first confidence coefficient, an object detection result in a first stage and a second confidence coefficient of a current stage; and determining whether the object exists in the vehicle at the current stage based on the object detection result at the current stage, the first confidence degree, the object detection result at the first stage and the second confidence degree. According to the method, when whether the object exists in the current stage or not is determined, the confidence coefficient of the object detection result in the current stage, the detection result in the stage before the current stage and the confidence coefficient of the detection result in the stage before the current stage are combined, and compared with the method that whether the object exists or not is determined based on one detection result in the prior art, the probability of object detection errors in a vehicle can be reduced, and the detection accuracy is effectively improved.

Description

Method and device for detecting object in vehicle

Technical Field

The present application relates to the field of radar detection, and in particular, to a method and an apparatus for detecting an object in a vehicle.

Background

Currently, in the detection of an occupant in a vehicle, the presence of an occupant in a seat is determined by comparing the intensity of a radar signal reflected from the seat with the intensity of a signal reflected from the occupant, and radars that provide radar signals typically include a single transmitter and a single receiver.

Because the space inside the vehicle is narrow and small, radar signals can be reflected for many times after being transmitted, and different reflected signals are mutually interfered, so that detection errors are caused.

Disclosure of Invention

The application provides a vehicle driver and passenger detection method and device, which are used for solving the problem of detection error caused by mutual crosstalk between different reflected signals after radar signals are transmitted through multiple reflections in the prior art.

In order to achieve the purpose, the technical scheme is as follows:

in a first aspect, the present application provides a method of detecting an object in a vehicle, the method comprising: acquiring an object detection result of a current stage, a first confidence coefficient, an object detection result of a first stage and a second confidence coefficient, wherein the first confidence coefficient is used for representing the accuracy of the object detection result of the current stage, the second confidence coefficient is used for representing the accuracy of the object detection result of the first stage, the current stage and the first stage are both stages in a driving cycle of a vehicle, and the first stage is located before the current stage, and different stages in the driving cycle of the vehicle are triggered by different preset events; and determining whether an object exists in the vehicle at the current stage based on the object detection result at the current stage, the first confidence level, the object detection result at the first stage, and the second confidence level.

According to the method for detecting the object in the vehicle, when whether the object exists in the current stage or not is determined, the confidence degree of the object detection result in the current stage, the detection result in the stage before the current stage and the confidence degree of the detection result in the stage before the current stage are combined. Compared with the prior art that whether the object exists or not is determined based on one detection result, the probability of object detection errors in the vehicle can be reduced, and the detection accuracy is effectively improved.

In a second aspect, the present application provides a detection apparatus for an object in a vehicle, the detection apparatus comprising: the device comprises an acquisition unit and a determination unit.

The above-mentioned obtaining unit is configured to obtain an object detection result of a current stage, a first confidence level, an object detection result of a first stage, and a second confidence level, where the first confidence level is used to characterize an accuracy of the object detection result of the current stage, the second confidence level is used to characterize an accuracy of the object detection result of the first stage, the current stage and the first stage are both stages within a driving cycle of the vehicle, and the first stage is located before the current stage, and different stages within the driving cycle of the vehicle are triggered by different preset events. The determining unit is configured to determine whether an object exists in the vehicle at the current stage based on the object detection result at the current stage, the first confidence level, the object detection result at the first stage, and the second confidence level, which are acquired by the acquiring unit.

In a third aspect, the present application provides a detection device for an object in a vehicle, the detection device comprising a memory and a processor. The memory is coupled to the processor. The memory is for storing computer program code comprising computer instructions. The detection device for an object in a vehicle, when the processor executes the computer instructions, performs the method for detecting an object in a vehicle as set forth in the first aspect and any one of its possible designs.

In a fourth aspect, the present application provides a computer-readable storage medium having stored therein instructions, which, when run on an apparatus for detecting an object in a vehicle, cause the apparatus to perform a method for detecting an object in a vehicle as set forth in the first aspect and any one of its possible designs.

In a fifth aspect, the present application provides a computer program product comprising computer instructions which, when run on a detection apparatus for an object in a vehicle, cause the detection apparatus for the object in the vehicle to perform the method for detecting an object in a vehicle as set forth in the first aspect and any one of its possible designs.

For a detailed description of the second to fifth aspects and their various implementations in this application, reference may be made to the detailed description of the first aspect and its various implementations; moreover, the beneficial effects of the second aspect to the fifth aspect and the various implementation manners thereof may refer to the beneficial effect analysis of the first aspect and the various implementation manners thereof, and are not described herein again.

These and other aspects of the present application will be more readily apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic diagram of formal period division provided in an embodiment of the present application;

fig. 2 is a first schematic flowchart of a method for detecting an object in a vehicle according to an embodiment of the present disclosure;

fig. 3 is a second schematic flowchart of a method for detecting an object in a vehicle according to an embodiment of the present application;

fig. 4 is a third schematic flowchart of a method for detecting an object in a vehicle according to an embodiment of the present application;

fig. 5 is a schematic hardware configuration diagram of a device for detecting an object in a vehicle according to an embodiment of the present application;

fig. 6 is a first schematic structural diagram of a device for detecting an object in a vehicle according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of a second detection apparatus for an object in a vehicle according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless otherwise specified.

