GB2568761A

GB2568761A - Method and system for detecting vehicle sound

Info

Publication number: GB2568761A
Application number: GB1719775.7A
Authority: GB
Inventors: Pilla Francesco; Shorten Robert; Mulkeen Brian; Power Bill
Original assignee: University College Dublin
Current assignee: University College Dublin
Priority date: 2017-11-28
Filing date: 2017-11-28
Publication date: 2019-05-29
Also published as: GB201719775D0

Abstract

A method and system for identifying a vehicle by audio detection, the method comprising: receiving a sound signal having an inaudible component 110; detecting the inaudible component of the sound signal 120: and processing the detected inaudible component to identify the vehicle 130. The inaudible component may be a high frequency sound which is not audible to humans. The method may include alerting a user via an audible, visible or vibratory alarm, e.g. on an arm band or smart watch. The sound may be detected by a sound pickup device, e.g. a microphone, which may be located on another vehicle or at a fixed location such as a toll booth, level crossing or car park. The sound signal may be processed to filter out background noise and to identify the type of vehicle (e.g. bicycle, electric, hybrid or internal combustion engine) by comparing the sound with a database of acoustic signatures. When the vehicle is identified to be diesel, this may trigger automatic number plate recognition and the data may be transmitted to a remote server.

Description

Method and System for Detecting Vehicle Sound

Field of the Invention

The present disclosure relates to sound detection. More particularly, it relates to a method and system for detecting inaudible sounds of vehicles such as electric vehicles.

Background of the Disclosure

In recent years there has been a gradual but progressively increasing movement towards a widespread use of electric vehicles in order to reduce the negative impacts of internal combustion engine vehicles on the environment and population’s health caused by air and noise pollution. Local authorities around Europe have been encouraged to set up clean air zones which would place driving restrictions on some vehicles, likely aimed at older, more polluting diesels. Local authorities are being encouraged to increase the number of “clean air zones”, particularly in areas of high pollution. The plans include a wide range of measures, such as: changing the road layout to decrease congestion, encourage uptake of low-emissions cars, and encourage the use of public transport and access restrictions on diesel vehicles. Other EU countries are planning to completely ban old diesel vehicles from city centres: Oslo in 2019; Paris, Madrid, Athens, and Mexico City have pledged to ban diesel vehicles from their streets by 2025, followed by many more cities across the globe.

Electric vehicles have the advantage of producing no air pollution and almost no noise at low speed, such as in cities where the speed limits are in the range of 3050 km/h. This presents a benefit in terms of noise pollution, but also a threat because electric vehicles are quiet, even too quiet and thus might not be perceived by pedestrians and other road users (e.g. cyclists) with obvious high risk of accidents.

Current solutions available on the market include providing electric cars with a system that generate an artificial noise at low speeds (e.g. Nissan Leaf). Several countries are moving towards statutory requirements for electric cars to be equipped with such a system. The scientific community is currently trying to assess the impact in terms of urban soundscape which would result from the introduction of an electric car fleet generating artificial noise. Even the related health impacts are unknown and difficult to anticipate.

In view of the above-described technologies, there is therefore a need for a method and system which addresses at least the problems outlined above.

Summary of the Invention

These and other problems are addressed by providing a method as detailed in claim 1 and a system according to claim 16. Advantageous features are provided in dependent claims.

The method and system of the present disclosure allows electric vehicles to run in silent mode because they will be detectable by pedestrians and other road users by using the system describe herein. This will have a positive impact on road safety and also on urban noise pollution, with related benefits for the population’s health. The method and system may be implemented as a stand-alone device or also integrated in existing devices and supported by a dedicated app.

These and other features will be better understood with reference to the following figures which are provided to assist in an understanding of the present teaching, by way of example only.

Brief Description of the Drawings

Figure 1 is a flowchart illustrating a method of identifying a vehicle by audio detection, according to an embodiment of the present disclosure;

Figure 2 is a flowchart illustrating a method of identifying a vehicle by audio detection, according to another embodiment of the present disclosure;

Figure 3 is a flowchart illustrating a method of identifying a vehicle which is emitting a high frequency sound, according to another embodiment of the present disclosure;

Figure 4 is a flowchart illustrating a method of identifying a diesel vehicle by audio detection, according to another embodiment of the present disclosure; and

Figure 5 is a block diagram illustrating a configuration of a computing device which includes various hardware and software components that function to perform processes according to embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will now be described with reference to some exemplary methods and systems described herein. It will be understood that the embodiments described are provided to assist in an understanding of the present disclosure and are not to be construed as limiting in any fashion. Furthermore, modules or elements that are described with reference to any one figure may be interchanged with those of other figures or other equivalent elements without departing from the spirit ofthe present disclosure.

