EP3381024A1

EP3381024A1 - Classifying one or a plurality of reflection objects

Info

Publication number: EP3381024A1
Application number: EP16801488.4A
Authority: EP
Inventors: Volker Mathis LÜCKEN; Nils VOSS
Original assignee: Ice Gateway GmbH
Current assignee: Ice Gateway GmbH
Priority date: 2015-11-27
Filing date: 2016-11-25
Publication date: 2018-10-03
Also published as: WO2017089568A1; DE102015120659A1; US20180275260A1

Abstract

A method is disclosed, inter alia, which comprises the following: obtaining ultrasonic echo signal data, wherein the ultrasonic echo signal data comprise a plurality of data points, wherein the ultrasonic echo signal data at least partly represent an ultrasonic echo signal detected by an ultrasonic sensor, and wherein the ultrasonic echo signal comprises signal components attributed to reflections at one or a plurality of reflection objects, grouping a plurality of data points of the ultrasonic echo signal data to form one or a plurality of data point clusters, determining characteristic data at least partly depending on one data point and/or a plurality of data points of a data point cluster of the ultrasonic echo signal data, classifying one or a plurality of the reflection objects at least partly on the basis of the characteristic data obtained as a result of the determining.

Description

Classify one or more reflection objects

Field Exemplary embodiments of the invention relate to the classification of one or more reflection objects in the detection range of an ultrasonic sensor.

BACKGROUND Various systems for detecting moving and stationary objects, for example for traffic monitoring, are known. These systems often include stationary imaging sensors, infrared sensors and radar sensors, or a combination of these types of sensors. The use of radar sensors is expensive and expensive due to the complexity of the technology. Infrared sensors can be disturbed by ambient light and high ambient temperatures, so that optimal results can not be achieved, especially in outdoor applications. The use of imaging sensors is often problematic in outdoor systems for data protection reasons and requires a high computing power to evaluate the sensor data. The common advantage of all the methods described so far is that they are all non-intrusive, meaning that the sensors do not have to be incorporated into the road surface. Intrusive sensors, such as induction loops, have good detection rates. However, the installation is associated with a great deal of effort and intervention in the road.

Ultrasonic sensors, as other non-intrusive sensors, have so far been used in road traffic primarily in parking aid systems of vehicles for distance measurement. It is only evaluated whether and at what distance a transmitted ultrasonic pulse is reflected first. However, such evaluations of the initial reflection are not sufficient for the exact detection of moving and stationary objects as well as for the classification of the objects, if other objects are also within the detection range. Ultrasonic sensors are particularly sensitive to disturbances and changes in the environment detected by the ultrasonic sensors, such as background reflections of the environment, the ground and fixed objects, and movement of tree branches by the wind and the like. Ultrasonic sensors have therefore not been used in systems for detecting moving and stationary objects in a complex environment. Summary of some exemplary embodiments of the invention

The present invention has, inter alia, the task of overcoming these problems.

According to the invention, a method is disclosed which comprises methods:

Obtaining ultrasound echo signal data, wherein the ultrasound echo signal data comprises a plurality of data points, the ultrasound echo signal data at least partially representing an ultrasound echo signal detected by an ultrasound sensor, and wherein the

Ultrasound echo signal comprises reflections on one or more reflection objects resulting signal components,

Grouping a plurality of data points of the ultrasonic echo signal data into one or more data point clusters,

Determining characteristic data at least partially in dependence on a data point and / or a plurality of data points of a data point cluster of the ultrasonic echo signal data,

Classifying one or more of the reflection objects based at least in part on the characteristics obtained as a result of the determining.

The method according to the invention and / or the steps of the method according to the invention are carried out, for example, by a device such as the device according to the invention described below. Alternatively, it is also possible for the method according to the invention and / or the steps of the method according to the invention to be carried out by different devices of a system such as the system according to the invention described below. According to the invention, a computer program is further disclosed, the computer program comprising program instructions which include a processor for executing and / or controlling the computer program

cause the inventive method when the computer program is running on the processor.

The computer program according to the invention can be used, for example, via a network such as the Internet, smart city infrastructures and smart building solutions such as that of the company ICE

Gateway GmbH distributed ICE Gateway, other open source solutions we Raspberry PI, a telephone or mobile network and / or a local network be distributed. The invention

Computer program may be at least partially software and / or firmware of a processor, and / or software and / or firmware of an embedded system. It may equally be at least partially implemented as hardware. The computer program according to the invention can be stored, for example, on a computer-readable storage medium, for example a touchable, magnetic, electrical, electromagnetic, optical and / or other type Storage medium. The storage medium may for example be part of the processor, for example a (non-volatile or volatile) program memory and / or main memory of the processor or a part thereof. According to the invention there is further disclosed a device comprising:

Means adapted for the execution and / or control of the method according to the invention or respective means for carrying out and / or controlling the steps of the method according to the invention. For example, the means of the inventive apparatus are arranged to execute and / or control the method or steps of the invention (e.g., except for the steps performed by a user). One or more of the steps of the method of the invention may also be carried out and / or controlled by the same means.

For example, one or more of the means of the device may be at least partially formed by one or more processors.

For example, the device according to the invention comprises at least one circuit which is set up to cause the device to execute and / or control at least the method according to the invention and / or the steps of the method according to the invention. Either all steps of the method according to the invention can be controlled, or all steps of the

According to the method of the invention, or one or more steps are controlled and one or more steps are carried out.

In the present case, a circuit should be understood to mean, for example, an implementation of the means of the device according to the invention only in hardware and / or an implementation of the means of the device according to the invention with a combination of hardware and software.

Implementation of hardware only means of the invention includes digital and / or analog circuits (e.g., digital and / or analog circuits only) such as configurable digital logic. For example, the device according to the invention comprises at least one digital and / or analog circuit which is set up to cause the device to execute and / or control at least the method according to the invention and / or the steps of the method according to the invention

An implementation of the means of the device according to the invention with a combination of hardware and software comprises, for example, at least one processor and at least one Memory with program instructions. For example, the device according to the invention comprises a processor and at least one memory which contains program code, wherein the memory and the program code are arranged, together with at least one processor, to cause the device to at least the method according to the invention and / or the steps of

execute and / or control method according to the invention. Under a processor, for example, a control unit, a microprocessor, a microcontroller such as a

Microcontroller, a Digital Signal Processor (DSP), a

Application Specific Integrated Circuit (ASIC) or Field Programmable Gate Array (FPGA).

According to the invention there is further disclosed a system comprising system:

one or more devices according to the invention, and

one or more stationary ultrasonic sensors.

The following describes the properties of the method according to the invention, of the computer program according to the invention, of the device according to the invention and of the system according to the invention - in part by way of example.

An ultrasound echo signal should, for example, be understood to be an ultrasound signal which is detected by an ultrasound sensor and comprises at least substantially signal portions attributable to reflections at one or more reflection objects. In this case, a reflection object is to be understood, for example, as an object in the detection range of the ultrasound sensor, at which an ultrasound signal (for example one or more ultrasound pulses) is reflected. For example, a reflection object may be a moving object (i.e., a moving reflection object) or a non-moving object (i.e., a non-moving reflection object). The detection range of the ultrasound sensor is, for example, the spatial area in the vicinity of the ultrasound sensor that can be monitored by the ultrasound sensor (for example the spatial area in which signal components due to reflections on one or more reflection objects in the direction of the ultrasound sensor can be detected by the ultrasound sensor).

The ultrasonic echo signal is detected by the ultrasonic sensor, for example, by measuring the signal strength of the ultrasonic echo signal. For example, the ultrasonic sensor is as

Ultrasonic detector formed. For example, the signal strength of one at the position of

Ultrasonic sensor detectable ultrasonic echo signal indirectly through one of the

Ultrasonic sensor comprised piezoelectric transducer detected and / or measured. For example, the piezoelectric transducer converts the ultrasonic echo signal into an electrical signal. For example, the value of the signal strength of the ultrasonic echo signal may be determined by measuring the voltage amplitude of that electrical signal. The ultrasonic echo signal data can be obtained, for example, by analog-to-digital conversion of this electrical signal.

The ultrasound echo signal data are, for example, a representation of the time profile of the signal strength of the ultrasound echo signal detected by the ultrasound sensor. The ultrasound echo signal data is preferably a digital representation of the time profile of the signal strength of the ultrasound echo signal detected by the ultrasound sensor. The signal strength corresponds for example to the signal energy of the detected ultrasonic echo signal.

For example, a data point of the ultrasound echo signal data includes a representation (e.g., a digital representation) of the value of the signal strength of the signal detected by the ultrasound sensor

Ultrasonic echo signal at a certain detection time. Further, such a data point may include, for example, a representation (e.g., a digital representation) of the acquisition time. Alternatively or additionally, the detection time may also result from the position of the data point in the ultrasound echo signal data. In addition, a data point of

Ultrasonic echo signal data optional additional information such as frequency and / or

Phase information (e.g., the frequency spectrum per data point and / or the phase position per data point).

Obtaining the ultrasonic echo signal data includes, for example, measuring the signal strength of the ultrasonic echo signal and / or determining the value of the signal strength or others

Information of the ultrasonic echo signal. In this case, the ultrasonic sensor is for example a part of the device according to the invention.

Alternatively or additionally, obtaining the ultrasound echo signal data may also include receiving the ultrasound echo signal data from the ultrasound sensor. For example, the ultrasonic sensor is not part of the device according to the invention. In this case, the ultrasound echo signal data are communicated, for example, from the ultrasound sensor to the device according to the invention. For example, the inventive apparatus includes communication means configured to receive the ultrasound echo signal data from the ultrasound sensor.

An example of such communication means is a communication interface, for example a wireless communication interface such as a communication interface of a wireless communication technology or a wired communication interface such as a

Communication interface of a wired communication technology. An example of one wireless communication technology is Zigbee, 6LOWPAN, a local radio network technology such as Radio Frequency Identification (RFID) and / or Near Field Communication (NFC) and / or Bluetooth (eg Bluetooth Version 2.1 and / or 4.0) and / or Wireless Local Area Network (WLAN) , For example, RFID and NFC are specified in accordance with ISO standards 18000, 11784/11785 and ISO / IEC standards 14443-A and 15693. The Bluetooth specifications are currently available on the internet

Available at www.bluetooth.org. For example, WLAN is specified in the standards of the IEEE 802.11 family. Another example of a wireless communication technology is an over-the-air radio network technology, for example a mobile radio technology, for example Global System for Mobile Communications (GSM) and / or Universal Mobile Telecommunications System (UMTS) and / or Long Term Evolution (LTE). The GSM, UMTS and LTE specifications are provided by the 3rd

The Generation Partnership Project (3GPP) is maintained and developed and is currently available on the Internet at www.3gpp.com. An example of a wired one

Communications technology includes Ethernet, Universal Serial Bus (USB), Firewire, UART (Universal Asynchronous Receiver Transmitters) such as RS-232, Serial Peripheral Interface (SPI), and / or I2C (Inter-Integrated Circuit). The USB specifications are currently available on the Internet at www.usb.org. A wired Ethernet communication interface could at the same time also be used to supply power to the device according to the invention and / or the ultrasound sensor in the context of a technique known as PoE (Power over Ethernet). For example, PoE is specified in the IEEE 802.3af-2003 standard. However, it should also be understood later and future versions of this standard or proprietary modifications under the term PoE. For example, PoE can be used both for supplying energy to the device according to the invention and / or the ultrasound sensor and as communication technology for communication of information and / or data between the device according to the invention and the ultrasound sensor. Various communication protocols such as CoAP (Constrained Application Protocol) can be used. CoAP is an application layer communication protocol specified inter alia in RFC 7252 of the IETF (Internet Engineering Task Force).