In the prior art, the transmission and reception of radar signals is accomplished by a single transmitter and a single receiver to determine whether there is a riding member in the seat. And the space inside the vehicle is narrow and small, can pass through multiple reflection after the radar signal transmission, and different reflection signals are intercrossed to cause the detection error.

In view of the above problems, the present application provides a method for detecting an object in a vehicle, which divides a driving cycle of the vehicle into different phases. In this way, when determining whether an object exists in the current stage, it may be determined whether an object exists in the vehicle in the current stage based on the object detection result in the current stage, the confidence (first confidence) of the object detection result in the current stage, the object detection result in the first stage, and the confidence (second confidence) of the object detection result in the first stage. Compared with the prior art that whether the object exists or not is determined based on one detection result, the scheme of the application can reduce the probability of object detection errors in the vehicle and effectively improve the detection accuracy.

The execution subject of the detection method provided by the embodiment of the application is a detection device (hereinafter, simply referred to as a detection device) of an object in a vehicle. The vehicle in the embodiment of the application is internally provided with the signal transceiving equipment, so that the detection device can detect the object according to the signal received by the signal transceiving equipment. The detection device and the signal transceiver in the vehicle may be integrated together or may be separately disposed, which is not limited in the embodiments of the present application.

The signal transceiving equipment may comprise at least one receiver and at least one transmitter. The number of receivers and the number of transmitters may or may not be equal. The signal transceiver device may be used for transceiving radar signals, may also be used for transceiving infrared signals, and may also be used for transceiving other types of signals, which is not specifically limited in this application.

Illustratively, the signal transceiving equipment is radar equipment, and the radar signals which can be transceived by the radar equipment are millimeter waves. The frequency domain of the millimeter wave is usually 30-300 GHz, and the wavelength of the millimeter wave is between centimeter wave and light wave. Millimeter wave radar has the characteristic of not receiving light and weather interference, can inspect characteristics such as human rhythm of the heart, breathing, also can inspect any removal action such as walking, swing for judge the existence of life signal in the car, shelter from to seat etc. and have the penetrability, can measure the position that life signal exists simultaneously, avoid arousing the wrong report police to the mismeasurement of car outer target.

The detection object according to the embodiment of the present application may be a human being, an animal, or an article such as luggage, but the present application is not limited thereto.

The detection method provided by the embodiment of the application is suitable for detecting the scene of the internal object of the vehicle, specifically can be used for detecting the scene of the internal object when the vehicle is in the running state, and can also be used for detecting the scene of the internal object when the vehicle is in the stopping state. The vehicles related to the embodiment of the application can be cars, trains, subways, buses, ambulances and other trains, and the embodiment of the application is not limited to the above.

As can be seen from the above description, the present application divides the driving cycle of the vehicle into different phases in advance. For ease of understanding, the description will be given first of all of the contents of dividing the travel cycle of the vehicle into different phases.

The starting time of the driving cycle of the vehicle is the time for unlocking the door lock of the vehicle, the ending time of the driving cycle of the vehicle is the time for closing the door lock of the vehicle, and different stages in the driving cycle of the vehicle are triggered by different preset events.

Optionally, the preset event may include unlocking of a vehicle door lock, door opening and closing actions, vehicle driving, and vehicle door locking.

Illustratively, as shown in fig. 1, the driving cycle 01 includes a vehicle door lock opening phase 02, a first door opening and closing action phase 03, a vehicle driving phase 04, a second door opening and closing action phase 05, and a vehicle door lock closing phase 06.

The vehicle door lock opening phase 02 is triggered by the vehicle door lock opening. The starting time of the vehicle door lock opening stage 02 is the time for opening the vehicle door lock, and the ending time of the vehicle door lock opening stage 02 is the time for opening and closing the vehicle door.

The first door opening and closing phase 03 is triggered by the door opening and closing action. The starting time of the first door opening and closing action phase 03 is the time when the vehicle has door opening and closing actions after the vehicle door lock opening phase 02, and the ending time of the first door opening and closing action phase 03 is the starting time of the vehicle driving phase 04.

The vehicle travel phase 04 is triggered by the vehicle travel. The starting time of the vehicle driving phase 04 is the time when the vehicle starts to drive and the vehicle speed reaches the preset speed, and the ending time of the vehicle driving phase 04 is the starting time of the second door opening and closing action phase 05.

Alternatively, the preset speed may be 5 kilometers per hour (km/h).