The present disclosure provides a method and system to detect high frequency noise emitted by electric vehicles combined with machine learning algorithms. A microphone and analytics are used to detect and analyse the noise. The microphone may be a directional or omnidirectional microphone depending on the application.

The method and system use a microphone to continuously monitor sound with the purpose of detecting high frequency sound emitted by the engines of electric vehicles. High frequency sound is generally not audible by humans. The signal of the monitored sound is processed and the background noise is filtered out. The signal is then analysed using machine learning algorithms to detect the sound emitted by electric vehicles by finding a match within a previously collected database of signals of different models and makes of electric vehicles. This helps to minimise the chance of false detection due to interference from other electric engines present in urban environments. Once the electric vehicle is detected, the end user may be alerted. The alert system to notify the end user may vary according to the typology of end-users. It will be understood that the below alert 5 systems are merely examples, and other systems may be envisaged.

User	Alert system
Cyclist	a vibrating hardware device mounted on an arm band to alert the user
People wearing smart watches or equivalent training equipment	wireless connection to the training equipment and trigger vibration in it to alert the user
Prams	a vibrating and/or visual alert device mounted on the pram
Blind or visually impaired people	a vibrating device mounted on an arm band to alert the user
Cars	a directional microphone instead of an omnidirectional microphone is mounted on the side mirrors of the car and pointed towards the rear of the car. When the car is parked and an approaching electric vehicle is detected, the car's control board is configured to lock the doors.

Figure 1 is a flowchart illustrating a method 100 of identifying a vehicle by audio 10 detection, according to an embodiment of the present disclosure.Referring to Figure

1, the method comprises operating one or more processors to receive a sound signal having an inaudible component 110, detect the inaudible component of the sound signal 120, and process the detected inaudible component to identify the vehicle 130.

The sound signal may be detected in the vicinity of a vehicle. The inaudible component may comprise a high frequency sound that is outside the audible frequency range that can be detected by humans. The generally accepted standard range of audible frequencies is 20 to 20,000 Hz. Thus, inaudible signal components may be defined as having freqencies that are outside this range.

The method may further comprise alerting comprising alerting the end user of the identified vehicle. The end user may be alerted via at least one of an audible, visual, or vibratory alarm, as described above.

The the sound signal comprising the inaudible component may be detected using a sound pickup device. The sound pickup device may be a directional or omnidirectional microphone. The sound pickup device may be located on another vehicle, a toll booth, a level crossing, or a car park. The detected sound signal may be processed to filter out background noise. Noise cancellation algorithms may be employed to filter out backgound and unwanted noise. This serves to help to identify the inaudible component. In an embodiment, a specifically configured monitoring zone may be adapted in areas of extreme traffic and congestion in which large numbers of pedestrians are present. Notifications of electric vehicles and other vehicles emitting inaudible sounds that are detected may be sent to pedestrians passing through the monitoring zone.

Processing the detected inaudible component to identify the vehicle may comprise comparing the detected inaudible component with an acoustic signature of a vehicle. The detected inaudible component may be compared with a database of acoustic signatures of vehicles. The database of acoustic signatures of vehicles may comprise acoustic signatures of electric vehicles, hybrid vehicles and internal combustion vehicles. The method may comprising identifying the vehicle as a bicycle, electric vehicle, hybrid vehicle, or internal combustion vehicle.

Figure 2 is a flowchart illustrating a method of identifying a vehicle by audio detection, according to another embodiment of the present disclosure. Referring to Figure 2, the method according to the present embodiment comprises receiving an input sound signal comprising an inaudible component detected in an urban environment 210, signal processing 220 the detected signal to filter out urban background noise 230, and analysing the processed signal to identify a vehicle in the urban environment 240. The vehicle identified may be an electric vehicle, a hybrid vehicle or an internal combustion vehicle. The analysis step 240 may comprise checking a database of electric vehicle acoustic signatures 250, applying machine learning algorithms 260 to identify the electric vehicle by finding a match 270 within a previously collected database of signals of different models and makes of electric vehicles. Finally, once an electric vehicle is identified, an end user may be alerted 280 of the presence of the electric vehicle.

An alternative scenario is also envisaged, in which vehicles are configured to output a specific inaudible sound according to the make and/or model of the vehicle. Such inaudible sound may comprise the sound of an electric motor or the sound of a specific device configured to emit such sound. Such a specific device may be mounted on a bicycle for example. As mentioned previously, inaudible sounds are high frequency sounds outside the audible frequency range that can be detected by humans. A distinctive acoustic signature can be assigned to makes and model of vehicles of all types. This allows for both electric vehicles and bicycles to be detected without having a negative impact on noise pollution in the surrounding environments. This is a valuable alternative to the current plans to configure electric vehicles with artificial sounds in the audible frequency range in order to be detected by pedestrians for safety reasons. The proposed solution also allows for bicycles to be detectable, with a huge potential benefit in the area of cycling safety.