For example, a data point cluster is understood to mean a group of data points. For example, the data points of a data point cluster are similar. For example, data points are grouped into a data point cluster if one or more properties of the

Data points (e.g., the locations of the data points within the ultrasound echo signal data) and / or the signal strength values represented by the data points and / or the acquisition times represented by the data points are within a similarity range (e.g., a predetermined similarity range). In particular, grouping multiple data points may be the same

Ultrasonic echo signal data to one or more data point clusters applying a

Clustering algorithm on the data points of the ultrasonic echo signal data include. By choosing a suitable similarity range and / or a suitable clustering algorithm For example, data points are grouped into one or more data point arrays, which at least essentially represent reflections on a particular reflection object attributable signal components of the ultrasonic echo signal. This makes it possible to distinguish signal components of the ultrasonic echo signal that are at least essentially due to reflections at different reflection objects.

Subsequently, characteristic data of the respective data point cluster can be determined.

For example, the characteristics describe characteristics of the data point clusters and / or characteristics of the data point clusters. Examples of such properties and characteristics are the localization, distribution, shape, morphology, pattern, and extent of a data point cluster. Further examples of this are the reflection energy and signal propagation time of the signal portion of the ultrasound echo signal data represented by a data point cluster (e.g., at least substantially due to reflections on a reflection object)

represented ultrasonic echo signal. These characteristics allow, for example, a

Description and investigation of the backscatter pattern.

Further examples of characteristic data are amplitude, frequency and / or phase information. For example, the characteristics are determined at least in part depending on the values of the signal strength represented by one or more data points (e.g., multiple data points of a data point cluster) and / or the detection times represented by one or more data points. For example, the characteristics include a value and / or an average value (e.g., an average) of the amplitude, frequency, and / or phase of the signal portion of the ultrasonic echo signal represented by one or more data points (e.g., multiple data points of a data point cluster).

Subsequently, one or more of the reflection objects are classified at least in part based on the characteristics obtained as a result of the determination. For example, the characteristics are selected to allow distinguishing different types of reflection objects and classifying the reflection objects accordingly. For example, various types of reflection objects, for example, various traffic objects such as pedestrians, cyclists, and motor vehicles can be distinguished from each other by the characteristics. For example, based on phase and / or frequency information, the speed of the

Reflection objects are estimated and / or determined so that reflection objects with

different speeds and can be classified accordingly. For example, at least fast and slow moving reflection objects can be detected using phase and / or frequency information can be distinguished. This distinction is taken into account, for example, in classifying. For example, a fast-moving reflection object may speak for a classification as a motor vehicle, whereas a slow-moving reflection object might speak for a classification as a pedestrian or a cyclist, for example. In addition to the speed, further characteristics of the reflection objects, such as the dimensions and / or the position, can be determined and / or estimated on the basis of the characteristic data and taken into account in the classification.

The classification can be performed, for example, locally by the device according to the invention. It is also possible that the classification by one or more

Devices according to the invention for a local group of devices according to the invention (for example a group of devices according to the invention of the system according to the invention).

Further, the classifying may also be performed, for example, by a server (e.g., a server of the

according to the invention). Of course, the classification can also be performed distributed by different devices and / or servers.

The present invention thus makes it possible to evaluate the ultrasound echo signal with regard to signal components which are at least essentially reflective to reflections at different wavelengths

Reflection objects in the detection range of the ultrasonic sensor go back, and is not limited to the evaluation of Erstrefflektion. Thereby, by grouping and determining the characteristics for the respective data point clusters, different classes of reflection objects in the detection range of the ultrasonic sensor such as various (e.g., moving) traffic objects can be recognized and discriminated. Thereby, the detection range of an ultrasonic sensor can be increased, for example, an ultrasonic sensor for traffic monitoring of multiple lanes or for monitoring multiple parking spaces can be used. If the evaluation of the

Ultrasonic echo signal is limited to the Erstreflektion, however, only a lane or a parking lot can be sensibly monitored by an ultrasonic sensor.

Other advantages of the disclosed invention will become apparent below by way of example

Embodiments of the method according to the invention, of the invention

Computer program, the device according to the invention and the system according to the invention described, the disclosure of which should apply equally to the respective categories (method, computer program, device, system). According to an exemplary embodiment of the invention, each data point represents the

Ultrasonic echo signal data the value of the signal strength of the detected ultrasonic echo signal in each case at a detection time. As described above, one data point includes the Ultrasonic echo signal data, for example, a representation (eg, a digital representation) of the value of the signal strength of the ultrasonic echo signal detected by the ultrasonic sensor at a certain detection time. Such a representation of a value of the signal strength is, for example, a digital value which corresponds at least substantially to the value of the signal strength (eg a rounded value or a digitized value of the signal strength). Further, such a data point may include, for example, a representation (eg, a digital representation) of the acquisition time. A representation of the detection time is, for example, a digital value that at least substantially corresponds to the date and time of the detection time (eg the Unix time and / or the POSIX time of the detection time).

According to an exemplary embodiment of the invention, the ultrasonic sensor is stationary. By stationary, it is to be understood, for example, that the ultrasonic sensor is permanently located at a specific position (for example, a geographical and / or spatial position). For example, the ultrasonic sensor is permanently installed and / or mounted at this position. For example, the ultrasonic sensor is in a sidefire configuration (e.g., in an oblique and / or angular orientation, e.g., in an oblique and / or angular orientation to the

Detection area and / or to a ground surface, e.g. the soil surface in the

Detection area) installed and / or mounted. This has the effect that the detection range of the ultrasonic sensor can cover a larger area than, for example, in a vertical orientation to the detection area and / or to a floor surface. Further are

Embodiments are possible in which the ultrasonic sensor is pivotable. For example, the ultrasonic sensor is mechanically pivotable and / or the detection direction of the ultrasonic sensor is electronically pivotable (e.g., by a phased array receiving arrangement). For example, in none of these embodiments is the ultrasonic sensor part of a portable device (e.g., a vehicle).

The ultrasound sensor may be part of a plurality of ultrasound sensors, for example part of an ultrasound sensor array. For example, the system of the invention includes such a plurality of ultrasonic sensors.

For example, a plurality of ultrasonic sensors may be arranged to be one

Capture ultrasonic echo signal asynchronously, for example, by a sequence of ultrasonic sensors in temporally successive periods detects the ultrasonic echo signal. As a result, the results from ultrasonic sensor to ultrasonic sensor can be further optimized, for example.

According to an exemplary embodiment of the invention, the method according to the invention furthermore comprises the emission and / or the initiation of the emission of one or more ultrasound pulses. For example, the transmitted ultrasound pulses are based on a time-limited prototype pulse that is modulated and / or frequency-shifted to an ultrasound carrier frequency (eg, 44 kHz).

For example, the ultrasonic pulses are emitted at regular intervals, so that the time difference between the transmission times of two successive ultrasonic pulses is always the same. In this case, for example, the point in time at which the emission of the ultrasonic pulse starts is to be understood by a transmission time of an ultrasonic pulse. Furthermore, the ultrasound pulses are, for example, the same and / or the ultrasound pulses have, for example, the same pulse length. However, the ultrasonic pulses may also be uneven and / or emitted at irregular intervals and / or with different pulse lengths. Embodiments are also possible in which the time intervals between two successive ultrasonic pulses and / or the pulse length of the ultrasonic pulses are variable.

For example, the ultrasonic pulses are emitted from the ultrasonic sensor. In this case, the ultrasonic sensor is formed, for example, as a combined ultrasonic transmitter and ultrasonic detector. Embodiments are also possible in which the ultrasound pulses are emitted by a suitably arranged ultrasound transmitter separate from the ultrasound sensor. For example, the ultrasonic transmitter is stationary. Under stationary, as described above for ultrasonic sensor, it should be understood, for example, that the ultrasonic transmitter is permanently at a certain position. For example, the ultrasonic transmitter is permanently installed and / or mounted at this position. For example, the ultrasonic transmitter is installed and / or mounted in a sidefire configuration (e.g., in an oblique and / or angular orientation, e.g., in an oblique and / or angular orientation to a ground surface, e.g., the ground surface). Furthermore, embodiments are possible in which the ultrasonic transmitter is pivotable. For example, the ultrasonic transmitter is mechanically pivotable and / or the transmission direction of the ultrasonic transmitter is electronically pivotable (e.g., by a phased array transmitter). For example, in none of these embodiments is the ultrasonic transmitter part of a portable one

Device (e.g., a vehicle).

For example, the device according to the invention comprises the ultrasonic transmitter.

Alternatively or additionally, the device according to the invention can be the ultrasonic transmitter

for example, to control the transmission of the ultrasonic pulses through the ultrasonic transmitter cause. For example, the device according to the invention comprises communication means which are set up to communicate a corresponding drive signal to the ultrasound transmitter. An example of such communication means, as explained above, is a communication interface, for example a wireless communication interface or a wired one

Communication interface. In this case, for example, the ultrasonic transmitter is not part of the device according to the invention.

An ultrasonic transmitter comprises, for example, a piezoelectric transducer which, for example, converts an electrical signal into an ultrasonic pulse.

The ultrasound transmitter (and / or the ultrasound sensor formed as a combined ultrasound sensor and ultrasound detector) may, for example, be part of a plurality of ultrasound transmitters

For example, the system according to the invention comprises such a plurality of ultrasound transmitters (and / or ultrasound sensors).

Each ultrasonic pulse emitted by another ultrasound transmitter of a plurality of ultrasound transmitters and / or another ultrasound sensor of a plurality of ultrasound sensors has, for example, a different ultrasound carrier frequency. This has the effect of being on

Reflections of ultrasound pulses of different ultrasonic transmitter and / or ultrasonic sensors returning signal components in an ultrasonic echo signal, for example by a

Bandpass filtering can be at least substantially separated.

Accordingly, the method according to the invention can comprise, for example, such bandpass filtering of the ultrasonic echo signal detected by the ultrasonic sensor. Alternatively or additionally, the ultrasound echo signal data obtained can represent, for example, a corresponding band-filtered ultrasound echo signal, which is at least essentially reflected by reflections from

Ultrasonic pulses of a single ultrasonic transmitter comprises returning signal components. According to an exemplary embodiment of the invention, the reflections comprise at least substantially reflections of the emitted ultrasonic pulses at the reflection objects. For example, the ultrasonic echo signal includes signal components that are at least substantially

Reflections of one or more of the previously emitted ultrasonic pulses to the

Go back to reflection objects.

According to an exemplary embodiment of the invention, the method according to the invention further comprises subdividing the ultrasound echo signal data into a plurality of ultrasound echo signal data blocks, wherein the ultrasound echo signal data blocks have successive periods of time

Time length of a time course of a value of the signal strength of the detected

Represent ultrasonic echo signal. For example, each of the time periods begins with the transmission time of an ultrasonic pulse. Further, the time period length of each of the time sections corresponds, for example, to the time difference between the transmission times of two successive ultrasonic pulses. This has the effect, for example, that the time profile of the signal strength of the detected ultrasonic echo signal represented by an ultrasound echo signal data block is determined at least essentially by reflections of the ultrasound pulse emitted at the beginning of the respective time segment and is therefore also referred to below by way of example as ultrasound pulse response.