The second door opening and closing phase 05 is triggered by the door opening and closing action. The starting time of the second door opening and closing action stage 05 is the time when the vehicle has the door opening and closing action after the vehicle driving stage 04, and the ending time of the second door opening and closing action stage 05 is the starting time of the vehicle door lock closing stage 06.

The vehicle door lock closing phase 06 is triggered by the vehicle door lock closing. The starting time of the vehicle door lock closing stage 06 is the time for closing the vehicle door lock, and the ending time of the vehicle door lock closing stage 06 is the time after the preset time length from the time for closing the vehicle door lock.

Alternatively, the vehicle may be in a key-off state when the vehicle is in the vehicle door lock-off phase 06.

Optionally, the preset time period may be 3 to 10 minutes (min), or may be other time periods, which is not limited in this embodiment of the application.

For example, the current phase may be any one of the first door opening and closing phase 03, the vehicle driving phase 04, the second door opening and closing phase 05, and the vehicle door lock closing phase 06.

The first phase may comprise at least one of a vehicle door lock opening phase 02, a first door opening and closing phase 03, a vehicle driving phase 04 and a second door opening and closing phase 05.

The following describes a method for detecting an object in a vehicle according to an embodiment of the present application.

As shown in fig. 2, the detection method includes:

s201, the detection device acquires the object detection result, the first confidence level, the object detection result in the first stage and the second confidence level of the current stage.

The object detection result is that an object exists in the vehicle, or the object detection result is that an object does not exist in the vehicle.

The first confidence is used for characterizing the accuracy of the object detection result of the current stage. The second confidence level is used to characterize the accuracy of the object detection results of the first stage.

For example, the object detection result in the current stage is that the object exists in the vehicle, the first confidence degree is 80%, and the accuracy indicating that the object detection result in the current stage is that the object exists in the vehicle is 80%. The current phase and the first phase are both phases within the driving cycle of the vehicle, and the first phase is located before the current phase. I.e. the start time of the current phase is later than the start time of the first phase.

For example, as shown in fig. 1, if the current phase is a first door opening and closing action phase 03, the first phase may be a vehicle door lock opening phase 02. If the current phase is a vehicle door lock closing phase 06, the first phase may include a vehicle door lock opening phase 02, a first door opening and closing phase 03, a vehicle driving phase 04, and a second door opening and closing phase 05.

Optionally, as shown in fig. 3, S201 includes S2011-S2015.

S2011, the detection device acquires an object detection result of the ith detection, an object detection result of the (i-1) th detection and a confidence coefficient of the (i-1) th detection in the target stage.

The target phase is the first phase or the current phase.

i belongs to [1, m ], and m is the maximum number of times of executing object detection in the target stage.

Optionally, m may be a maximum detection number of the target stage in a preset detection mode within a first preset time. The duration of the first preset duration is not limited in the embodiment of the present application.

For example, the first preset time period may be 10 min.

The preset detection mode may include continuous detection and interval detection.

Illustratively, when the target stage is entered, detecting a second preset time length to obtain an object detection result of the 1 st detection, and then performing continuous detection, wherein if the duration of the current stage is too long, interval detection can be performed after the preset continuous detection time is reached, so that the operation resources can be saved.

Similarly, the duration of the first preset duration is not limited in the embodiment of the present application. Illustratively, the second preset duration may be 5-30 seconds(s).

For example, the detection frequency of the continuous detection can be 2-20 times/second, the interval time can be 5s, and the continuous detection time can be 3-10 min.

The interval detection can be 10-30s each time, and the interval time can be 2-10 min.

The confidence of the detection of the (i-1) th time is used for representing the accuracy of the detection result of the object of the (i-1) th time.

For example, when i is 3, i-1 represents the 2 nd detection, the object detection result of the 2 nd detection is the object existing in the vehicle, the confidence of the object detection result of the 2 nd detection is 80%, and the accuracy of the object detection result of the 2 nd detection representing the object existing in the vehicle is 80%.

Optionally, the initial value of the confidence is a preset value.

For example, when i is 1, i.e., the 1 st detection, the confidence of the object detection result of the 1 st detection may be set to 80%, indicating that the accuracy of the object detection result of the 1 st detection is 80%. The object detection result at the 1 st time is the presence of the object in the vehicle, and the confidence of the object detection result of the 1 st detection is 80%, which indicates that the accuracy of the object detection result of the 1 st detection that the object is present in the vehicle is 80%.

Further, the object detection result of the 1 st detection is that an object exists in the vehicle, the confidence of the object detection result of the 1 st detection may be set to 80%, the object detection result of the 1 st detection is that an object does not exist in the vehicle, and the confidence of the object detection result of the 1 st detection may also be set to 80%.

S2012, the detecting device determines whether the object detection result at the i-th time is the same as the object detection result at the i-1 th time.

Illustratively, when i is 2, the detection apparatus determines whether the object detection result of the 2 nd detection is the same as the object detection result of the 1 st detection.