In this regard, Figure 3 is a flowchart illustrating a method of identifying a vehicle which is emitting a high frequency inaudible sound, according to another embodiment of the present disclosure. Referring to Figure 3, the method according to the present embodiment comprises receiving an input sound signal detected in an urban environment 310, signal processing 320 the detected signal to filter out urban background noise 330, and analysing the processed signal to identify the vehicle in the urban environment 340. The identified vehicle may be an electric vehicle or a bicycle for example. Once the vehicle is identified, an end user may be alerted 350 of the presence of the vehicle.

By configuring different types of vehicles such as electric vehicles and bicycles with a source of artificial high frequency sound outside the audible frequency range, such vehicles can be detected and identified without having a negative impact on noise pollution. The above-described embodiment can be used to alert end users in the following ways. It will be understood that the below alert systems are merely examples, and other systems may be envisaged.

User	Alert system
cyclist	a vibrating hardware device mounted on an arm band to alert the user
People wearing smart watches or equivalent training equipment	a device may be wirelessly connected to the training equipment and trigger vibration in it to alert the user
Prams	a vibrating and/or visual alert hardware and mounted on the pram
Blind or visually impaired people	a vibrating hardware mounted on an arm band to alert the user
Cars	a directional microphone instead of an omnidirectional microphone mounted on the side mirrors of the car and pointed towards the rear of the car. When the car is parked and an approaching electric vehicle is detected, the car's control board may be configured to lock the doors.

The methodology of the present disclosure can also be applied to detection and identification of internal combustion vehicles. Machine learning algorithms can be configured to detect not just electric vehicles and bicycles, but also internal 10 combustion vehicles having diesel and petrol engines. Diesel engines have a distinctive sound signature which is different from other engines. As such, in an embodiment of the present disclosure, the method can be applied to detect diesel engines, trigger Automatic Plate Number Recognition (APNR) devices and thus capture APNR data only when a diesel engine is detected. This has the advantages 15 to reduce the volume of data generated by APNR systems because the APNR is not recording, saving and analysing images when diesel engines are not detected. The second benefit is the related improvement in privacy for citizens because the APNR device is not recording and storing data in a continuous way. The functionality of the present embodiment may be integrated in the APNR system or an external processing device may be remotely connected to the APNR system.

Figure 4 is a flowchart illustrating a method 400 of identifying a diesel engine by audio detection, according to another embodiment of the present disclosure. Referring to Figure 4, the method 400 comprises receiving a sound signal having an inaudible component 410, signal processing the received sound signal 420, determining whether a diesel engine is detected 430, trigger an APNR device when a diesel engine is detected 440, and identifying the vehicle 450 as a diesel vehicle. The APNR data may be transmitted to a remote server, such as at a local, governmental or police authority.

The method and system of the present disclosure allows electric vehicles to run in silent mode because they will be detectable by pedestrians and other road users who are using the developed system. This will have a positive impact on road safety and also on urban noise pollution, with related benefits for the population’s health. The present disclosure provides the capability to detect a sound which is not detectable by humans by using portable low-cost equipment. The method and system of the present disclosure will allow the analysis and recognition of the acoustic signature of an electric vehicle. The method and system may be implemented as a stand-alone device or also integrated in existing devices and supported by a dedicated app. The method and system may be used for blind people and visually impaired people as an aid to detect electric vehicles when crossing roads, on prams, on bikes, to detect incoming cars from behind, on fitness bracelets for runners training with headsets to alert them of incoming electric vehicles, on car side mirrors (as directional microphone) to detect incoming electric vehicles or bicycles (if artificial high frequency wound is introduced as described above) prevent the opening of car’s doors, and policing of diesel vehicles in no or low emission zones.

Figure 5 is a block diagram illustrating a configuration of a computing device 900 which includes various hardware and software components that function to perform processes according to the present disclosure. Referring to Figure 16, the computing device 900 comprises a user interface 910, a processor 920 in communication with a memory 950, and a communication interface 930. The processor 920 functions to execute software instructions that can be loaded and stored in the memory 950. The processor 920 may include a number of processors, a multi-processor core, or some other type of processor, depending on the particular implementation. The memory 950 may be accessible by the processor 920, thereby enabling the processor 920 to receive and execute instructions stored on the memory 950. The memory 950 may be, for example, a random access memory (RAM) or any other suitable volatile or non-volatile computer readable storage medium. In addition, the memory 950 may be fixed or removable and may contain one or more components or devices such as a hard drive, a flash memory, a rewritable optical disk, a rewritable magnetic tape, or some combination of the above.