Furthermore, this ensures, for example, that when the time difference between the

Transmission points of two consecutive ultrasonic pulses is always the same, data points that are located at the same position in different ultrasonic echo signal data blocks, each with the same signal delay time (starting from the transmission time at the beginning of the respective period) are associated. For example, a detection time shall be understood to be associated with a signal delay if the time difference between the detection time and a

Transmission time of a previously transmitted ultrasonic pulse corresponds to the signal delay. In this case, for example, the time difference between the transmission time of a

Ultrasonic pulse and a detection time of the attributable to one or more reflections of the ultrasonic pulse signal components are understood in an ultrasonic echo signal.

This embodiment is advantageous, for example, if the ultrasound pulses are each emitted by a stationary ultrasound transmitter and / or stationary ultrasound sensor and the

Ultrasonic echosignal be detected by a stationary ultrasonic sensor, since in such a scenario, reflect on reflections of multiple ultrasound pulses on a reflection object at a certain distance in a certain distance signal components of the detected ultrasonic echo signal in each case the same distance and thus have the same signal propagation time. In other words, the data points which are located at the same position in different ultrasound echo signal data blocks in this scenario each represent a signal component of the ultrasound echo signal that is at least essentially a reflection of the respective ultrasound pulse on a reflection object at the same distance (eg in the same distance) Distance from the ultrasonic sensor and / or ultrasonic transmitter) goes back. According to an exemplary embodiment of the invention, the method according to the invention further comprises determining a graphical representation of the ultrasound echo signal data at least partially in dependence on the ultrasound echo signal data blocks. As a result of determining the graphical representation, for example, a graphically representable ultrasonic echo signal data structure is obtained, such as a two-dimensional data field and / or a data array and / or a graphics file (eg, a graphics file in an image data format such as the bitmap format, BMP format, the graphical representation for example, a two-dimensional representation of

Ultrasonic echo signal data. Alternatively or additionally, the graphical representation is for example a graphical interpretation and / or abstraction of the ultrasound echo signal data.

For example, the graphical representation is and / or includes a pixel array having pixels arranged in a raster (e.g., the ultrasound echo signal data structure obtained as a result of determining the graphical representation may be represented as a pixel array). For example, each pixel of the pixel array depending on a data point of the

Ultrasonic echo signal data determined. For example, the color, coloration and / or gray level of a pixel is determined as a function of the value of the signal strength represented by the respective data point.

For example, adjacent pixels in a raster column of the raster become, for example, successive data points of a respective ultrasound echo signal data block

Ultrasound echo signal data blocks determined; and adjacent pixels in a raster line of the raster become, for example, data points that are in successive

Ultrasonic echo signal data blocks are located (e.g., at the same position in consecutive ultrasonic echo signal data blocks). This has the effect, for example, that when each of the time periods represented by the ultrasonic echo signal data blocks coincides with the

Transmission time of an ultrasonic pulse begins and the time period length of each of the time segments, for example, the time difference between the transmission times of two successive

Ultrasonic pulses corresponding to the pixels of a grid column are determined at least substantially by a respective ultrasonic impulse response (i.e., at least substantially by reflections of the ultrasound pulse emitted at the beginning of the respective time period). In this case, the pixels located at the same position in different grid columns represent, for example, a signal component of the signal represented by the ultrasonic echo signal data

Ultrasonic echo signal, at least substantially to a reflection of the respective Ultrasonic pulse at a reflection object in each case at the same distance (eg at the same distance from the ultrasonic sensor and / or ultrasonic transmitter) goes back.

The signal component of the ultrasound echo signal represented by the ultrasound echo signal data which is based on reflections of a plurality of successive ultrasound pulses on an immobile reflection object is represented in such a pixel arrangement by, for example, pixels located in successive raster columns at the same position. By contrast, the signal component of the ultrasound echo signal represented by the ultrasound echo signal data due to reflections of a plurality of successive ultrasound pulses on a moving reflection object is represented in such a pixel arrangement, for example by pixels which are located at different positions in successive raster columns.

This is advantageous, for example, to signal components attributable to reflections in the ultrasound echo signal represented by the ultrasound echo signal data, for example with

Recognize and analyze image processing algorithms. Furthermore, a human observer is also enabled by such a pixel arrangement, reflecting signal components of the ultrasound echo signal data which are based on reflections

Detect and / or analyze ultrasonic echo signal. For example, the method of the invention involves applying a

An image processing algorithm such as a two-dimensional filter (e.g., a two-dimensional Hamming filter) on the graphical representation and / or a graphically representable ultrasound echo signal data structure obtained as a result of determining the graphical representation. For example, grouping multiple data points of the ultrasound echo signal data into one or more data point clusters is based at least in part on the graphical representation (e.g., the pixel array described above) and / or a graphically representable ultrasound echo signal data structure obtained as a result of determining the graphical representation. For example, grouping multiple data points of the ultrasound echo signal data into one or more data point clusters includes applying a clustering algorithm to the graphical representation (e.g., the pixel array described above) and / or one as a result

Determining the graphical representation obtained graphically

Ultrasonic echo signal data structure. The clustering algorithm can be, for example, a hierarchical, a density-based or a partitioning clustering algorithm as well as a combination of different clustering algorithms be. An example of a density-based clustering algorithm is the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm.

According to an exemplary embodiment of the invention, grouping a plurality of data points of the ultrasound echo signal data into one or more data point clusters comprises

Applying a clustering algorithm to the ultrasonic echo signal data and / or data points of the ultrasonic echo signal data. This can be done, for example, by applying a clustering algorithm to the graphical representation (e.g., the pixel array described above) and / or a graphically-representable ultrasound echo signal data structure obtained as a result of determining the graphical representation.

According to an exemplary embodiment of the method according to the invention, the characteristics comprise at least one or more of the following information:

Amplitude, frequency and / or phase information,

Information about a location, distribution, shape, morphology, pattern and / or extent of a data point cluster (e.g., a data point cluster of data point clusters),

Information about a reflection energy of the signal component of the ultrasonic echo signal represented by the data points of a data point cluster (for example, a data point cluster of the data point clusters) of the ultrasonic echo signal represented by the ultrasonic echo signal data,

Information about a signal delay of the signal component of the ultrasonic echo signal represented by the ultrasound echo signal data, represented by the data points of a data point cluster (e.g., a data point cluster of the data point clusters). The characteristics are, for example, at least partially depending on the

Ultrasound echo signal data determined (e.g., at least in part, as a function of one or more data points of the ultrasound echo signal data).

As described above, the characteristics include, for example, amplitude, frequency and / or phase information.

Amplitude information may be obtained, for example, by determining an average of the amplitude (eg, an average of the signal strength) of the signal portion of the ultrasonic echo signal represented by one or more data points of a data point cluster (eg, a data point cluster of data point clusters). By an average, for example, the median, the arithmetic mean and / or the geometric mean to be understood. For example, the characteristics include one or more such averages as Amplitude information, Such amplitude information, for example, allow conclusions about the signal component of a previously transmitted reflected by a reflection object

Ultrasonic pulse. This is for example advantageous to different types of

Reflect reflection objects from each other and classify accordingly.

Frequency information may be obtained, for example, by determining a frequency spectrum of the signal portion of the ultrasonic echo signal represented by one or more data points of a data point cluster and / or a frequency difference between the frequency of one or more data points of a data point cluster (eg, a data point cluster of data point clusters ) signal component of the ultrasonic echo signal and the frequency of a previously transmitted ultrasonic pulse are obtained. For example, the characteristics include a representation of the frequency spectrum and / or the value of the frequency difference as

Frequency information. An analysis of the frequency spectrum can be, for example, evidence of a frequency shift due to the Doppler effect in a reflection on a moving

Reflection object result. For example, the presence of a frequency difference may directly indicate a frequency shift due to the Doppler effect of a reflection on a moving reflection object. The frequency shift is dependent on the movement speed and the direction of movement of the reflection object.

Frequency information is thus advantageous, for example, to distinguish different fast-moving reflection objects from each other and to be able to classify accordingly.

Phase information may be obtained, for example, by determining a phase change between the phase of the data passing through one or more data points of a data point cluster (e.g.

Data point clusters of the data point clusters) and the phase of the signal portion of the ultrasonic echo signal represented by one or more other data points of the data point cluster. For example, such a phase change may be determined by comparing the phases of the ultrasonic echo signal portions represented by multiple data points of a data point cluster of successive ultrasonic echo signal data blocks. A phase change may, for example, be due to a reflection on a moving reflection object. The phase change is dependent on the movement speed and the direction of movement of the reflection object. Phase information is thus advantageous, for example, to distinguish different fast moving reflection objects from each other and to be able to classify accordingly. Alternatively or additionally, the characteristic data can contain information about the reflection energy and / or signal propagation time of the (eg a data point cluster of the data point cluster) represented by a data point cluster (eg, at least substantially reflections on a reflection object declining) signal portion of the signal represented by the ultrasonic echo signal data

Include ultrasonic echo signal.

Information about the reflection energy may be obtained, for example, by determining the value of the energy of the signal portion of the one of the .sup. (1) signal represented by a data point cluster (e.g., at least substantially due to reflections on a reflection object)

Ultrasonic echo signal data representative ultrasonic echo signal can be obtained. For example, the characteristics include one or more such energy values as information about the reflection energy. If necessary, these characteristics allow conclusions to be drawn about the reflection surface and / or the reflection angle.

Signal propagation time information can be obtained, for example, by determining the signal propagation time of the data point cluster represented by one or more data points of a data point cluster (e.g.

at least substantially due to reflections on a reflection object)

Signal component of the ultrasonic echo signal represented by the ultrasound echo signal data can be obtained. For example, the minimum and maximum signal propagation times of the signal component represented by a data point cluster (e.g., at least substantially due to reflections on a reflection object) may be represented by the ultrasound echo signal data

Ultrasonic echo signal can be determined. For example, the characteristics include one or more values of such signal propagation time as signal propagation time information. These characteristic data are, for example, an indication of the position of the reflection object, such as the distance between the reflection object and the ultrasound sensor and / or ultrasound transmitter. Also, these characteristics allow, for example, conclusions on outside dimensions of the reflection object (e.g., a height and / or width of the reflection object). For example, outside dimensions of a

Reflection object at least partially determined and / or estimated depending on these characteristics (for example, by a comparison with corresponding characteristics when no reflection on a reflection object or a reflection takes place on another reflection object). For example, outer dimensions of different reflection objects can be compared. This is advantageous, for example, to reflection objects with different outer dimensions

to differentiate and classify.

Alternatively or additionally, the characteristic data can describe, for example, characteristic properties of the data point clusters. These include, for example, information about the location, distribution, shape, morphology, pattern, and extent of a data point cluster. For example, these characteristics allow a description and analysis of the backscatter pattern. By information about the localization, distribution, shape, morphology, pattern and extent of a data point cluster is meant, for example, the geometric shape of a reflection pattern and / or the energy distribution in the different dimensions and / or the typical reflection paths of a particular object and / or object type , This is advantageous, for example, in order to be able to recognize typical reflection patterns for certain types of reflection objects.

According to an exemplary embodiment of the method according to the invention, the classification of one or more of the reflection objects comprises one or more of the following steps: detection of one or more of the reflection objects,

Associating one or more of the reflection objects with an object class,

Determining a probability of belonging to one or more

Reflection objects to an object class. The detection of one or more of the reflection objects should, for example, be understood as the detection of the presence of one or more reflection objects in the detection area of the ultrasound sensor. This can be done, for example, based on the data point clusters. For example, it is assumed that the data points of a data point cluster at least substantially represent rejections of the ultrasound pulses on a reflection object attributable signal components of the ultrasound echo signal. Accordingly, one or more of the reflection objects are recognized, for example, when the data points become one or more

Grouping of data point clusters.

An object class includes, for example, reflection objects of a certain type, for example, traffic objects of a certain type, such as pedestrians, cyclists, motor vehicles (e.g.

Motorcycles, passenger cars, trucks), etc.

For example, based on the characteristics, the reflection objects (e.g., the detected reflection objects) are assigned (i.e., classified as an object of that object class) to an object class.

As described in detail below, such assignment of the reflection objects to an object class can be done, for example, by a machine learning algorithm and / or a machine learning technique. The assignment of the reflection objects to an object class can also be based on a given

Decision tree done. For example, in a first stage of a decision tree for assigning the reflection objects to a traffic object class, it can be decided whether the respective reflection object is a pedestrian, a bicycle or a motor vehicle, and be assigned accordingly. This assignment may, for example, at least partially in response to an estimated and / or specific speed of the respective

Reflection object are taken. In a simple example, reflection objects with an estimated speed less than 10 km / h of the traffic object class pedestrian,

Reflection objects with an estimated speed between 10 and 25 km / h

Traffic object class cyclists and reflection objects with an estimated speed greater than 25 km / h of traffic object class motor vehicles are assigned. In addition to the speed, characteristics of the reflection objects such as external dimensions and / or the position (such as the distance between the light source) and the position can be determined on the basis of the characteristic data

Reflection object and the ultrasonic sensor and / or ultrasonic transmitter) determined and / or estimated and taken into account in the assignment. Subsequently, in an optional further stage of the decision tree, if it has been decided that the respective reflection object is a motor vehicle, it may be decided whether it is a lorry or a truck

Passenger car or a motorcycle / scooter. The assignment can be further refined in optional further stages of the decision tree.

Alternatively or additionally, based on the characteristic data, a probability for the membership of the reflection objects to an object class is determined. The reflection objects are then assigned, for example, to the object class with the highest probability. The determination of the probability is advantageous, for example, in order to allow more accurate extrapolations, for example in the case of statistical evaluations (for example a traffic statistic and / or an averaging over time). According to an exemplary embodiment of the method according to the invention that includes

The method further comprises estimating and / or determining (e.g., approximating) location and / or motion information of one or more of the reflection objects.

As described above, the signal propagation time of a signal component of the ultrasound echo signal represented by the ultrasound echo signal data is dependent on the distance in which a reflection object from the ultrasound transmitter and / or the ultrasound sensor is located. Accordingly, you can

Location information (eg the distance) of a reflection object can be estimated and / or determined, for example, based on the signal propagation time of a signal component of the ultrasound echo signal at least substantially reflected by the reflection object. Movement information can for example be estimated and / or determined based on frequency and / or phase information of a signal component of the ultrasound echo signal, which is at least substantially reflected by the reflection object, of the ultrasound echo signal represented by the ultrasound echo signal data. As described above, an analysis of the frequency spectrum of the signal component may, for example, give indications of a frequency shift due to the Doppler effect in a reflection on a moving reflection object. For example, the presence of a frequency difference may also directly indicate a frequency shift due to the Doppler effect in a reflection on a moving reflection object. The

Frequency shift is dependent on the speed and the direction of movement of the reflection object, so that the speed and the direction of movement can be estimated and / or determined based on it. For example, the include

Motion information is a value of the velocity and / or a representation of the direction of the reflection object. According to an exemplary embodiment of the invention, the classification of the

Ultrasound echo signal data at least in part depending on a machine learning algorithm and / or a machine learning technique.

For example, an assignment of the reflection objects to an object class by a

Algorithm for machine learning and / or a technique of machine learning done.

Machine learning may be in the form of supervised machine learning or unsupervised machine learning, for example. In supervised machine learning, for example, the result of the classifying is compared with reference results and / or data, and the

Algorithm adjusted accordingly. For example, the reference results and / or data may be from another sensor (e.g., an imaging sensor such as a camera) or other device, or may be obtained through laboratory testing

For example, reference results and / or data may be performed during an initial training phase or permanently. Furthermore, machine learning may also include pre-information such as e.g. take into account the static environment of the detection range of the ultrasonic sensor (for example, the number and course of lanes as well as immobile objects such as houses in the detection area).

Techniques of machine learning include, for example, an artificial neural network, a support vector machine, a linear discriminant analysis, or a combination of these techniques. According to an exemplary embodiment of the method according to the invention, the method further comprises providing the result of classifying for one or more

Applications. Such an application can be realized, for example, by a computer program executed on a processor.

By providing the result of classifying, it should be understood, for example, that the result is communicated to the application and / or a device executing the application. These devices can be, for example, a server, for example a cloud and / or backend server and / or one or more further devices according to the invention and / or a control device (eg a control device for controlling a light source such as one from the company ICE Gateway GmbH distributed ICE Gateway) act. For example, the inventive apparatus comprises communication means arranged to communicate the result of the classifying. An example of such

Communication means, as described above, a communication interface, such as a wireless communication interface or a wired communication interface.

For example, the application takes into account the results of classifying by a variety of devices of the invention. For example, the device executing the application receives (receives) the results of classifying a plurality of devices of the invention.

One possible application for classifying moving reflection objects is, for example, traffic counting and / or monitoring. For such a traffic counting and / or monitoring, for example, the respective object class (eg traffic object class) obtained as a result of the classification or a probability distribution of object classes of the recognized reflection objects can be provided. For example, based on this, a traffic and / or vehicle density of the lanes located in the detection area of the ultrasound sensor can be determined. Further, for example, location information can also be provided for this purpose, for example, to allow a traffic lane to precisely determine the traffic and / or vehicle density. Furthermore, further information about individual reflection objects, such as a location and motion information, complementary to this data exist. By optionally considering the results of the classification by a plurality of devices according to the invention, for example, a large-scale traffic counting and / or monitoring can be achieved, which incorporates the results of the classification at the respective locations of the plurality of devices according to the invention. Another possible application for classifying reflection objects is, for example, parking space monitoring. For such a parking space monitoring, for example, the respective object class (eg vehicle type) obtained as a result of the classification and location information of the detected reflection objects can be provided. The status (eg occupied or free) of an im

Detection range of the ultrasonic sensor parking lot, for example, at least partially based on the provided results and, for example, further information about the parking lot (for example, location information, size information, etc.) and / or before

provided results. For example, it is determined that the parking lot is occupied when, at the location of the parking lot, an object of a predetermined object class is recognized for a predetermined period of time. Also for this purpose, the results of the classification can be optionally taken into account by a plurality of devices according to the invention. In one possible application, the detected objects or the status (e.g., occupied or vacant) of one or more parking spaces may be further processed by the apparatus of the invention and / or to others

Devices are communicated (e.g., communicated to other device by means of communication from the device of the invention). The communication link is, for example, a direct connection (e.g., a peer-to-peer connection via a wireless local area network such as WLAN) or an indirect connection (e.g., a connection over the Internet). The other device is, for example, a mobile user device (e.g., a mobile phone such as a smartphone). For example, a user may, by means of his user device (e.g., by means of a computer program running thereon such as an app), have one

Reserve a free parking space and / or pay a parking fee and / or report a wrongly booked parking space.

Another possible application is, for example, a controller. For example, if the provided result of the classification corresponds to a given result, then

Control a control signal (e.g., a predetermined control signal) are output. It will be understood that the control signal may depend, at least in part, on other results and / or events (e.g., signals detected by other sensors and / or other sensor types). Such a control signal may be used, for example, to drive an actuator (for example a lighting device and / or a camera). For example, the actuator may be activated by the control signal when a moving

Object is detected. For example, the actuator is part of the device according to the invention. However, embodiments are also possible in which the actuator is separate from the device according to the invention. For example, the inventive device comprises communication means arranged to communicate the control signal to the actuator. An example of such

Communication means, as described above, a communication interface, such as a wireless communication interface or a wired communication interface. Such an actuator is for example a lighting means and / or a control device for controlling a lighting means.

There are also other applications such as traffic logic, prediction, decision level,

Visualization for users (e.g., customers and / or users) is conceivable. For example, a user visualization application provides a way to present the recognized data to a user, such as a Web site.

Furthermore, the results of the classification can also be used as feedback, for example in order to influence the grouping of a plurality of data points of the ultrasound echo signal data, the determination of characteristic data and / or the normalization of the ultrasound echo signal data.

According to an exemplary embodiment of the inventive method, the method further comprises re-grouping a plurality of data points of a data point cluster into one or more new and / or existing data point clusters. This allows, for example, a correction of incorrectly grouped and / or separated data point clusters.

According to an exemplary embodiment of the method according to the invention, the method further comprises:

Fusing the ultrasound echo signal data with further ultrasound echo signal data, and / or

Fusing the characteristics with other characteristics, the other characteristics were determined at least partially as a function of other ultrasonic echo signal data.

For example, the further ultrasound echo signal data may represent an ultrasound echo signal detected by another ultrasound sensor. Alternatively or additionally, the further ultrasound echo signal data may represent, for example, the time profile of the signal strength of a further ultrasound echo signal, which is at least substantially dependent on reflections from

Ultrasonic pulses of another ultrasonic transmitter and / or ultrasonic sensor comprises returning signal components.

By fusing the ultrasound echo signal data with further ultrasound echo signal data, it should be understood, for example, that the ultrasound echo signal data with the other

Ultrasonic echo signal data compared, summarized and / or enriched.

Accordingly, the merging of the characteristic data with further characteristic data should be understood to mean that the characteristic data are compared, combined and / or enriched with the further characteristic data. The fused ultrasound echo signal data can, for example, with regard to different characteristics such as amplitude, signal delay, phase and frequency differences or more

Characteristics such as reflection patterns are evaluated. Basically, fusing can take place both before classifying and after classifying.

The merging is advantageous, for example, if it takes place before classifying in order to increase the data basis for the classification and thus to be able to improve the result of the classification, for example by using location information and / or

Triangulation techniques and / or other signal-level fusion techniques. One way of doing this is beamforming that determining location information of one or more

Reflection objects based on fused ultrasound echo signal data (e.g., multiple

Ultrasonic sensors) allows.

According to an exemplary embodiment of the method according to the invention, the method further comprises normalizing the ultrasound echo signal data.

For example, normalizing the ultrasound echo signal data comprises normalizing at least a first data point of the ultrasound echo signal data at least partially as a function of at least one second data point of the ultrasound echo signal data, wherein the first data point represents the value of the signal strength of the detected ultrasound echo signal at a first detection time, the second data point of the ultrasound echo signal data Represents the signal strength of the detected ultrasonic echo signal at an earlier second detection time, wherein normalized ultrasonic echo signal data comprising the normalized first data point is obtained as a result of normalizing the ultrasonic echo signal data. For example, the first data point and the second data point are associated with the same signal propagation time and / or are, for example, in the same position in successive ultrasound echo signal data blocks. By normalizing the ultrasound echo signal data, according to a first aspect, it should be understood, for example, that reflections of one or more previously emitted ultrasound pulses on immobile and / or quasi-stationary reflection objects result in the normalized ultrasound echo signal represented by the normalized ultrasound echo signal data according to the first aspect detected ultrasonic echo signal are at least partially reduced. This first aspect is advantageous, for example, when moving reflection objects (for example traffic objects in the context of traffic monitoring) are to be classified in order in this case to interfere with reflections on immobile and / or quasi-stationary reflection objects to reduce returning signal components. According to a second aspect, standardizing the ultrasound echo signal data in the present case is understood, for example, to be at least partially reduced to reflections of one or more ultrasound pulses previously emitted on moving objects in the normalized ultrasound echo signal represented by the normalized ultrasound echo signal data according to the second aspect compared to the detected ultrasound echo signal , This second aspect is advantageous, for example, when non-moving reflection objects (for example in the context of parking space monitoring) are to be classified. By a combination of the first and second aspects, the signal components attributable to reflections on stationary and / or quasi-stationary objects and those due to reflections on moving objects can be separated from one another.

The normalization of at least the first data point of the ultrasound echo signal data according to the first and the second aspect takes place, for example, by determining a normalized first data point based at least on the first data point and the second data point. For example, a representation of a value of signal strength included in the normalized first data point is based on that of the first data point and the second data point

determined values of the signal strength of the detected ultrasonic echo signal. As a result of normalizing the ultrasonic echo signal data, for example, normalized

Obtained ultrasound echo signal data, which include at least the normalized first data point.

For example, normalizing at least the first data point includes at least one of:

Determining a signal strength average at least in response to the values of the signal strength of the ultrasonic echo signal represented by the first data point and the second data point;

Determining a signal strength standard deviation and / or a signal strength variance at least partially as a function of the values of the signal strength of the ultrasonic echo signal represented by the first data point and the second data point;

Dividing the signal strength average by the signal strength standard deviation;

Subtracting the signal strength average from that of the first data point

represented value of the signal strength of the detected ultrasonic echo signal; and

Dividing the result of the subtraction of the signal strength average from the value of the signal strength of the detected ultrasonic echo signal represented by the first data point by the signal strength standard deviation. According to an exemplary embodiment of the inventive method, the method further comprises applying an analysis and compensation algorithm to the

Ultrasonic echo signal data such as a multi-reflection analysis algorithm compensation and / or for propagation analysis / compensation. This is advantageous, for example, to compensate for different signal propagation times of the signal components due to reflections on a reflection object due to multiple reflections. This can be done, for example, by prior knowledge of the reflection patterns of different objects and / or learned information about reflection patterns, which enable compensation and / or further analysis.

According to an exemplary embodiment of the invention, the device according to the invention is a control device for controlling a luminous means, comprises a control device for controlling a luminous means and / or is part of a control device for controlling a luminous means. For example, the device according to the invention comprises means which are arranged to control one or more light sources. For example, the control may be at least partially dependent on the result of classifying the ultrasound echo signal data. An example of such

Control device is for example a control device for a traffic light system and / or one or more street lamps.

Such a control device for controlling a luminous means of a lamp in the outer region is described for example in the patent application with the file reference DE 10 2014 102 678.0, which is incorporated herein by reference. Furthermore, such a device is for example a device manufactured by the company ICE Gateway under the product name ICE Gateway.

By controlling a luminous means (for example a luminous means connected to the device), it should be understood, for example, that the luminous means are switched on, switched off and / or dimmed.

For example, the device according to the invention further comprises one or more

Power supply means. For example, the power supply means are set up with the

Be connected to bulbs and the bulbs to provide energy and / or provide power to operate the bulbs. For example, the lighting means are controlled by controlling the power supply means. For example, the include

Power supply means a power converter, a controllable driver circuit and / or a controllable voltage converter (for example, a controllable DC-DC converter).

The luminous means is preferably a DC-based luminous means. For example, the illuminant is an LED (Light Emitting Diode) and / or an OLED (Organic Light Emitting Diode). However, the light source can also be an AC-based light source. For example, the illuminant is a light bulb and / or a gas discharge lamp. For example, the lighting means are controlled at least in part depending on the result of the evaluation of the ultrasonic echo signal data. For example, the light bulbs are turned on or turned up at certain results of the classification, and turned off or dimmed at other results of the classification.

As a result, for example, a device for controlling a lighting means with further

Functions such as processing of ultrasonic echo signal data provided. This is advantageous, for example, since there is no additional provision for the provision of the further functions

Installation costs must be operated and can be used on the existing means of the device for controlling the bulb. Also, such devices for controlling a lighting device are typically part of a lighting system (e.g.

Lighting system of a city), which has a variety of devices for controlling a

Includes lighting, so that thereby a large public area can be covered. For example, the device according to the invention can be arranged or arranged on or in a lamp in the exterior, in particular a street lamp. For example, the

Device according to the invention part of a lighting device such as a lamp, for example a lamp in the outdoor area, in particular a street lamp and / or a lamp of a traffic light system.

Under arranged on or in a lamp in the outdoor area to be understood, for example, that the device according to the invention within the lamp (eg in the lamp head or in the mast) and / or on the housing of the lamp (eg on the lamp head and / or on the mast) is mounted. For example, the device according to the invention is arranged in the luminaire, on or on the luminaire, in the lantern and / or on the lantern.

According to an exemplary embodiment of the invention, the device according to the invention is located at or in a bus stop, at or on a platform, at or in a public place, at a traffic light intersection, at or in a public building (for example at an entrance and / or

Exit door) and / or attached to measure the influx of objects (such as vehicles, passers-by and / or visitors).

According to an exemplary embodiment of the invention, the system according to the invention further comprises one or more control devices for controlling a luminous means. It goes without saying that the system according to the invention can alternatively or additionally comprise further external components (eg sensors, servers and / or devices). According to an exemplary embodiment of the invention, the system according to the invention is a lighting system (eg a city).

According to an exemplary embodiment of the invention, the system according to the invention further comprises one or more further devices according to the invention and / or one or more servers.

Further advantageous exemplary embodiments of the invention are given in the following detailed description of some exemplary embodiments of the present invention, in particular in conjunction with the figures. However, the figures enclosed with the application are intended only for the purpose of clarification but not for determining the scope of protection of the invention. The accompanying drawings are not necessarily to scale and are merely exemplary of the general concept of the present invention. In particular, features included in the figures should by no means be considered as a necessary part of the present invention.

Show it:

1 is a block diagram of the electronic components of an exemplary embodiment

Embodiment of a device according to the invention;

FIG. 2 is a block diagram of an exemplary embodiment of a

system according to the invention;

3 shows a flow chart of an example of a method according to the invention;

4 shows a flow chart of an example of a method according to the invention;

Fig. 5a is a flow chart of an example of a modified DBSCAN clustering algorithm;

5b is a flowchart of an example for determining the number of

Data Points in an Epsilon Neighborhood in the Modified DBSCAN Clustering Algorithm FIG. 6 is an exemplary graphical representation of one of

Ultrasonic echo signal data represented ultrasound echo signal; FIG. 7 is an exemplary graphical representation of an ultrasonic echo signal represented by a plurality of consecutive ultrasound echo signal data blocks; FIG.

8 is an exemplary illustration of a graphical representation of

Ultrasonic echo signal data;

9a and 9b an exemplary representation of a graphical representation of

Ultrasonic echo signal data before and after applying the modified DBSCAN clustering algorithm;

Fig. 1 is a block diagram of an exemplary embodiment of the invention

Device 10.

Processor 11 of device 10 is designed in particular as a microcontroller or microprocessor. Processor 11 executes program instructions stored in program memory 12 and stores, for example, intermediate results or the like in main memory 13. For example, program memory 12 is a non-volatile memory such as a flash memory

Magnetic memory, an EEPROM memory, a persistent memory such as a ROM memory and / or an optical memory. Main memory 13 is, for example, a volatile or nonvolatile memory, in particular a random access memory (RAM) such as a static RAM (SRAM), a dynamic random access memory (DRAM). Preferably, program memory 12 and main memory 13 are arranged together with processor 11 in a module, processor 11 is, for example, operationally with program memory 12 and

Main memory 13 connected, for example via a bus.

In program memory 12, for example, program instructions are stored which cause the processor 11 and / or device 10, when the processor 11 executes the program instructions, to be at least partially illustrated in FIG. 3 and / or FIG. 4 and / or FIGS. 5a and 5b Execute and / or control procedures.

Device 10 includes an ultrasonic sensor 14. However, embodiments are also possible in which the ultrasonic sensor 14 is not a part of the device 10, but is separate from the device 10, for example. The ultrasonic sensor 14 is formed, for example, as a combined ultrasonic detector and ultrasonic transmitter.

Accordingly, ultrasound sensor 14 is adapted to detect an ultrasound echo signal. The ultrasonic sensor 14, for example, communicates ultrasonic echo signal data to the processor 11, which is a representation of the time course of the signal strength of the detected

Ultrasonic echo signal are. For detecting the ultrasonic echo signal, the ultrasonic sensor 14 has, for example, a piezoelectric transducer which converts an ultrasonic echo signal detectable at the position of the ultrasound sensor 15 into an electrical signal. Furthermore, the

For example, an ultrasonic sensor may include other components for processing the electrical signal (e.g., one or more filters such as one or more bandpass filters, a mixer such as a

Down-converter, etc.] and for analog-to-digital conversion of the electrical signal and for obtaining the ultrasonic echo signal data (e.g., an analog-to-digital converter such as a delta-sigma converter and / or a parallel converter).

On the other hand, ultrasonic sensor 14 is set up, for example, one or more

Send ultrasonic pulses, for example, when a corresponding control signal from the processor 11 to the ultrasonic sensor 14 is received. To send the ultrasonic pulses of the

Ultrasonic sensor 14 also have a piezoelectric transducer, which converts an electrical signal into one or more ultrasonic pulses. Preferably, the same piezoelectric transducer may be used for emission and detection.

Processor 11 is, for example, operatively connected to ultrasonic sensor 14, for example via a bus.

For example, the optional wireless communication interface 15 is configured to communicate in accordance with one or more wireless communication techniques. In the following, it is assumed by way of example that the wireless communication interface 15 supports the communication via a local radio network and a mobile radio network. For example, the wireless communication interface 15 is at least partially formed by a transceiver of the local radio network technology, a transceiver of the mobile radio technology and one or more antennas. As disclosed above, an example of a local radio network technique RF1D, NFC, Bluetooth and / or WLAN; and an example of a mobile technology is GSM, UMTS and / or LTE. Optionally, the wireless communication interface 15 may only be one of these wireless ones

Communication techniques or other wireless and / or wired

Support communication techniques. For example, the processor 11 may communicate via the wireless communication interface 15 with other devices such as a server, a remote monitoring device, one or more separate ultrasonic sensors, and / or other devices of the invention. For example, processor 11 is operatively connected to wireless communication interface 15, for example via a bus. For example, the wireless

Communication interface 15 receive or interrogate information from other devices and forward to processor 11 and / or receive information from processor 11 and send it to other devices. For example, processor 11 controls the communication interface 15 at least partially.

FIG. 2 is a block diagram of an exemplary embodiment of the inventive system 20. The system 20 includes the device 10 with the ultrasonic sensor 14 (not shown in FIG. 2). Optionally, the system 20 may comprise further devices according to the invention, ultrasound sensors and / or ultrasound transmitters and one or more servers.

Device 10 is mounted in system 20, for example, in a Sidefire configuration on a mast of a street lamp, and angularly (i.e., obliquely, that is, neither vertically nor horizontally) aligned with the road surface. In the detection range of the ultrasonic sensor 15 are in the example scenario shown in FIG. 2, both moving objects 21, 22, 23 and 24 and a stationary object 25th

3 is a flowchart 300 that exemplifies the steps of a method according to the invention. The steps illustrated in flowchart 300 are executed and / or controlled by means of the device 10, for example. For example, the steps are at least partially executed and / or controlled by the processor 11 of the device 10.

In a step 301, ultrasound echo signal data are obtained at the device 10, wherein the ultrasound echo signal data at least partially represent an ultrasound echo signal detected by the ultrasound sensor 14. The ultrasonic echo signal data is obtained at the device 10, for example, by detecting the ultrasonic echo signal by the ultrasonic sensor 14.

The ultrasound echo signal data are, for example, a representation of the time profile of the signal strength of the ultrasound echo signal detected by the ultrasound sensor. Each data point of the ultrasonic echo signal data includes, for example, a representation of a value of the signal strength of the detected ultrasonic echo signal at a detection timing and a representation of the detection timing. An exemplary graphical representation 60 of the

Ultrasonic echo signal data represented ultrasonic echo signal 61 is shown in Fig. 6. Everyone Signal point of the ultrasonic echo signal 61 corresponds to a data point of

Ultrasonic echo signal data. In Fig. 6, the ultrasonic echo signal 61 as a time course of

Signal strength shown. Accordingly, the time t is plotted on the abscissa 62 and the signal strength s (t) is plotted on the ordinate 63.

In the graph 60 of the ultrasound echo signal data represented

Ultrasonic echo signal 61 is a possible example of a first data point corresponding to a first signal point designated by the reference numeral 64. In this example, the first one includes

Data point, for example, a representation of the value of the signal strength s (ti) and a

Representation of the first detection time ti. A possible example of a signal point corresponding to a second data point is provided with the reference numeral 65, so that the second data point, for example, a representation of the value of the signal strength s [tz] and a

Representation of the second detection time t ₂ includes. The second detection time t ₂ is earlier in time than the first detection time tj. In addition, the data points of the

In a step 302, a plurality of data points of the ultrasonic echo signal data are grouped into one or more data point clusters. As described above, grouping a plurality of data points of the ultrasound echo signal data into one or more data point clusters may include applying a clustering algorithm to the data points of the ultrasound echo signal data.

In a step 303 characteristic data are determined at least partially as a function of a data point and / or a plurality of data points of a data point cluster of the ultrasonic echo signal data. As a result of the determination, in step 303, for example, the characteristics are obtained. The characteristics include, as described above, for example, amplitude, frequency and / or phase information (eg, amplitude, frequency and / or phase information of one or more data points represented signal portion of the ultrasonic echo signal) and / or information about the morphology, the pattern and / or the location of one or more data point clusters.

In a step 304, one or more of the reflection objects (eg, objects 21 to 25) located in the detection range of the ultrasonic sensor 14 are classified at least in part based on the characteristics obtained as a result of the determination in step 303. For example, the characteristics are chosen to allow classifying the reflection objects. For example, classifying includes detecting one or more of the reflection objects. By recognizing one or more of the reflection objects, for example, the recognition of the presence of one or more reflection objects in the detection area of the ultrasound sensor 14 should be understood. This can be done, for example, based on the data point clusters. For example, it is assumed that the data points of a data point cluster at least substantially represent reflections of the ultrasound pulses on a reflection object attributable signal components of the ultrasonic echo signal. Accordingly, one or more of the reflection objects are recognized, for example, if the data points were grouped into one or more data point clusters in step 303.

Based on the characteristic data, the reflection objects are assigned, for example, to an object class in step 304. For example, an object class includes reflection objects of a particular type, such as pedestrians, cyclists, or motor vehicles (e.g., motorcycles,

Passenger cars, lorries).

For example, the assignment of the reflection objects to an object class, as described above, can be done on the basis of a given decision tree or by a machine learning algorithm and / or a machine learning technique. For example, such a machine learning algorithm receives the characteristics determined in step 303 as input and / or start data.

Alternatively or additionally, based on the characteristic data, a probability for the

Affiliation of the reflection objects to an object class determined. The reflection objects are then assigned, for example, to the object class with the highest probability.

4 is a flowchart 400 that exemplifies the steps of a method according to the invention. The steps illustrated in flowchart 400 are executed and / or controlled by means of device 10, for example. For example, the steps are at least partially executed and / or controlled by the processor 11 of the device 10.

In a step 401, the device 10 emits one or more ultrasound pulses and / or causes the emission of the ultrasound pulses. For example, the ultrasonic pulses are emitted at regular time intervals TR. Alternatively or additionally, for example, the emission of the ultrasound pulses is initiated at regular time intervals TR. Preferably, the emitted ultrasonic pulses are the same. For example, the transmitted ultrasound pulses are based on a time-limited prototype pulse that is modulated and / or frequency-shifted to an ultrasound carrier frequency (eg, 44 kHz). For example, the ultrasonic pulses are emitted by the ultrasonic sensor 14 in step 401. For example, the processor 11 drives the ultrasonic sensor 14 to cause the ultrasonic sensor 14 to emit the ultrasonic pulses.

In a step 402, ultrasound echo signal data are obtained at the device 10, wherein the ultrasound echo signal data at least partially represent an ultrasound echo signal detected by the ultrasound sensor 14. The ultrasonic echo signal data is obtained at the device 10, for example, by detecting the ultrasonic echo signal by the ultrasonic sensor 14. For example, step 402 corresponds to step 301 described above in connection with flowchart 300 shown in FIG.

As described above, the ultrasound echo signal data is, for example, a representation of the time profile of the signal strength of the ultrasound echo signal detected by the ultrasound sensor 14. For example, the ultrasound echo signal represented by the ultrasound echo signal data includes, at least substantially, reflections from the ultrasound pulses emitted at step 401 on moving objects (e.g., objects 21 through 24 in Fig. 2) and stationary objects (e.g., object 25 in Fig. 2). An exemplary graphical representation 60 of the

Ultrasonic echo signal data represented ultrasonic echo signal 61 is, as described above, shown in Fig. 6.

In a step 403, the ultrasonic echo signal data is divided into several

Ultrasonic echo signal data blocks divided, for example, the processor 11 subdivided the

Ultrasonic echo signal data in multiple ultrasound echo signal data blocks. Here are the

Ultrasonic echo signal data is divided into a plurality of ultrasonic echo signal data blocks such that the

Ultrasonic echo signal data blocks represent successive periods of equal time segment length of the time course of the value of the signal strength of the detected ultrasonic echo signal, wherein a first ultrasonic echo signal data block the first data point and a second

Ultrasonic echo signal data block comprises the second data point.

For example, each of the time periods begins with the transmission time of an ultrasonic pulse. This has the effect in the present case that the length of the period of each of the time periods

for example, corresponds to the time interval TR between the transmission times of two successive ultrasonic pulses. Furthermore, the temporal profile of the signal strength of the detected ultrasonic echo signal represented by an ultrasound echo signal data block is in this case at least substantially reflected by reflections at the beginning of the respective time segment emitted ultrasound pulse is determined and is thus hereinafter referred to by way of example as an ultrasonic impulse response.

The beginning of a period of time can be done for example by the exact knowledge of the transmission times. For example, when the processor 11 drives the ultrasonic sensor 14 to cause the ultrasonic sensor 14 to transmit the ultrasonic pulses, the processor 11 knows the transmission timing of the ultrasonic pulses. Alternatively or additionally, corresponding transmission time data representing one or more transmission times of one or more ultrasonic pulses, in

Program memory 12 may be stored. Alternatively or additionally, the transmission time of an ultrasonic pulse can also be determined. For example, if the ultrasound sensor 14 is a combined ultrasound detector and ultrasound transmitter, it may be determined by analysis of the remaining feedback of a transmitted ultrasound pulse into the ultrasound detector (e.g., feedback through common components of the ultrasound detector and ultrasound transmitter such as a duplexer).

An exemplary graphical representation 70 of the three consecutive graphs

Ultrasonic echo data blocks represented ultrasonic echo signal 71 is shown in Fig. 7. The ultrasonic echo signal 71 corresponds to the ultrasonic echo signal 61 shown in FIG. 6.

Accordingly, in Fig. 7 on the abscissa 72, the time t and on the ordinate 73 the

Signal strength s (t) plotted. The three consecutive time sections 74, 75 and 76 each have the time period TR selected here by way of example and start in each case with one of the transmission times To, Ti and T _{2 of} an ultrasound pulse emitted in step 401. These time intervals 74, 75 and 76 and the time course of the signal strength of the signal shown therein

Ultrasonic echo signal 71 correspond to an ultrasonic echo signal data block, respectively.

Subsequently, the ultrasound echo signal data, for example, in an optional in

Flowchart 400 step not shown normalized. As described above, normalizing the ultrasound echo signal data according to a first aspect is intended to mean, for example, that reflections of one or more previously emitted ultrasound pulses on immobile objects (eg object 25 in FIG. 2) return signal components in the normalized ultrasound echo signal represented by the normalized ultrasound echo signal data be at least partially reduced compared to the detected ultrasonic echo signal. In the following, the normalization of the ultrasonic echo signal data according to this first aspect will be described. In order to obtain normalized ultrasound echo signal data according to the second aspect, the difference between the ultrasound echo signal data obtained in step 402 and the ultrasound echo signal data normalized according to the first aspect can then be formed, for example. For example, normalizing according to the first aspect of at least a first data point of the ultrasound echo signal data comprises selecting at least a second data point at least partially in response to the first data point and determining a normalized first data point based at least on the first data point and the second data point. Various algorithms are possible for this, of which a possible algorithm is described below by way of example.

For example, the second data point is determined and / or chosen such that it is associated with the same signal propagation time At as the first data point and / or in the second

Ultrasonic echo signal data block is located at the same position as the first data point in the first ultrasonic echo signal data block. In addition to the second data point, further data points may be determined and / or selected such that they are each associated with the same signal propagation time At as the first data point and / or in their respective ultrasound echo signal data block at the same position as the first data point in the first ultrasound echo signal data block.

In the graph 70 of the ultrasound echo signal data represented

Ultrasonic echo signal 71 is a possible example of a signal point corresponding to the first data point denoted by reference numeral 77. For example, in this example, the first data point includes a representation of the value of the signal strength s (ti) and a representation of the first detection time ti. A possible example for a second data point

Signal point is provided with the reference numeral 78, so that the second data point, for example, a representation of the value of the signal strength s (tz) and a representation of the second

Detection time tz includes. The second detection time t ₂ is earlier in time than the first detection time ti.

The time difference between the first detection timing ti and the first transmission timing TI and the time difference between the second detection timing t2 and the second transmission timing T2 correspond to At, respectively. In this case, At corresponds to the signal propagation time at the beginning of the respective one

Time interval emitted ultrasonic pulse. From the signal propagation time At, the distance d of the reflecting object can be determined, unless there is multiple reflection (for example, with the following

Formula: d = -, with speed of sound v). Accordingly, both values of the signal strength s (ti) and s (t2), if there are no multiple reflections, respectively, are based on a reflection of the ultrasound pulse emitted at the beginning of the respective time segment on an object at the same distance d from the ultrasound sensor 14. For example, the second data point and optionally the other data points can be determined at least partially as a function of a window function h (t). For example, depending on the beginning of the first time interval Ti (ie, the first transmission time Ti), the window function specifies a time segment in which the second data point and possibly the other data points are located. The window function can do this specify a past time segment and / or a future time segment (eg by delaying the real-time processing of the ultrasound echo signal data).

For those of the first data point and the second data point and, if necessary, the other

Data points represented values of signal strength (e.g., s (ti) with ti = Ti + At for the first

Data point, s (t ₂ ) for the second data point) of the detected ultrasonic _{echo signal} are then determined, for example, the mean value s (T _lf At) and the variance T ^ At). The window function can do this give a weighting of the values of the signal strength represented by the first data point and the second data point and, if appropriate, the further data points. The first data point s "(ti) normalized according to the first aspect can then be determined, for example, according to the following formula: sCtJ - sCiyAt)

This has the effect that the average reflection levels and beyond the

Fluctuation variable, which is also distance-dependent, at least partially reduced and / or compensated. This will compensate for and / or reduce the static

Ambient effects, ie the effects due to reflections on stationary and / or quasi-stationary objects.

This is advantageous, for example, from the variability of both

Objects as well as the environment in the detection range of the ultrasonic sensor 15 resulting effects and disturbances to minimize. This can e.g. slight changes (e.g., moving trees, opening windows, etc.), but also objects that permanently fit in or out of the environment (e.g., parked vehicles). To take these factors into account, a time window (weighted function of several ultrasonic echo data blocks) can be used to derive, for example, characteristics of the environment (eg basic reflections of the environment, the ground and fixed objects) and the general variability of the environment (magnitude of the variation of the all-around Reflections, such as the movement of trees,

Vibrations, sensor errors and disturbances caused) can be considered. In addition, you can Individual objects (eg parked cars) that permanently change the environment are also taken into account mathematically after recognition.

For example, the normalization of at least the first data point described above is repeated for each data point of the ultrasound echo signal data. For example, the first data point is in each case the data point to be standardized according to the first aspect. For example, the second data point (and, if appropriate, each of the further data points) becomes dependent on the first one

Data point determined and / or selected. As a result of normalization (e.g., according to the first aspect), normalized

Obtained ultrasound echo signal data comprising at least the normalized first data point. If the normalization is repeated for each data point of the ultrasound echo signal data, normalized ultrasound echo signal data comprising the normalized data points (e.g., including exclusively normalized data points) is obtained as the result of normalizing (e.g., the first aspect)

Data points). In this case, the following steps of the flowchart are continued, for example, with the normalized ultrasonic echo signal data. The normalization may alternatively or additionally be performed at another time (e.g., after step 404).

As an alternative or in addition to the normalization, further analysis and compensation algorithms can be applied to the .alpha. In one or more further optional steps, for example

Ultrasonic echo signal data are applied such as algorithms for

Multiple reflection analysis / compensation and / or propagation analysis / compensation.

In a step 404, a graphical representation of the ultrasound echo signal data is determined at least in part depending on the ultrasound echo signal data blocks. The graphic

Representation is, for example, a two-dimensional representation of the ultrasound echo signal data. For example, the graphical representation is and / or includes a pixel array having pixels arranged in a raster. As a result of the determination in step 404, for example, the graphical representation and / or a graphically representable ultrasound echo signal data structure is obtained. As described above, such a graphically representable ultrasonic echo signal data structure is, for example, a two-dimensional data field and / or a data array and / or a graphics file (e.g., a graphics file in an image data format such as the bitmap format, BMP format).

8 shows an exemplary representation of a graphical representation of

Ultrasonic echo signal data. The graphical representation in Fig. 8 is a pixel array 80 with in a grid arranged pixels. For example, each pixel of the pixel array 80 is determined depending on a data point of the ultrasonic echo signal data. For example, the gray level of a pixel is determined as a function of the value of the signal strength (alternatively also frequency and / or phase) represented by the respective data point. and data points of successive ultrasonic echo signal data blocks are each represented by pixels of the pixel array 80 arranged in successive grid columns of the raster For the above-described case, each time period represented by an ultrasonic echo signal data block is represented by the pixel

Thus, for example, each grid column of the grid of the pixel array 80 represents an ultrasonic pulse response of a previously emitted

Ultrasonic pulse.

For example, the signal propagation time At with the maximum value TR is plotted on the ordinate 81 running in the direction of the grid columns. As described above, from the signal propagation time At, the distance d of the reflection object can be determined unless there is a multiple reflection (for example, with the following formula: d- with sound velocity v). The ordinate can therefore also as

Impulse response axis, distance axis or signal transit time axis. On the abscissa 82, for example, the transmission times (eg To, Ti, T ₂ ) of the ultrasonic pulses are plotted as discrete times. It thus represents the number of each detected on an ultrasonic pulse

Ultrasound impulse responses and can also be referred to as time axis.

Accordingly, the position of each pixel in FIG. 8 is determined by the transmission timing of the

Ultrasonic pulse, which determines the beginning of the time portion of the ultrasonic echo signal data block of the respective data point, and determines the associated with the respective data point signal propagation time. Furthermore, the gray level of each pixel is determined, for example, as a function of the value of the signal strength represented by the respective data point.

Thus, the ultrasound echo signal data in this two-dimensional representation can be e.g. processing with image processing algorithms.

The graphical representation is, for example, the starting point for the further steps of the flowchart 400. In a step 405, multiple data points of the ultrasound echo signal data are grouped into one or more data point clusters. For example, grouping multiple data points of the ultrasound echo signal data into one or more data point clusters is based, at least in part, on the graphical representation determined in step 404 (eg, those described above

Pixel arrangement) and / or a graphically representable ultrasound echo signal data structure obtained as a result of determining the graphical representation in step 404. For example, grouping multiple data points of the ultrasound echo signal data into one or more data point clusters includes applying a clustering algorithm to the graphical representation (e.g., the pixel array described above) and / or one as a result

Determining the graphical representation obtained graphically

Ultrasonic echo signal data structure.

As described above, the clustering algorithm can be, for example, a hierarchical, a density-based or a partitioning clustering algorithm as well as a combination

be different clustering algorithms. An example of a density-based clustering algorithm is the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm. FIG. 5 a shows a flowchart 500 of a modified DBSCAN clustering algorithm as an example of a clustering algorithm. By selecting a suitable clustering algorithm, for example, data points are grouped into one or more data point clusters, which represent at least substantially signal components of the ultrasound echo signal attributable to reflections on a particular reflection object. This is advantageous, for example, for distinguishing and evaluating (for example, by determining characteristic data in step 406) the reflections from signal components originating at different reflection objects in the detection region in the ultrasonic echo signal represented by the ultrasound echo signal data.

9a and 9b show an exemplary representation of a graphical representation of

Ultrasonic echo signal data before and after applying the modified DBSCAN clustering algorithm shown in FIG. 5a. The graphical representation in Fig. 9a is like Fig. 8 a

Pixel arrangement 90a with pixels arranged in a grid and is based on the representation in Fig. 8. Accordingly, on the in the direction of the grid columns Ordninate 91 is the

Signal delay At with the maximum value TR applied. On the abscissa 92, for example, the transmission times (for example To, Ti, T2) of the ultrasound pulses are plotted as discrete times. Within the marking 93, pixels are represented which have a signal component which is at least essentially due to the reflection at a specific reflection object

Ultrasonic echo signal data represented represent ultrasonic echo signal. The result of applying the modified DBSCAN clustering algorithm shown in FIG. 5a to this Ultrasonic echo signal data is shown in Fig. 9b. The data points within the marker 93 have been at least partially grouped into the data point cluster 94.

In a step 406, characteristic data are determined at least partially as a function of a data point and / or a plurality of data points of a data point cluster of the ultrasound echo signal data. For example, the data point clusters are the data point clusters obtained as a result of grouping in step 405. For example, step 406 corresponds to step 303 described above in connection with flowchart 300 shown in FIG. 3. As described above, the characteristics include, for example, one or more data points (eg, multiple data points of a data point cluster, eg, the data point cluster 94) certain amplitude, frequency and / or phase information.

Amplitude information may be obtained, for example, by determining an average of the amplitude (e.g., an average of the signal strength) of the signal component of the signal represented by one or more data points (e.g., multiple data points of a data point cluster)

Ultrasonic echo signal can be obtained.

Frequency information may be obtained, for example, by determining a frequency spectrum of the signal portion of the ultrasonic echo signal represented by one or more data points of a data point cluster and / or a frequency difference between the frequency of the signal echo signal represented by one or more data points (eg, multiple data points of a data point cluster) the frequency of a previously emitted

Ultrasonic pulses are obtained. Phase information can be obtained, for example, by determining a phase change. For example, such phase change may be accomplished by comparing the phases of one or more data points (e.g., signal points 77 and 78) with one another

Ultrasonic echo signal data blocks (e.g., ultrasonic echo signal data blocks 74 and 75)

represented signal components of the ultrasonic echo signal can be determined.

Alternatively or additionally, as described above, the characteristics may include information about the reflection energy and / or signal propagation time of the data point cluster (e.g.

Data point clusters 94) represented (e.g., at least substantially due to reflections on a reflection object) the signal component of the ultrasound echo signal data

comprising ultrasonic echo signal. Information about the reflection energy can be obtained, for example, by determining the value of the energy of the signal component of the signal group represented by a data point cluster (eg, at least substantially due to reflections on a reflection object)

Ultrasonic echo signal data representative ultrasonic echo signal can be obtained.

at least substantially due to reflections on a reflection object)

Signal component of the ultrasonic echo signal represented by the ultrasound echo signal data can be obtained.

Further, as described above, the characteristics may describe, for example, characteristics of the data point clusters. These include, for example, information about the location, distribution, shape, morphology, pattern, and extent of a data point cluster.

In addition, the characteristic data may comprise further additional information, for example at least partially in dependence on otherwise processed ultrasound echo signal data (for example, with or without normalization, without or with propagation compensation, without or with

Multiple reflection compensation).

As a result of the determination in step 406, for example, the characteristics are obtained.

Subsequently, the ultrasound echo signal data, for example, in an optional in

Flowchart 400 not shown step with further ultrasonic echo signal data and / or other characteristics are fused. Alternatively or additionally, the fusing can also take place at another location, for example before step 403 or before step 406.

Ultrasonic pulses of another ultrasonic transmitter and / or ultrasonic sensor comprises returning signal components. By fusing the ultrasound echo signal data with further ultrasound echo signal data, it should be understood, for example, that the ultrasound echo signal data with the other

Ultrasonic echo signal data compared, summarized and / or enriched. Accordingly, the merging of the characteristic data with further characteristic data should be understood to mean that the characteristic data are compared, combined and / or enriched with the further characteristic data. In a step 407, one or more of the reflection objects in the detection range of the ultrasonic sensor 14 are classified at least in part based on the characteristics obtained as a result of the determination. Step 407 corresponds, for example, to step 304 described above in connection with flowchart 300 shown in FIG. 3. Further, in step 407, for example, location and / or motion information of one or more of the reflection objects may be estimated and / or determined. Location information (eg a location vector and / or a distance) of a reflection object can be estimated based on the signal propagation time of a signal component of the ultrasound echo signal at least substantially reflected by the reflection object of the ultrasound echo signal represented by the ultrasound echo signal data

determined). Movement information (eg a motion vector, a direction and / or a velocity) can be estimated (eg determined) on the basis of frequency and / or phase information of a signal component of the ultrasound echo signal at least substantially reflected by the reflection object. Subsequently, the results obtained in step 407 are provided, for example, for one or more applications. For example, the results are provided for an application for parking space monitoring and / or traffic counting and / or monitoring. For such a traffic counting and / or monitoring, for example, the respective object class (eg vehicle type) obtained as a result of the classification can be provided to the reflection objects recognized as being moved. For example, based on this, a traffic and / or vehicle density of the lanes located in the detection range of the ultrasound sensor can be determined. For parking space monitoring, it is possible, for example, to provide the respective object class (eg the respective traffic object class) obtained as a result of the classification, as well as location information of the detected reflection objects. The status (eg occupied or free) of a parking area located in the detection range of the ultrasound sensor can be determined, for example, at least partially based on the provided results and, for example, further information about the parking space (eg location information, size information, etc.) and / or previously provided results. For example, it is determined that the parking lot is occupied when, at the location of the parking lot, an object of a predetermined object class is recognized for a predetermined period of time. Further possible applications are traffic logic, prediction, decision level, visualization for users (eg customers or users). The applications may be performed both locally by, for example, the device 10 and by one or more other devices. These further devices may be, for example, a server (eg a cloud and / or backend server) and / or one or more further devices 10 and / or a control device (eg a control device for controlling a light source such as one of the ICE Gateway GmbH distributed ICE Gateway] act.

The results obtained in step 407 may alternatively or additionally be used as feedback to control preprocessing (e.g., in previous steps 401-406)

Ultrasonic echo signal data and / or the ultrasound echo signal represented by the ultrasound echo signal data can be used.

FIG. 5a shows a flow chart 500 exemplifying the steps of a modified DBSCAN algorithm. The steps illustrated in flowchart 500 are executed and / or controlled by means of the device 10, for example. For example, the steps are at least partially executed and / or controlled by the processor 11 of the device 10.

For example, the steps of the flowchart 500 are applied to ultrasound echo signal data to group the data points of the ultrasound echo signal data into data point clusters.

For this purpose, it is first checked in a step 501 whether there are still unprocessed data points. In this case, unprocessed data points are, for example, data points which are in the steps of

Flowchart 500 has not yet been considered. If there are no raw data points, flowchart 500 ends.

Otherwise, in a step 502, an arbitrary data point of the raw data points is selected as the reference data point, and then the number of data points in an epsilon neighborhood of the reference data point is determined (see step 503). Determining the number of data points in an epsilon neighborhood of the reference data point is exemplified in Fig. 5b.

In a step 504, it is checked whether the number of data points in epsilon neighborhood of the reference data point is larger than a predetermined threshold. The threshold is

for example, between 5 and 50, preferably between 10 and 40, more preferably between 15 and 30, for example, the threshold is 20. If the number of data points in epsilon neighborhood of the reference data point is not greater than the predetermined threshold, the Flowchart 500 continued with step 501. Otherwise, a new data point cluster is generated in step 505.

In a step 506 it is checked whether there are any more data points in the epsilon neighborhood of the

Reference data points that have not yet been added to the data point cluster created in step 505. If there is no data point in the epsilon neighborhood of the reference data point, flowchart 500 proceeds to step 501.

Otherwise, in step 507, data points not yet added to the data point cluster are added to the data point cluster. Subsequently, in a step 508, the epsilon neighborhood of the added data point is determined and this epsilon neighborhood is added to the epsilon neighborhood of the reference data point. In other words, the epsilon neighborhood of the reference data point becomes the epsilon neighborhood of step 507

added data point expanded. Thereafter, flowchart 500 proceeds to step 506.

As described above, Figs. 9a and 9b show an exemplary illustration of a graphical

Representation of ultrasonic echo signal data before and after applying the modified DBSCAN clustering algorithm shown in FIG. 5a.

Fig. 5b shows a flowchart 600 exemplifying the steps for determining the number of data points in epsilon neighborhood of a reference data point. The steps illustrated in flowchart 600 are executed and / or controlled by means of the device 10, for example. For example, the steps are at least partially performed by the processor 11 of FIG

Device 10 executed and / or controlled.

For example, the steps of the flowchart 600 are performed in step 503 of the flowchart 500 to determine the number of data points in the epsilon neighborhood of a reference data point.

In a step 601 it is checked whether there are still unprocessed data points. In this case, unprocessed data points are, for example, data points which have not yet been taken into account in the steps of flowchart 600. If there are no raw data points, the flowchart 600 ends. Otherwise, in step 602, any unprocessed data point is selected, and then the Euclidean distance of the data point selected in step 602 to the

Reference data point determined (see step 603). In step 604, the Euclidean distance determined in step 603 is divided by the value of the data point selected in step 602.

In a step 605, the value obtained as a result of the calculation in step 604 is compared with the value obtained as a result of multiplying a threshold value by the value of the reference data point. The threshold value is for example between 0 and 5, preferably between 0 and 1, particularly preferably between 0.1 and 0.2, for example the threshold value is 0.15. If the value obtained as a result of the calculation in step 604 is greater than or is equal to the value obtained as a result of the multiplication of the threshold value with the value of the reference data point, the flowchart 600 is continued with step 601.

Otherwise, in step 606, the data point selected in step 602 is added to the epsilon neighborhood of the reference data point and the number of data points in the epsilon neighborhood of the reference data point is incremented by one. Subsequently, the flowchart 600 is continued with step 601.

For example, certain embodiments of the invention allow for the novel use of ultrasound sensors to monitor complex environments (e.g., outdoor environments, especially on the road). By the evaluation not only one, but all in the

Covering reflections are new configurations, such as the so-called. Sidefire arrangement from the side of the road to monitor multiple lanes, possible. Even the most diverse target applications, such as traffic monitoring or parking space monitoring, are possible simultaneously with a sensor or a sensor network. In this case, the evaluation by the novel internal or graphical representation (for example in the form of a pixel arrangement), which a simultaneous analysis of the temporal and spatial relationships in the

Ultrasonic sensors evaluation allows to be facilitated.

The use of ultrasonic sensors represents the far better alternative to sensors used in the prior art for economic and economic reasons, such as radar sensors. Thus, the results can even be improved and optimized by the higher number of multiple distributed sensors at several optimal locations. The exemplary embodiments of the present invention described in this specification are also to be understood as disclosed in all combinations with each other. In particular, the description of a feature encompassed by an embodiment is - unless explicitly explained to the contrary - not be understood in this case as meaning that the feature is essential or essential for the function of the exemplary embodiment. The sequence of the method steps described in this specification in the individual flowcharts is not mandatory, alternative sequences of the method steps are conceivable. The method steps can be implemented in various ways, so an implementation in software (by program instructions), hardware, or a combination of both to implement the method steps is conceivable.

Terms used in the claims, such as "comprising," "comprising," "including," "containing," and the like, do not exclude other elements or steps. The phrase "at least partially" includes both the "partial" and "full" cases

Formulation "and / or" shall be understood to mean that both the alternative and the combination should be disclosed, ie "A and / or B" means "(A) or (B) or (A and B)" of units, persons or the like in the context of this specification means several units, persons or the like.The use of the indefinite article does not exclude a plurality.A single device may perform the functions of several in the

Performing claims mentioned units or devices. Reference signs indicated in the claims should not be regarded as limitations on the means and steps employed.

Claims

Patent claims

A method, comprising:

2. The method of claim 1, wherein each data point of the ultrasound echo signal data represents the value of the signal strength of the detected ultrasound echo signal at a detection time, respectively.

3. The method according to any one of claims 1 and 2, wherein the ultrasonic sensor is stationary.

4. The method according to any one of claims 1 to 3, the method further comprising:

Emitting and / or causing the emission of one or more ultrasonic pulses, wherein the reflections at least substantially reflections of the emitted

Include ultrasonic pulses on the reflection objects.

5. The method according to any one of claims 1 to 4, the method further comprising:

Dividing the ultrasonic echo signal data into a plurality of ultrasonic echo signal data blocks, wherein the ultrasonic echo signal data blocks have successive periods of time

Time period length of a time course of a value of the signal strength of the detected ultrasonic echo signal represent.

6. The method of claim 5, the method further comprising: Determining a graphical representation of the ultrasound echo signal data at least in part depending on the ultrasound echo signal data blocks.

The method of claim 6, wherein the graphical representation is and / or comprises a pixel array having pixels arranged in a raster.

8. A method according to claim 7, wherein the pixels of each raster column of the raster are respectively in

Dependence of the data points of a respective ultrasonic echo signal data block

Ultrasonic echo signal data blocks are determined.

9. The method of claim 6, wherein grouping a plurality of data points of the ultrasound echo signal data into one or more data point clusters is based at least in part on the graphical representation.

10. The method of claim 1, wherein grouping a plurality of data points of the ultrasound echo signal data into one or more data point clusters comprises applying a clustering algorithm to the data points of the ultrasound echo signal data.

11. The method according to any one of claims 1 to 10, wherein the characteristics include at least one or more of the following information:

Amplitude, frequency and / or phase information,

Information about a localization, a distribution, a shape, a morphology, a pattern and / or an extent of a data point cluster,

Information about a reflection energy of the signal component, represented by the data points of a data point cluster, of the ultrasonic echo signal represented by the ultrasound echo signal data,

Information about a signal propagation time of the represented by the data points of a data point cluster signal component of the represented by the ultrasonic echo signal data

Ultrasonic echo signal ..

12. The method of claim 1, wherein classifying one or more of the reflection objects comprises one or more of the following steps:

Detecting one or more of the reflection objects,

Associating one or more of the reflection objects with an object class,

Determining a probability of belonging to one or more

Reflection objects to an object class.

13. The method of claim 1, further comprising: estimating location and / or motion information of one or more of

Reflection properties.

14. The method according to any one of claims 1 to 13, wherein classifying the

Ultrasonic echo signal data is at least partially in response to a machine learning algorithm and / or a machine learning technique.

15. The method according to any one of claims 1 to 14, the method further comprising:

Fusing the ultrasound echo signal data with further ultrasound echo signal data, and / or fusing the characteristic data with further characteristic data, the further characteristic data being determined at least partially as a function of a data point and / or a data point cluster of further ultrasound echo signal data.

16. The method according to any one of claims 1 to 15, the method further comprising:

Normalizing the ultrasonic echo signal data.

A computer program comprising program instructions that cause a processor to execute and / or control the method of any one of claims 1 to 16 when the computer program is run on the processor.

18. Device comprising:

Means adapted for carrying out and / or controlling the method according to one of claims 1 to 16 or comprising respective means for carrying out and / or controlling the steps of the method according to one of claims 1 to 16.

19. The device according to claim 18, wherein the device is part of a control device for

Controlling a lighting means and / or a control device for controlling a lighting means is.

20. System comprising:

one or more devices according to any one of claims 18 and 19, and

one or more stationary ultrasonic sensors.