For example, the object detection result of the 1 st detection is that an object is present in the vehicle, if the object detection result of the 2 nd detection is that an object is present in the vehicle, the detection device determines that the object detection result of the 2 nd detection is the same as the object detection result of the 1 st detection, and if the object detection result of the 2 nd detection is that an object is not present in the vehicle, the detection device determines that the object detection result of the 2 nd detection is not the same as the object detection result of the 1 st detection.

If the detection result of the object detected at the ith time is the same as the detection result of the object detected at the (i-1) th time, continuing to execute S2013. If the object detection result of the ith detection is different from the object detection result of the (i-1) th detection, S2014 is continuously performed.

S2013, determining the confidence coefficient of the ith detection as follows: and the confidence of the i-1 detection is added to a first preset threshold value.

For example, the first preset threshold may be 1%.

For example, when i is 2, if the object detection result of the 1 st detection is the presence of an object in the vehicle, the confidence of the object detection result of the 1 st detection is 80%, and the object detection result of the 2 nd detection is the presence of an object in the vehicle, the confidence of the object detection result of the 2 nd detection is 81%.

S2014, determining the confidence coefficient of the ith detection as follows: and the difference between the confidence coefficient of the object detection result at the i-1 th moment and a second preset threshold value.

Optionally, the second preset threshold may be the same as or different from the first preset threshold. For example, the second preset threshold may be 1%.

For example, when i is 2, if the object detection result of the 1 st detection is that an object is present in the vehicle, the confidence of the object detection result of the 1 st detection is 80%, and the object detection result of the 2 nd detection is that an object is not present in the vehicle, the confidence of the object detection result of the 2 nd detection is 79%.

And S2015, determining an object detection result and a confidence degree of the mth detection, taking the object detection result of the mth detection as an object detection result of the target stage, and taking the confidence degree of the mth detection as a confidence degree corresponding to the target stage.

For example, if the object detection result of the m-th detection is that an object exists in the vehicle, the object detection result of the target stage is that an object exists; and if the object detection result of the m-th detection indicates that no object exists in the vehicle, the object detection result of the target stage indicates that no object exists.

Optionally, the maximum value of the confidence corresponding to the target stage may be 100%, and the minimum value of the confidence corresponding to the target stage may be 0%.

Illustratively, when m is 3, the object detection result of the 3 rd detection is acquired, and the detection apparatus determines whether the object detection result of the 3 rd detection is the same as the object detection result of the 2 nd detection.

For example, if the object detection result of the 3 rd detection is that an object exists in the vehicle, the object detection result of the 2 nd detection is that an object exists in the vehicle, and the confidence of the object detection result of the 2 nd detection is 81%, and the detection device determines that the object detection result of the 3 rd detection is the same as the object detection result of the 2 nd detection, the confidence of the object detection result of the 3 rd detection is the confidence of the object detection result of the 2 nd detection plus a first preset threshold (1%), that is, the confidence of the object detection result of the 3 rd detection is 82%, and the corresponding confidence of the target stage is 82%.

S202, determining whether an object exists in the vehicle at the current stage or not based on the object detection result at the current stage, the first confidence degree, the object detection result at the first stage and the second confidence degree.

In an implementation manner, in the case that the object detection result in the first stage is that no object exists in the vehicle and the second confidence is within a preset low confidence interval, if the object detection result in the current stage is that an object exists in the vehicle and the first confidence is within a preset high confidence interval, it is determined that an object exists in the vehicle in the current stage.

Optionally, the preset low confidence interval may be 80-85%.

Optionally, the preset low confidence intervals at different stages in the driving cycle 01 may be the same or different. For example, the preset low confidence intervals of the vehicle driving phase 04 and the vehicle door lock closing phase 06 may be 80-85%, and the preset low confidence intervals of the vehicle door lock opening phase 02, the first door opening and closing phase 03, and the second door opening and closing phase 05 may be 60-70%.

Illustratively, the predetermined high confidence interval may be 96-100%.

Optionally, the preset high confidence intervals at different stages in the driving cycle 01 may be the same or different. For example, the predetermined high confidence intervals in the vehicle driving phase 04 and the vehicle door lock closing phase 06 may be 80 to 85%, and the predetermined high confidence intervals in the vehicle door lock opening phase 02, the first door opening and closing phase 03, and the second door opening and closing phase 05 may be 91 to 100%.

For example, when the current phase is the vehicle driving phase 04 and the first phase is the first door opening and closing action phase 03, the detection result of the first door opening and closing action phase 03 is that no object exists in the vehicle, and the confidence of the first door opening and closing action phase 03 is 81% (that is, the second confidence is in the preset low confidence interval), if the object detection result of the vehicle driving phase 04 is that an object exists in the vehicle and the confidence of the object detection result of the vehicle driving phase 04 is 92% (that is, the first confidence is in the preset high confidence interval), it is determined that an object exists in the vehicle driving phase 04, otherwise, it is determined that no object exists in the vehicle driving phase 04.

In another implementation manner, when the object detection result in the first stage is that an object exists in the vehicle and the second confidence is greater than or equal to the minimum value of the preset intermediate confidence interval, if the object detection result in the current stage is that an object exists in the vehicle and the first confidence is greater than or equal to the minimum value of the preset intermediate confidence interval, it is determined that an object exists in the vehicle in the current stage.

Optionally, the preset intermediate confidence interval may be 86-95%.

Optionally, the preset intermediate confidence intervals at different stages in the driving cycle 01 may be the same or different. For example, the preset intermediate confidence intervals of the vehicle driving phase 04 and the vehicle door lock closing phase 06 may be 86-95%, and the preset intermediate confidence intervals of the vehicle door lock opening phase 02, the first door opening and closing phase 03, and the second door opening and closing phase 05 may be 70-90%.

For example, when the current phase is the vehicle driving phase 04 and the first phase is the first door opening and closing action phase 03, the detection result of the first door opening and closing action phase 03 is that no object exists in the vehicle, and the confidence of the first door opening and closing action phase 03 is 71% (that is, the second confidence is greater than or equal to the minimum value of the preset intermediate confidence interval of 70%), if the object detection result of the vehicle driving phase 04 is that an object exists in the vehicle and the confidence of the object detection result of the vehicle driving phase 04 is 88% (that is, the first confidence is greater than or equal to the minimum value of the preset intermediate confidence interval of 86%), it is determined that an object exists in the vehicle driving phase 04, and otherwise, it is determined that no object exists in the vehicle driving phase 04.

In another implementation, the first stage includes at least two sub-stages. At least two sub-phases are triggered by different preset events.

And if the object detection result of the current stage is that the object exists in the vehicle and the first confidence coefficient is greater than or equal to the minimum value of the preset middle confidence coefficient interval, determining that the object exists in the vehicle at the current stage.

The third confidence is used to characterize the accuracy of the object detection results of the sub-stage.

For example, when the current phase is the vehicle driving phase 04, and the first phase includes the vehicle door lock unlocking phase 02 and the first door opening and closing action phase 03, the detection result of the vehicle door lock unlocking phase 02 is that an object exists in the vehicle, and the confidence of the object detection result of the vehicle door lock unlocking phase 02 is 61% (i.e., the confidence of the object detection result of the vehicle door lock unlocking phase 02 is greater than or equal to the minimum value 60% of the preset low confidence interval), the detection result of the first door opening and closing action phase 03 is that an object exists in the vehicle, and the confidence of the object detection result of the first door opening and closing action phase 03 is 61% (i.e., the confidence of the object detection result of the first door opening and closing action phase 03 is greater than or equal to the minimum value 60% of the preset low confidence interval), if the object detection result of the vehicle driving phase 04 is that an object exists in the vehicle, and the confidence of the object detection result of the vehicle driving phase 04 is 87% (i.e., the first confidence is greater than or equal to the minimum value 60% of the object detection result of the preset low confidence interval) A minimum value of 86%) of the intermediate confidence interval is preset, it is determined that an object is present in the vehicle driving phase 04, otherwise it is determined that an object is not present in the vehicle driving phase 04.

In another implementation manner, if the object detection result in the first stage is that an object exists in the vehicle and the second confidence is within a preset low confidence interval, it is determined that an object exists in the vehicle in the current stage if the object detection result in the current stage is that an object exists in the vehicle and the first confidence is within a preset high confidence interval.

For example, when the current phase is the vehicle driving phase 04 and the first phase is the first door opening and closing action phase 03, the detection result of the first door opening and closing action phase 03 is that an object exists in the vehicle, and the confidence of the first door opening and closing action phase 03 is 61% (that is, the second confidence is greater than or equal to the minimum value 60% of the preset intermediate confidence interval), if the object detection result of the vehicle driving phase 04 is that an object exists in the vehicle and the confidence of the object detection result of the vehicle driving phase 04 is 97% (that the first confidence is greater than or equal to the minimum value 96% of the preset high confidence interval), it is determined that an object exists in the vehicle driving phase 04, and otherwise, it is determined that an object does not exist in the vehicle driving phase 04.

In another implementable manner, the first stage comprises at least two sub-stages; at least two sub-phases are triggered by different preset events.

And under the condition that at least one fourth confidence coefficient is smaller than the minimum value of the preset low confidence coefficient interval, if the object detection result in the current stage is that the object exists in the vehicle and the first confidence coefficient is larger than or equal to a third preset threshold value, determining that the object exists in the vehicle in the current stage.

Alternatively, the third preset threshold may be 99%.

The fourth confidence is used to characterize the accuracy of the object detection results of the sub-stages.

Illustratively, when the current phase is a vehicle door lock closing phase 06, and the first phase includes a vehicle door lock opening phase 02, a first door opening and closing phase 03, a vehicle driving phase 04, and a second door opening and closing phase 05, the detection result of the vehicle door lock opening phase 02 is that an object exists in the vehicle, and the confidence of the object detection result of the vehicle door lock opening phase 02 is 59% (i.e., the confidence of the object detection result of the vehicle door lock opening phase 02 is less than the minimum value of the preset low confidence interval 60%), if the object detection result of the vehicle door lock closing phase 06 is that an object exists in the vehicle, and the confidence of the object detection result of the vehicle door lock closing phase 06 is 100% (i.e., the first confidence is greater than or equal to the third preset threshold 99%), it is determined that an object exists in the vehicle door lock closing phase 06, otherwise, it is determined that no object is present in the vehicle during the vehicle door lock closing phase 06.

According to the method for detecting the object in the vehicle, the driving cycle of the vehicle is divided into different stages. In this way, when determining whether an object exists in the current stage, it may be determined whether an object exists in the vehicle in the current stage based on the object detection result in the current stage, the confidence (first confidence) of the object detection result in the current stage, the object detection result in the first stage, and the confidence (second confidence) of the object detection result in the first stage. Compared with the prior art that whether the object exists or not is determined based on one detection result, the scheme of the application can reduce the probability of object detection errors in the vehicle and effectively improve the detection accuracy.

Furthermore, in a scene that an object exists in the vehicle at the current stage, a control instruction can be generated according to the detection result, different services can be executed according to the control instruction, and the accuracy of vehicle service is improved.

With reference to fig. 2, as shown in fig. 4, the method for detecting an object in a vehicle according to the embodiment of the present application further includes S203-S204.

And S203, the detection device generates a control command according to the detection result.

And S204, the detection device sends the control command to at least one of an air conditioner, a multimedia device or an alarm device of the vehicle.

And the air conditioner, the multimedia device or the alarm device executes corresponding actions according to the received control command.

The detection device performs in-vehicle communication through Controller Area Network (CAN) communication, Local Interconnect Network (LIN) communication, or the like, and CAN communicate with a signal transmitting and receiving device, a seat, an air conditioning device, a multimedia device, an alarm device, or the like.

The air conditioning device may provide air conditioning or heating for each vehicle seat. Under the condition, when the detection device detects that the object exists in the vehicle, the vehicle-mounted air conditioner can be started to ventilate in the vehicle, or the refrigeration cycle of the vehicle-mounted air conditioner can be started simultaneously to adjust the temperature in the vehicle, so that the heatstroke of people staying in the vehicle is avoided. Further, when the detection means detects the position of the object in the vehicle, the air conditioning means may provide air conditioning or heating to the seat corresponding to the position of the object.

The multimedia device may be mounted to the front of each vehicle seat, and may provide a 1: 1. In other words, a multimedia device may be installed to the front of each seat in the vehicle to output desired multimedia contents to each object. For this reason, when the detection means accurately detects the position of the object, the multimedia device installed at the front of the seat where the detected object is located may play multimedia content or the like. The multimedia device may be implemented as a head-up display (HUD), a dashboard, audio-video navigation, etc. In addition, a User Setup Menu (USM) using a dashboard may directly receive color input and the like from a user. Further, the multimedia device may include at least one of: liquid crystal displays, thin film transistors, light emitting diode displays, organic diode displays, active matrix organic diode displays, flexible displays, curved displays, and three-dimensional displays. Some of which may be implemented as a transparent display configured as a transparent type or a semi-transparent type to view the outside. Further, the multimedia device may be implemented as a touch screen including a touch panel to serve as an input device in addition to an output device.

The warning device may issue a warning to the outside when the detection device may be used to determine that an object is present in the vehicle.

For example, when it is determined that an object exists in the vehicle during the vehicle door lock closing stage 06, since the entire vehicle is in a locked state, the dangerous situation of people staying in the vehicle is quite hidden and is not easily perceived by the external environment. The alarm device can start the vehicle-mounted loudspeaker and the vehicle lamp and remind the outside according to a preset alarm mode. For example, the vehicle-mounted loudspeaker can give out uninterrupted sound alarm to remind the external pedestrian, and meanwhile, the vehicle lamp can continuously flash or simultaneously double flash to remind the external pedestrian. Of course, the two warning manners may be performed simultaneously or alternatively, and the present application does not limit this.

Optionally, alarm device can also send alarm information to the high in the clouds server through wireless communication, the condition of detaining personnel in the car at present is sent for the external world, and forward this alarm information for the mobile communication equipment of the user (generally for the driver) that the current vehicle binds through the high in the clouds server, for example, send the cell-phone etc. for the user that binds of current vehicle in time learns the condition of detaining personnel in the car, because the condition of detaining personnel in the car often is that the driver stops temporarily and neglects after handling affairs and forgets and lead to, therefore this can in time remind the driver, return the vehicle rapidly and save the detained personnel.

According to the method for detecting the object in the vehicle, the control instruction is generated according to the detection result and sent to at least one of the air conditioner, the multimedia device or the alarm device of the vehicle, so that the at least one of the air conditioner, the multimedia device or the alarm device executes corresponding action according to the received control instruction, and therefore the accuracy of vehicle service can be improved.

The scheme provided by the embodiment of the application is mainly introduced from the perspective of a method. To implement the above functions, it includes hardware structures and/or software modules for performing the respective functions. Those of skill in the art would readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

As shown in fig. 5, an embodiment of the present application provides a device 500 for detecting an object in a vehicle. The apparatus for detecting an object in a vehicle may include at least one processor 501, a communication line 502, a memory 503, and a communication interface 504.

Specifically, the processor 501 is configured to execute computer-executable instructions stored in the memory 503, so as to implement steps or actions of the terminal.

The processor 501 may be a chip. For example, the Field Programmable Gate Array (FPGA) may be an Application Specific Integrated Circuit (ASIC), a system on chip (SoC), a Central Processing Unit (CPU), a Network Processor (NP), a digital signal processing circuit (DSP), a Micro Controller Unit (MCU), a Programmable Logic Device (PLD) or other integrated chips.

A communication line 502 for transmitting information between the processor 501 and the memory 503.

The memory 503 is used for storing and executing computer execution instructions, and is controlled by the processor 501 to execute.

The memory 503 may be separate and coupled to the processor via a communication link 502. The memory 303 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM). It should be noted that the memory of the systems and devices described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

A communication interface 504 for communicating with other devices or a communication network. The communication network may be an ethernet, a Radio Access Network (RAN), or a Wireless Local Area Network (WLAN).

It is noted that the structure shown in fig. 5 does not constitute a limitation of the detecting device of the object in the vehicle, and the detecting device of the object in the vehicle may include more or less components than those shown in fig. 5, or may combine some components, or may be arranged differently.

As shown in fig. 6, the present embodiment provides a device 60 for detecting an object in a vehicle. The device for detecting the object in the vehicle may include an acquisition unit 61 and a determination unit 62.

The obtaining unit 61 is configured to obtain the object detection result at the current stage, the first confidence level, the object detection result at the first stage, and the second confidence level. For example, in conjunction with fig. 2, the obtaining unit 61 may be configured to perform S201.

A determination unit 62 configured to determine whether an object exists in the vehicle at the current stage based on the object detection result at the current stage, the first confidence level, the object detection result at the first stage, and the second confidence level acquired by the acquisition unit. For example, in connection with fig. 2, the determination unit 62 may be configured to perform step S202.

With reference to fig. 6, as shown in fig. 7, the apparatus 60 for detecting an object in a vehicle according to the embodiment of the present application may further include a generating unit 63 and a transmitting unit 64.

And a generating unit 63, configured to generate a control instruction according to the detection result. For example, in connection with fig. 4, the generating unit 63 may be configured to perform S203.

A transmitting unit 64 for transmitting the control command to at least one of an air conditioner, a multimedia device, or an alarm device of the vehicle. For example, in conjunction with fig. 4, the sending unit 64 may be configured to perform S204.

It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

In actual implementation, the obtaining unit 61, the determining unit 62, the generating unit 63, and the sending unit 64 may be implemented by the processor 501 shown in fig. 5 calling the program code in the memory 503. The specific implementation process may refer to the description of the method for detecting an object in a vehicle shown in fig. 2 or fig. 4, and will not be described herein again.

Another embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions that, when executed on a device for detecting an object in a vehicle, cause the device for detecting an object in a vehicle to perform the steps performed by the device for detecting an object in a vehicle in the method flow shown in the above-mentioned method embodiment.

In another embodiment of the present application, there is also provided a computer program product comprising instructions that, when executed on a device for detecting an object in a vehicle, cause the device for detecting an object in a vehicle to perform the steps performed by the device for detecting an object in a vehicle in the method flow shown in the above-mentioned method embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of detecting an object in a vehicle, comprising:

acquiring an object detection result, a first confidence coefficient, an object detection result in a first stage and a second confidence coefficient of a current stage; the first confidence level is used for representing the accuracy of the object detection result of the current stage, and the second confidence level is used for representing the accuracy of the object detection result of the first stage; the current stage and the first stage are both stages within a driving cycle of the vehicle, and the first stage is located before the current stage; different stages in the driving cycle of the vehicle are triggered by different preset events;

determining whether an object is present within the vehicle at the current stage based on the object detection result at the current stage, the first confidence, the object detection result at the first stage, and the second confidence.

2. The detection method according to claim 1, wherein obtaining the object detection result of the current stage, the first confidence level, the object detection result of the first stage, and the second confidence level comprises:

performing the following operations on each detection in a target stage until an object detection result and a confidence coefficient of the mth detection are determined, taking the object detection result of the mth detection as the object detection result of the target stage, taking the confidence coefficient of the mth detection as the confidence coefficient corresponding to the target stage, wherein m is the maximum number of times of executing object detection in the target stage, and the target stage is the first stage or the current stage; the operation is as follows:

obtaining an object detection result of the ith detection, an object detection result of the (i-1) th detection and the confidence coefficient of the (i-1) th detection; i belongs to [1, m ], and the confidence coefficient of the detection of the (i-1) th time is used for representing the accuracy of the detection result of the object of the (i-1) th time; the initial value of the confidence coefficient is a preset value;

if the object detection result of the ith detection is the same as the object detection result of the (i-1) th detection, determining the confidence coefficient of the ith detection as follows: the sum of the confidence coefficient of the i-1 th detection and a first preset threshold value;

if the object detection result of the ith detection is different from the object detection result of the (i-1) th detection, determining the confidence coefficient of the ith detection as follows: and the difference between the confidence coefficient of the object detection result at the i-1 th moment and a second preset threshold value.

3. The detection method according to claim 1 or 2, wherein determining whether an object is present in the vehicle at the current stage based on the object detection result at the current stage, the first confidence, the object detection result at the first stage, and the second confidence includes:

and if the object detection result of the first stage is that no object exists in the vehicle and the second confidence degree is in a preset low confidence degree interval, determining that an object exists in the vehicle at the current stage if the object detection result of the current stage is that an object exists in the vehicle and the first confidence degree is in a preset high confidence degree interval.

4. The detection method according to claim 1 or 2, wherein the determining whether an object is present in the vehicle at the current stage based on the object detection result at the current stage, the first confidence, the object detection result at the first stage, and the second confidence includes:

and under the condition that the object detection result in the first stage is that the object exists in the vehicle and the second confidence coefficient is greater than or equal to the minimum value of a preset intermediate confidence coefficient interval, if the object detection result in the current stage is that the object exists in the vehicle and the first confidence coefficient is greater than or equal to the minimum value of the preset intermediate confidence coefficient interval, determining that the object exists in the vehicle in the current stage.

5. The detection method according to claim 1 or 2, characterized in that the first phase comprises at least two sub-phases; the at least two sub-stages are triggered by different preset events;

the determining whether an object is present in the vehicle at the current stage based on the object detection result at the current stage, the first confidence, the object detection result at the first stage, and the second confidence includes:

if the object detection results of at least two sub-stages are that an object exists in the vehicle and the third confidence coefficient is greater than or equal to the minimum value of a preset low confidence coefficient interval, determining that the object exists in the vehicle at the current stage if the object detection results of the current stage are that the object exists in the vehicle and the first confidence coefficient is greater than or equal to the minimum value of a preset intermediate confidence coefficient interval; the third confidence level is used to characterize the accuracy of the object detection results of the sub-stage.

6. The detection method according to claim 1 or 2, wherein the determining whether an object is present in the vehicle at the current stage based on the object detection result at the current stage, the first confidence, the object detection result at the first stage, and the second confidence includes:

and under the condition that the object detection result of the first stage is that the object exists in the vehicle and the second confidence degree is in a preset low confidence degree interval, if the object detection result of the current stage is that the object exists in the vehicle and the first confidence degree is in a preset high confidence degree interval, determining that the object exists in the vehicle at the current stage.

7. The detection method according to claim 1 or 2, characterized in that the first phase comprises at least two sub-phases; the at least two sub-stages are triggered by different preset events;

under the condition that at least one fourth confidence coefficient is smaller than the minimum value of a preset low confidence coefficient interval, if the object detection result of the current stage is that an object exists in the vehicle and the first confidence coefficient is larger than or equal to a third preset threshold value, determining that the object exists in the vehicle at the current stage; the fourth confidence level is used to characterize the accuracy of the object detection results of the sub-stage.

8. An apparatus for detecting an object in a vehicle, comprising:

the device comprises an acquisition unit, a judgment unit and a processing unit, wherein the acquisition unit is used for acquiring an object detection result, a first confidence coefficient, an object detection result in a first stage and a second confidence coefficient of a current stage; the first confidence level is used for representing the accuracy of the object detection result of the current stage, and the second confidence level is used for representing the accuracy of the object detection result of the first stage; the current stage and the first stage are both stages within a driving cycle of the vehicle, and the first stage is located before the current stage; different stages in the driving cycle of the vehicle are triggered by different preset events;

a determination unit configured to determine whether or not an object is present in the vehicle at the current stage based on the object detection result at the current stage, the first confidence, the object detection result at the first stage, and the second confidence acquired by the acquisition unit.

9. A detection device for an object in a vehicle, the detection device comprising a memory and a processor; the memory and the processor are coupled; the memory for storing computer program code, the computer program code comprising computer instructions; the detection apparatus, when the processor executes the computer instructions, performs a method of detecting an object in a vehicle as recited in any one of claims 1-7.

10. A computer-readable storage medium having stored therein instructions that, when run on a detection apparatus for an object in a vehicle, cause the detection apparatus to execute the detection method for an object in a vehicle according to any one of claims 1 to 7.