One or more software modules 960 may be encoded in the memory 950. The software modules 960 may comprise one or more software programs or applications having computer program code or a set of instructions configured to be executed by the processor 920. Such computer program code or instructions for carrying out operations for aspects of the systems and methods disclosed herein may be written in any combination of one or more programming languages.

The software modules 960 may include at least a first application 961 and a second application 962 configured to be executed by the processor 920. During execution of the software modules 960, the processor 920 configures the computing device 900 to perform various operations relating to the embodiments of the present disclosure, as has been described above.

Other information and/or data relevant to the operation of the present systems and methods, such as a database 970, may also be stored on the memory 950. The database 970 may contain and/or maintain various data items and elements that are utilized throughout the various operations of the system described above. It should be noted that although the database 970 is depicted as being configured locally to the computing device 900, in certain implementations the database 970 and/or various other data elements stored therein may be located remotely. Such elements may be located on a remote device or server - not shown, and connected to the computing device 900 through a network in a manner known to those skilled in the art, in order to be loaded into a processor and executed.

Further, the program code of the software modules 960 and one or more computer readable storage devices (such as the memory 950) form a computer program product that may be manufactured and/or distributed in accordance with the present disclosure, as is known to those of skill in the art.

The communication interface 940 is also operatively connected to the processor 920 and may be any interface that enables communication between the computing device 900 and other devices, machines and/or elements. The communication interface 940 is configured for transmitting and/or receiving data. For example, the communication interface 940 may include but is not limited to a Bluetooth, or cellular transceiver, a satellite communication transmitter/receiver, an optical port and/or any other such, interfaces for wirelessly connecting the computing device 900 to the other devices.

The user interface 910 is also operatively connected to the processor 920. The user interface may comprise one or more input device(s) such as switch(es), button(s), key(s), and a touchscreen.

The user interface 910 functions to facilitate the capture of commands from the user such as an on-off commands or settings related to operation of the system described above. The user interface 910 may function to issue remote instantaneous instructions on images received via a non-local image capture mechanism.

A display 912 may also be operatively connected to the processor 920. The display 912 may include a screen or any other such presentation device that enables the user to view various options, parameters, and results. The display 912 may be a digital display such as an LED display. The user interface 910 and the display 912 may be integrated into a touch screen display.

The operation of the computing device 900 and the various elements and components described above will be understood by those skilled in the art with reference to the method and system according to the present disclosure.

The present disclosure is not limited to the embodiment(s) described herein but can be amended or modified without departing from the scope of the present disclosure. Additionally, it will be appreciated that in embodiments of the present disclosure some of the above-described steps may be omitted and/or performed in an order other than that described.

Similarly the words comprises/comprising when used in the specification are used to specify the presence of stated features, integers, steps or components but do not preclude the presence or addition of one or more additional features, integers, steps, components or groups thereof.

Claims

1. A method of identifying a vehicle by audio detection, the method comprising operating one or more processors to :

receive a sound signal having an inaudible component; detect the inaudible component of the sound signal; and process the detected inaudible component to identify the vehicle.

2. The method of claim 1, further comprising alerting an end user of the identified vehicle.

3. The method of claim 2, comprising alerting the end user via at least one of an audible, visual, or vibratory alarm.

4. The method of any preceding claim, wherein the sound signal is detected in the vicinity of a vehicle.

5. The method of any preceding claim, comprising detecting the sound signal using a sound pickup device.

6. The method of claim 5, comprising detecting the sound signal using a directional or omni-directional microphone.

7. The method of claim 5 or 6, wherein the sound pickup device is located on another vehicle, a toll booth, a level crossing, or a car park.

8. The method of any preceding claim, comprising processing the detected sound signal to filter out background noise.

9. The method of any preceding claim, wherein processing the detected inaudible component to identify the vehicle comprises comparing the detected inaudible component with an acoustic signature of a vehicle.

10. The method of claim 9, comprising comparing the detected inaudible component with a database of acoustic signatures of vehicles.

11. The method of claim 10, wherein the database of acoustic signatures of vehicles comprises acoustic signatures of electric vehicles, hybrid vehicles and internal combustion vehicles.

12. The method of any preceding claim, comprising identifying the vehicle as a bicycle, electric vehicle, hybrid vehicle, or internal combustion vehicle.

13. The method of claim 12, comprising identifying the vehicle as a diesel vehicle.

14. The method of claim 13, comprising triggering an Automatic Plate Number Recognition (APNR) device to capture APNR data of the vehicle in question.

15. The method of claim 14, comprising transmitting the APNR data to a remote server.

16. A computing system configured for identifying a vehicle by audio detection, the computing system comprising:

a memory; and one or more processors configured to: