WO2022229051A1

WO2022229051A1 - Computer-implemented method for determining an absolute velocity of at least one moving object

Info

Publication number: WO2022229051A1
Application number: PCT/EP2022/060815
Authority: WO
Inventors: Michael Kutschera; Hanne JULING; Dorothee Selma STAUDT; Giuseppe La Spina; Mario Ramos DA SILVA JUNIOR
Original assignee: Basf Se
Priority date: 2021-04-26
Filing date: 2022-04-25
Publication date: 2022-11-03
Also published as: CN117223029A; EP4330916A1; KR20240000588A

Abstract

A computer-implemented method for determining an absolute velocity of at least one moving object (112) is disclosed. The method comprises: a. capturing a plurality of images of the moving object (112) within a time frame by using at least one camera (114); b. encoding the plurality of images captured by the camera (114) to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels, wherein the signal further comprises a plurality of motion vectors (116), wherein each of the motion vectors (116) is assigned to at least one group of pixels of the encoded image representing the moving object (112); and c. retrieving the signal from the camera (114) via at least one evaluation device (118) and evaluating the signal by combining the plurality of the motion vectors (116), thereby determining the absolute velocity of the moving object (112). Further, a computer-implemented method for determining an absolute velocity of a material flow in a chemical plant, a system (110) for determining an absolute velocity of at least one moving object (112), a use of the system (110) and a computer program and a computer-readable storage medium for performing the method for determining an absolute velocity of at least one moving object (112) are disclosed.

Description

Computer-implemented method for determining an absolute velocity of at least one moving ob ject

Technical Field

The invention relates to a computer-implemented method for determining an absolute velocity of at least one moving object, a computer-implemented method for determining an absolute veloc ity of a material flow in a chemical plant, a system for determining an absolute velocity of at least one moving object and to a computer program and a computer-readable storage medium for performing the computer-implemented method. The system and methods can be used for a contactless and a non-invasive measurement of the velocity, for example in the field of industrial and/or chemical plants. However, other fields of application are also possible, where velocity has to be determined in a contactless manner.

Background art

Velocity measurements of moving objects may comprise either using measuring probes con tacting the moving objects or using optical systems configured for contactless determining the velocity of the moving objects. As an example, the velocity of moving fluids may be determined by measuring a rotational movement of a measuring probe, such as an impeller wheel or the like. As another example, contactless determining the velocity of moving objects generally com prises using dedicated systems, such as laser or radar system. These systems may provide means for a time-resolved distance measurement of the moving objects.

On the technical field of vehicles, methods for estimating vehicle speed are known, e.g. from US 2014/063247 A1 and US 2008/205710 A1. US 2014/063247 A1 describes an automated video- based vehicle speed estimation that operates within the video stream to screen video se quences to identify and eliminate clear non-violators and/or identify and select potential violators within a multi-layer speed enforcement system, in which deeper layers provide enhanced accu racy on selected candidate vehicles. Video motion vector clusters corresponding to a vehicle are identified and tracked across multiple frames of captured video. Movement of the motion vector clusters translated from pixels per second to real speed to determine whether the vehicle was speeding. Estimated speed data is added to the video stream data is metadata, and video segments of candidate speeding vehicles are stored and/or transmitted for subsequent review. US 2008/205710 A1 describes a device, a method and a computer program product for extract ing motion information from a sequence of video frames. The device comprises a digital video camera which includes a processing unit for processing video frames grabbed by the video camera. The processing uses a 3D recursive search block matching algorithm to extract the mo tion information from the video frames. The device can be used for traffic surveillance applica tions, e.g. for determining the speed of vehicles on the streets and roads. CN 111 445444 B describes of molten iron flow rate detection, in particular to a method for de tecting molten iron flow rate based on polarization characteristics.

Despite the advantages achieved by known methods and devices, there is still a need for a sim ple and cost-effective determination of velocities in a contactless and non-invasive manner.

Problem to be solved

It is therefore desirable to provide methods and devices for determining an absolute velocity of at least one moving object which at least partially address above-mentioned technical chal lenges. Specifically, it is desirable to provide methods and devices which allow determining an absolute velocity in a contactless and non-invasive manner, preferably with low technical effort and with low requirements in terms of technical resources and cost.

Summary

This problem is addressed by a computer-implemented method for determining an absolute ve locity of at least one moving object, a computer-implemented method for determining an abso lute velocity of a material flow in a chemical plant, a system for determining an absolute velocity of at least one moving object and a computer program and a computer-readable storage me dium for performing the computer-implemented method with the features of the independent claims. Advantageous embodiments which might be realized in an isolated fashion or in any ar bitrary combinations are listed in the dependent claims as well as throughout the specification.

In a first aspect of the present invention, a computer-implemented method for determining an absolute velocity of at least one moving object is disclosed.

As used herein, the term “computer-implemented” is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a spe cial or customized meaning. The term specifically may refer, without limitation, to a process which is fully or partially implemented by using a data processing means, such as data pro cessing means comprising at least one processor, for example a computer. The term “com puter”, thus, may generally refer to a device or to a combination or network of devices having at least one data processing means such as at least one processor. The computer, additionally, may comprise one or more further components, such as at least one of a data storage device, an electronic interface or a human-machine interface. The computer and/or computer network may comprise at least one processor which is configured for performing at least one of the method steps of the method according to the present invention. Specifically, each of the method steps is performed by the computer and/or computer network. The method may be performed completely automatically, specifically without user interaction.

As used herein, the term “object" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a living object and a non-living object. The object may comprise a solid object and/or a non-solid object, such as liquid moving object and/or a gaseous object. As an example, the at least one object may comprise one or more at least one fluid, in particular comprising incorporated inhomogeneities, at least one de vice, specifically at least one of a conveyor belt, a chain belt and a transportation device, at least one rotating equipment within an industrial production environment, specifically one or more of a motor, a rotating shaft and a roll, a plurality of arbitrary objects such as cells, bacteria, animals, people, cars or other driving vehicles and the like. As used herein, the term “moving object" is a broad term and is to be given its ordinary and customary meaning to a person of or dinary skill in the art and is not to be limited to a special or customized meaning. The term spe cifically may refer, without limitation, to an object having non-zero velocity. The moving object may be subjected to a velocity determination. The moving object may specifically be in a state of motion, for example a state of motion having a non-zero linear momentum and/or a non-zero angular momentum.

As used herein, the term “absolute velocity" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a numerical indica tion of a temporal rate of change of a position of the moving object with respect to a frame of reference, in particular a coordinate system. The frame of reference may be a coordinate sys tem of at least one camera and/or of an environment of the moving object. The frame of refer ence may be considered being a fixed frame of reference, thus rendering the velocity of the moving object an absolute velocity. For distinguishing, “relative velocity” may be denoted herein measurements of velocity between two objects as determined in a single coordinate system.

The absolute velocity may comprise at least one of a scalar quantity and a vector quantity, such as a one-dimensional vector, a two-dimensional vector and/or a three-dimensional vector. The absolute velocity may specifically comprise a vector quantity describing a moving direction of the moving object, wherein an absolute value of the vector quantity may indicate a speed of the moving object. The absolute velocity may be determined for at least one of a linear motion and a rotational motion of the moving object. The absolute velocity may be at least one of a linear velocity and an angular velocity. The absolute velocity may comprise indication on a state of motion of the moving object, for example on a state of motion having non-zero momentum and/or a state of motion having zero momentum.

As used herein, the term “determining an absolute velocity" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a quanti tative and/or a qualitative determination of the absolute velocity of the moving object. The result of the determination may be the absolute velocity of the moving object, such as an indication of one or more of speed, moving direction and state of motion. As an example, the determination of the absolute velocity of the moving object may result in a vector quantity describing a state of motion of the moving object, specifically one or more of a moving direction and/or a speed of the moving object. The method may specifically comprise contactless determining the absolute velocity of the mov ing object. The term “contactless”, as used in the context of “contactless determining an abso lute velocity", is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an absence of any physical contact. Contactless de termining the absolute velocity may not require any physical contact with the moving object to be measured. Specifically, contactless determining the absolute velocity may comprise a deter mination of the absolute velocity without having a probe or any other sensing device in contact with the moving object. Thus, as will be outlined in further detail below, the method may com prise determining the absolute velocity of the moving object based on an analysis and evalua tion of optical data, specifically of image data captured by a camera. The determination of the absolute velocity may be an optical determination, i.e. without having a sensor or a probe in contact with the moving object. The method may specifically be a non-invasive method of deter mining the absolute velocity of the moving object.

The method comprises the following method steps which, specifically, may be performed in the given order. Still, a different order is also possible. It is further possible to perform two or more of the method steps fully or partially simultaneously. Further, one or more or even all of the method steps may be performed once or may be performed repeatedly, such as repeated once or several times. Further, the method may comprise additional method steps which are not listed.

The method comprises: a. capturing a plurality of images of the moving object within a time frame by using at least one camera; b. encoding the plurality of images captured by the camera to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels, wherein the signal further com prises a plurality of motion vectors, wherein each of the motion vectors is assigned to at least one group of pixels of the encoded image representing the moving object; and c. retrieving the signal from the camera via at least one evaluation device and evaluating the signal by combining the plurality of the motion vectors, thereby determining the absolute velocity of the moving object.

As used herein, the term “camera" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a device having at least one im aging element configured for recording or capturing spatially resolved one-dimensional, two-di mensional or even three-dimensional optical data or information. As an example, the camera may comprise at least one camera chip, such as at least one CCD chip and/or at least one CMOS chip configured for recording images. As used herein, without limitation, the term “im- age” is a broad term and is to be given its ordinary and customary meaning to a person of ordi nary skill in the art and is not to be limited to a special or customized meaning. The term specifi cally may refer, without limitation, to data recorded by using a camera, such as a plurality of electronic readings from the camera, such as the pixels of the camera chip. The pixels of the camera chip may generate the optical data or information for the pixels of the image. Thus, the term “pixel”, as used in the context of the image, may refer to an element of the image compris ing the optical data or information, such as one or more color or gray values, generated by a pixel of the camera chip.

The camera, besides the at least one camera chip or imaging chip, may comprise further ele ments, such as one or more optical elements, e.g. one or more lenses. As an example, the camera may be a fix-focus camera, having at least one lens which is fixedly adjusted with re spect to the camera. Alternatively, however, the camera may also comprise one or more varia ble lenses which may be adjusted, automatically or manually. Additionally or alternatively, the camera may comprise one or more data processing devices such as one or more data proces sors. Other cameras, however, are feasible.

The camera specifically may be a color camera. The camera may be configured for providing and/or generating for each pixel, color information, such as color values for three colors R, G, B. A larger number of color values is also feasible, such as four colors for each pixel, for example R, G, G, B. Color cameras are generally known to the skilled person. As an example, each pixel of the camera may have three or more different color sensors, such as color recording pixels like one pixel for red (R), one pixel for green (G) and one pixel for blue (B). For each of the pix els, such as for R, G, B, values may be recorded by the pixels, such as digital values in the range of 0 to 255, depending on the intensity of the respective color. Instead of using color tri ples such as R, G, B, as an example, quadruples may be used, such as R, G, G, B or C, M, Y,

K or the like. The color sensitivities of the pixels may be generated by color filters or by appro priate intrinsic sensitivities of the sensor elements used in the camera pixels. These techniques are generally known to the skilled person. As another example, the camera may be an RGB-D camera. The RGB-D camera may provide aside the color information (RGB) for each pixel also a depth or distance information (D) of the moving objects in relation to the camera.

The method for determining the absolute velocity of the moving object may specifically comprise using a combination of a simple technical setup having the at least one camera and an evalua tion algorithm for evaluating the signal provided by the camera. The camera may be a state-of- the-art camera. The camera may continuously provide the signal comprising the plurality of en coded images, specifically being encoded by using at least one motion compensation. With the signal, the camera may provide the plurality of motion vectors. The plurality of motion vectors may be used for determining the absolute velocity of the moving object. The evaluation of the plurality of motion vectors may require low effort in terms of technical requirements and compu ting resources and, thus, may be performed using simple evaluation algorithms. Thereby, it may be possible to precisely determine the absolute velocity using the data provided by the camera, as outlined in further detail below. As used herein, the term “capturing a plurality of images" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to one or more of imaging, image recording, image acquisition, image capturing. Specifically, capturing the plurality of images may comprise capturing a sequence of images. For example, capturing the plurality of images may comprise recording continuously a sequence of images such as a video or a movie. The plurality of images may specifically comprise a sequence of multiple im ages being captured within a time frame. As used herein, the term “time frame" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a given time interval during which the capturing of the plurality of images takes place. For example, the time frame may be from 1 to 10 seconds. The capturing of the plurality of images may be performed repeatedly. The capturing of the plurality of images may be per formed depending on a frame rate of the camera. The frame rate may be the number of images that are captured per time span. As an example, capturing the plurality of images may comprise capturing at least 8 images, preferably at least 20 images, more preferably at least 25 images, within a time frame of one second. Flowever, other frame rates are also possible.

The capturing of the images may take place, as an example, by acquiring a stream of images with the camera. As used herein, the term “stream" is a broad term and is to be given its ordi nary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to constantly captured images such as with a given frame rate. The stream may comprise a plurality of indi vidual images captured by the camera. The stream may be provided to the evaluation device by using at least one communication network such as, for example, via a local area network (LAN), via a wireless local area network (WLAN), via the internet, via a standardized protocol such as USB or FireWire or via a specialized protocol. The stream may be provided to the evaluation device directly and/or may be provided to a streaming server accessible by the evaluation de vice for retrieving the stream. The stream may be provided to the evaluation device in real-time, also denoted as “live stream”. For example, the camera may be a streaming camera and/or live streaming camera such as at least one camera available under AXIS® Q1659 or other cameras from the network camera range produced by Axis Communications AB, Lund, Sweden.

The capturing of the plurality of images may be a continuous capturing of images and/or may automatically be initiated, e.g. once the presence of the moving object within a field of view and/or within a predetermined sector of the field of view of the camera is automatically detected. These automatic image acquisition techniques are known e.g. in the field of automatic bar-code readers, such as from automatic barcode reading apps.

As outlined above, the method comprises encoding the plurality of images captured by the cam era to generate the signal. As used herein, the term “encoding" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process of compressing and/or reducing a data load of the plurality of images captured by the camera. The encoding may comprise preparing an output of the camera. The process of encod ing may comprise using a compression and/or encoding algorithm, for example a video com pression algorithm. Such compression and/or encoding algorithm are generally known to the skilled person. The encoding of the plurality of images may specifically be performed by the camera, for example by one or more data processing devices comprised by the camera. The camera may be configured, such as by hardware configuration and/or by software program ming, for encoding the plurality of images. The plurality of images as captured by the camera, i.e. with full pixel information, may be subjected the process of encoding. The encoding of the plurality of images may result in images having a reduced data load, such as having reduced pixel information. However, encoding the plurality of images may preserve the full pixel infor mation of the captured images, specifically by converting pixel information of the images in addi tional items of information having a reduced data load compared with the captured images. Consequently, the term “encoded image”, as used herein, may refer to an image which was subjected to the process of encoding.

The plurality of encoded images may be encoded by using at least one motion compensation, specifically by using at least one block motion compensation. The motion compensation may be a well-known algorithmic technique for encoding the plurality of images captured within the time frame, specifically for encoding the video. The camera may specifically be configured, such as by hardware configuration and/or by software programming, for providing the plurality of en coded images. As an example, the plurality of encoded images may comprise at least one en coding format that uses motion compensation as part of the encoding process. Specifically, the plurality of encoded images may comprise at least one encoding format selected from the group consisting of: H.120.V2; H.261 ; H.262; H.263; H.264/AVC; H.265/HEVC; AV1 ; Daala; VP6;

VP7; VP8; VP9; VC-1 ; DivX; Theora and similar implementations of the MPEG-4 part 2, part 10, part 29 or part 31. However, other encoding formats using motion compensation, specifically block motion compensation, may also be suitable for being used in the method for determining the absolute velocity of the moving object according to the present invention.

The process of encoding of the plurality of images may result in a generation of the signal. As used herein, the term “signal" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an encoding format comprising information on the plurality of captured images. The signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises the plurality of pixels. Specifically, the signal may comprise, besides the plurality of encoded images, one or more of the additional items of information added by the process of encoding.

The signal further comprises the plurality of motion vectors, wherein each of the motion vectors, specifically each of the motion vectors comprised by the plurality of motion vectors, is assigned to the at least one group of pixels of the encoded image representing the moving object. Specifi cally, the moving object may be represented in the encoded images by a plurality of groups of pixels. At least one motion vector may be assigned to each group of pixels in the encoded im age representing the moving object. The signal may specifically comprise the plurality of motion vectors assigned to the plurality of groups of pixels of the encoded image representing the mov ing object. As used herein, the term “group of pixels" is a broad term and is to be given its ordi nary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a cluster of adjacent pixels in an image of the plurality of images captured by the camera. The image may specifically be divided into a plurality of groups of pixels, wherein the plurality of groups of pixels may cover the full image. For example, each group of pixels in the image may comprise a size of 8x8, 16x16 and/or 32x32 pixels. However, it may also be possible that the size of the group of pixels varies within the image and that the group of pixels is non-quadratic. The moving ob ject may be represented in the encoded images by one or more groups of pixels. Specifically, the moving object may be represented in the encoded images by a plurality of groups of pixels. The group of pixels may also be referred to as a macroblock of the encoded image.

As used herein, the term “motion vector" is a broad term and is to be given its ordinary and cus tomary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a one-dimensional, two-dimensional or three-dimensional vector indicating a displacement of the group of pixels be tween two or more encoded images of the plurality of encoded images. Specifically, the motion vector may be a two-dimensional vector used for indicating an offset from coordinates of the group of pixels between two or more encoded images of the plurality of encoded images. For each group of pixels, the signal may comprise at least one, specifically exact one, motion vec tor. The encoded images comprised by the signal may specifically be at least one of an intra frame image, a predictive image and a bidirectional image. The intra-frame image may be an encoded image comprising full pixel information. The predictive image may be an encoded im age comprising one or more item of information on a difference to a preceding encoded image in the plurality of encoded images. Specifically, the predictive image may comprise at least one motion vector indicating a displacement of a group of pixels between the predictive image and the preceding encoded image. The bidirectional image may be an encoded image comprising one or more item of information on a difference to a preceding encoded image and/or to a sub sequent encoded image in the plurality of encoded images. Specifically, the bidirectional image may comprise at least one motion vector indicating a displacement of a group of pixels between the bidirectional image and one or more of the preceding encoded image and the subsequent encoded image.

The signal may specifically comprise the plurality of motion vectors assigned to the plurality of groups of pixels covering the encoded image. The plurality of the motion vectors may comprise at least 10 motion vectors, preferably at least 100 motion vectors, more preferably at least 1000 motion vectors. A number of the plurality of motion vectors may correspond to a number of the groups of pixels used for encoding the plurality of images. As outlined above, the method comprises retrieving the signal from the camera via the evalua tion device and evaluating the signal by combining the plurality of the motion vectors, thereby determining the absolute velocity of the moving object. As used herein, the term “evaluation de vice" is a broad term and is to be given its ordinary and customary meaning to a person of ordi nary skill in the art and is not to be limited to a special or customized meaning. The term specifi cally may refer, without limitation, to a device, such a single device or a plurality of devices, comprising at least one computational element, such as at least one processor. As used herein, the term “processor” may refer to an arbitrary logic circuitry configured for performing basic op erations of a computer or system, and/or, generally, to a device which is configured for perform ing calculations or logic operations. In particular, the processor may be configured for pro cessing basic instructions that drive the computer or system. As an example, the processor may comprise at least one arithmetic logic unit (ALU), at least one floating-point unit (FPU), such as a math coprocessor or a numeric coprocessor, a plurality of registers, specifically registers con figured for supplying operands to the ALU and storing results of operations, and a memory, such as an L1 and L2 cache memory. In particular, the processor may be a multi-core proces sor. Specifically, the processor may be or may comprise a central processing unit (CPU). Spe cifically, the processor may be or may comprise at least one Graphics Processing Unit (GPU). Additionally or alternatively, the processor may be or may comprise a microprocessor, thus spe cifically the processor’s elements may be contained in one single integrated circuitry (IC) chip. Additionally or alternatively, the processor may be or may comprise one or more application- specific integrated circuits (ASICs) and/or one or more field-programmable gate arrays (FPGAs) and/or one or more tensor processing unit (TPU) and/or one or more chip, such as a dedicated machine learning optimized chip, or the like. The processor specifically may be configured, such as by software programming, for performing one or more evaluation operations.

The evaluation device may be configured for retrieving the signal from the camera. As used herein, the term “retrieving" is a broad term and is to be given its ordinary and customary mean ing to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process of one or more of re questing, transmitting and receiving the signal from the camera directly and/or via a streaming server. Specifically, retrieving the signal may comprise a wire-bound or wireless transmission of the signal from the camera to the evaluation device. The retrieving may be performed in real time. The evaluation device may comprise at least one communication interface for exchanging data with at least one further device, for example with the camera. The evaluation device may be configured for retrieving the signal from the camera via the communication interface. As used herein, the term “communication interface" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a spe cial or customized meaning. The term specifically may refer, without limitation, to an item or ele ment forming a boundary configured for transferring information. In particular, the communica tion interface may be configured for transferring information from a computational device, e.g. a computer, such as to send or output information, e.g. onto another device. Additionally or alter natively, the communication interface may be configured for transferring information onto a computational device, e.g. onto a computer, such as to receive information. The communication interface may specifically provide means for transferring or exchanging information. In particu lar, the communication interface may provide a data transfer connection, e.g. Bluetooth, NFC, inductive coupling or the like. As an example, the communication interface may be or may com prise at least one port comprising one or more of a network or internet port, a USB-port and a disk drive. The communication interface may be at least one web interface.

The evaluation device may be configured for evaluating the signal by combining the plurality of the motion vectors. As used herein, the term “evaluating" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to any ac tions for determining the absolute velocity from the received signal. For example, the evaluating may comprise decoding the signal retrieved from the camera. The decoding the signal may spe cifically refer to a reverse process of the encoding the plurality of images as defined above. Specifically, decoding may comprise a processing of the signal to obtain a data format of the signal which can be used by the evaluating device for further processing. The evaluating may comprise extracting the plurality of motion vectors from the signal. Specifically, evaluating may comprise decoding signal retrieved from the camera to obtain the plurality of motion vectors. For example, the evaluating may comprise using the plurality of motion vectors comprised by the signal for further processing such as by using at least one mathematical operation and/or at least one mathematical algorithm.

In the method for determining the absolute velocity of the moving object, when decoding the plurality of motion vectors from the signal, it may be not necessary to decode the full image from the signal. Specifically, there is no need to reconstruct the full original image-pixel information for performing the method step c.. By evaluating only the plurality of motion vectors from the signal, the method may enable saving computing resources, such as resources of CPU and memory. Additionally, there is no necessity to separately detect the moving object within the plurality of images captured by the camera. Thus, by using the plurality of motion vectors, the method may provide a simple and resource-effective evaluation in order to determine the abso lute velocity of the moving object.

As used herein, the term “combining" is a broad term and is to be given its ordinary and custom ary meaning to a person of ordinary skill in the art and is not to be limited to a special or cus tomized meaning. The term specifically may refer, without limitation, to at least one process of joining information from the plurality of motion vectors, in particular by using at least one mathe matical operation and/or at least one mathematical algorithm.

Step c. may comprise extracting the plurality of motion vectors from the signal, such that the plurality of motion vectors may be used for further processing. Extracting the plurality of motion vectors from the signal may specifically refer to a processing of the signal thereby obtaining the plurality of motion vectors independent from the signal. After extracting the plurality of motion vectors from the signal, the motion vectors may be subjected to further processing, specifically to the evaluating performed by the evaluation device.

For example, method step c. may comprise combining all of the motion vectors from the plurality of motion vectors comprised by the signal or combining some, in particular selected motion vec tors, of the plurality of motion vectors comprised by the signal.

For example, step c. may comprise selecting motion vectors from the plurality of motion vectors. The selected motion vectors may be used for determining the absolute velocity of the moving object. The selection of motion vectors may specifically be performed in the context of evaluat ing the signal retrieved from the camera via the evaluation device. As an example, motion vec tors having a non-zero motion vector may be selected from the plurality of motion vectors. The method may comprise rejecting zero-motion vectors. Additionally or alternatively, motion vectors assigned to a group of pixels from a border area of the image, specifically of an image of the plurality of images, may be rejected. Each of the captured images may comprise a central im age region and border area. The central image region may be defined by the fact that a group of pixels of the central image region is completely surrounded by other adjacent groups of pixels. The border area may be defined by the fact that a group of pixels from the border area of the image has on at least one side no further adjacent group of pixels. Flowever, it may also be pos sible to manually or automatically define a border area and the central image region in the plu rality of images.

Step c. may further comprise filtering the plurality of motion vectors, specifically by only taking into account motion vectors having a velocity value within predetermined and/or determinable boundaries and/or by only taking into account motion vectors having a direction within predeter mined and/or determinable boundaries. The filtering may specifically be performed with the se lected motion vectors. As an example, the boundaries for filtering the plurality of motion vectors may be determined or may be set prior to performing the method, thereby specifying the prede termined boundaries. For example, the boundaries for filtering the plurality of motion vectors may be determined based on an analysis of the plurality of motion vectors, thereby obtaining the determinable boundaries. For example, the boundaries may be determined such that only motion vectors diverging in their value by not more than one, two, three or more standard devia tions from a mean value of the plurality of motion vectors are taken into account for further pro cessing. The boundaries may comprise an upper threshold and/or a lower threshold. The filter ing may specifically comprise taking into account motion vectors having a value below the upper threshold and/or above the lower threshold for further processing. The filtering of the plurality of motion vectors may be performed in the context of evaluating the plurality of the motion vectors, specifically prior to combining the plurality of motion vectors.

Evaluating the signal may comprise applying at least one mathematical operation to the plurality of motion vectors, specifically to the filtered motion vectors. Specifically, the mathematical oper ation may comprise at least one of: a unary operation; a binary operation; a logic operation. As an example, the mathematical operation may comprise using at least one mathematical function having the plurality of motion vectors as an input of the mathematical function and the absolute velocity of the moving object as an output of the mathematical function. Flowever, other opera tions are also feasible.

For example, combining the plurality of motion vectors may comprise computing a sum of the plurality of motion vectors according to:

wherein v_abs denotes the absolute velocity of the moving object, v( ) denotes the motion vector assigned to the group of pixel n and N denotes a total number of the plurality of motion vectors. This sum may be computed in case the moving object performs a linear motion. In this example, the motion vectors comprised by the signal may describe the moving direction and the speed of the linearly moving object.

For example, combining the plurality of motion vectors may comprise computing a sum of length of the plurality of motion vectors according to:

wherein v_abs denotes the absolute velocity of the moving object, \v(n) denotes the length of the motion vector assigned to the group of pixel n and N denotes a total number of the plurality of motion vectors. This sum may be computed in case the moving object performs a rotational mo tion. In this example, the motion vectors may be added by their length in order to determine the angular velocity of the rotationally moving object.

The method may comprise: d. converting the absolute velocity v_abs of the moving object by using a least one conversion coefficient C, thereby obtaining an converted absolute velocity v_conv of the moving object:

The converted absolute velocity may specifically refer to an absolute velocity having a dimen sion of [m/s] or [ rad/s ].

The conversion coefficient may comprise one or more of a time conversion coefficient C_time, specifically a time conversion coefficient C_time having a dimension of [1/s], and a distance con version coefficient C_distance, specifically a distance conversion coefficient C_distance having a di mension of [m] or [rad\. For example, the conversion coefficient C may comprise both, the time conversion coefficient C_time and the distance conversion coefficient C_distance\

The conversion coefficient may comprise a predetermined conversion coefficient. The method may comprise determining the conversion coefficient, specifically one or more of the time con version coefficient and the distance conversion coefficient, prior to step a.. As an example, the time conversion coefficient may be a camera-specific conversion coefficient. The time conver sion coefficient may be determined from the frame rate of the camera, i.e. from a number of im ages captured by the camera within the time frame. The time conversion coefficient may be de termined according to C_time = frame rate - 1, wherein this determination may account for the fact that the signal comprises one intra-frame image within the time frame having no motion vectors assigned thereto. Additionally or alternatively, the distance conversion coefficient may be determined by at least one of a distance calibration and a geometric calibration. The dis tance calibration may comprise determining a size of a known length scale in the images cap tured by the camera. The geometric calibration may take into account a fixed distance between the camera and the moving object, an aperture size of the camera and a spatial resolution of the camera for determining the distance conversion coefficient.

Step d. may comprise applying at least one correction factor to the converted absolute velocity of the moving object. The correction factor may specifically be a constant correction factor. The correction factor may correct the absolute velocity, specifically the converted absolute velocity, for systematic measurement errors. For example, in the case of non-linear deviations of the converted absolute velocity, a correction factor which is dependent from the converted absolute velocity may be used according to: vconv — C .^vabs^ ^vabs-

The method may be performed continuously, wherein the continuous performance may com prise performing the method with a determination frequency. The determination frequency may be dependent on the frame rate of the camera and may typically be a fraction of the image ac quisition frequency, also referred to as the frame rate of the camera. For example, the method may comprise determining the absolute velocity of the moving object at least 1 times per mi nute, specifically at least 1 times per second, more specifically at least 5 times per second, even more specifically at least 25 times per second.

For example, the moving object may comprise inhomogeneities, specifically one or more of gas eous inhomogeneities and/or solid inhomogeneities, incorporated by at least one flowing fluid, specifically at least one of a liquid fluid and a gaseous fluid. The flowing fluid may move the in homogeneities. The inhomogeneities incorporated by the flowing fluid may be visible to the camera. The inhomogeneities may, as an example, comprise one or more of gas bubbles, fume and solid particles.

For example, the moving object may comprise at least one flow-indicating device, specifically one or more of a winged wheel, an impeller, a fan and a flow-ball. The motion of the flow-indi cating deice may be driven by the at least one flowing fluid. It may be possible to detect motion of the flow-indicating device by using the method according to the present invention, thereby de termining the absolute velocity of the flowing fluid. For example, the moving object may comprise at least one linearly moving device, specifically at least one of a conveyor belt, a chain belt and a transportation device. The linearly moving de vice may be configured for carrying industrial produced products. The industrial produced prod ucts being carried by the linearly moving device may be visible to the camera. For example, the linearly moving device may comprise at least one of a chemical belt-reactor and a continuously operating chemical reactor configured for carrying chemical products. Alternatively or addition ally, the moving object may be conveyed by the linearly moving device, such as an object being transported by a conveyor belt. For example, the moving object may comprise a chemical prod uct carried on a chemical belt reactor, wherein the chemical products may comprise incorpo rated inhomogeneities and/or may be inhomogeneously distributed on the chemical belt reactor. The chemical belt reactor may comprise inhomogeneous spreading of the chemical product on the chemical belt reactor, such as spreading generated by spraying nozzles or dispenser.

For example, the moving object may be or may comprise at least one rotating equipment within an industrial production environment, specifically one or more of a motor, a rotating shaft and a roll. The rotational motion of the rotating equipment may be detectable by the method for deter mining the absolute velocity the least one moving object.

For example, the moving object may comprise a plurality of uniformly or randomly moving ob jects, specifically one or more of cells, bacteria, animals, people, cars or other driving vehicles. The camera may be configured for capturing a plurality of images in step a. of the uniformly or randomly moving cells or bacteria using a microscope or other lens systems for enlarging the image of the moving objects.

The method may additionally comprise determining a velocity of a moving reference frame by evaluating the plurality of motion vectors assigned to at least one group of pixels of the encoded image representing the moving reference frame. For example, an absolute velocity of a car may be determined by determining an absolute velocity of a moving underlying street. As another ex ample, an absolute velocity of drones may be determined by determining an absolute velocity of a moving landscape.

In a further aspect of the present invention, a computer-implemented method for determining an absolute velocity of a material flow in a chemical plant is disclosed. As used herein, the term “chemical plant” is a broad term and is to be given its ordinary and customary meaning to a per son of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to any technical infrastructure that is used for an industrial purpose of manufacturing, producing or processing of one or more chemical products, i.e., a manufacturing or production process or a processing performed by the chemical plant. Accordingly, the chemical plant may be one or more of a process plant, a pharmaceutical plant, a food processing plant, a fossil fuel processing facility such as an oil and/or a natural gas well, a refinery, a petro-chemical plant, a cracking plant, and the like. The chemical plant can even be any of a distillery, a treatment plant, or a recycling plant. The chemical plant can even be a com bination of any of the examples given above or their likes.

The term "chemical product" is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to any industrial product, such as chemical, pharmaceutical, nutritional, cosmetic, a biological product, a beverage, a textile, a metal, a plastic or even any of their combination. The chemical product may either consist en tirely of natural components, or it may at least partially comprise one or more synthetic compo nents. Some non-limiting examples of the chemical product are, organic or inorganic composi tions, monomers, polymers, foams, pesticides, herbicides, fertilizers, feed, nutrition products, precursors, pharmaceuticals or treatment products, or any one or more of their components or active ingredients. In some cases, the chemical product may even be a product usable by an end-user or consumer, for example, a cosmetic or pharmaceutical composition. The chemical product may even be a product that is usable for making further one or more products, for ex ample, the chemical product may be a synthetic foam usable for manufacturing soles for shoes, or a coating usable for automobile exterior. The chemical product may be in any form, for exam ple, in the form of solid, semi-solid, paste, liquid, emulsion, solution, pellets, granules, or pow der. Additionally, or alternatively, the chemical product can even be a service product, for exam ple, recovery or waste treatment such as recycling, chemical treatment such as breakdown or dissolution into one or more chemical products.

As used herein, the term “material flow” is a broad term and is to be given its ordinary and cus tomary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to flow of any feed stock, raw material, pre-fabricate, part, component, integrated objects, and/or final chemical product. The material flow may comprise at least one of a gaseous material flow, a liquid mate rial flow and a solid material flow. The gaseous material and/or the liquid material may flow through a piping system being at least partially transparent, such as having one or more sight glasses. The solid material flow may be transported on at least one of a conveyor belt, a chain belt and a transportation device.

The material flow comprises the at least one moving object. Specifically, the material flow may comprise incorporated inhomogeneities, specifically one or more of gaseous inhomogeneities and/or solid inhomogeneities, being transported by the material flow. The inhomogeneities in corporated by the material flow may be visible to a camera.

The method comprises: a. capturing a plurality of images of the moving object within a time frame by using at least one camera; b. encoding the plurality of images captured by the camera to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels, wherein the signal further com prises a plurality of motion vectors, wherein each of the motion vectors is assigned to at least one group of pixels of the encoded image representing the moving object; and c. retrieving the signal from the camera via at least one evaluation device and evaluating the signal by combining the plurality of the motion vectors, thereby determining the absolute velocity of the material flow.

The method may specifically comprise the method for determining an absolute velocity of at least one moving object according to the present invention, such as according to any one of the embodiments disclosed above and/or according to any one of the embodiments disclosed in fur ther detail below. Thus, for definition of terms related to the method for determining an absolute velocity of a material flow in a chemical plant, reference is made to the description of the method for determining an absolute velocity of at least one moving object.

In a further aspect of the present invention, a computer program is disclosed. The computer program comprises instructions which, when the program is executed by a computer or com puter network, cause the computer or computer network to perform the method for determining an absolute velocity of at least one moving object according to the present invention, such as according to any one of the embodiments disclosed above and/or according to any one of the embodiments disclosed in further detail below. Similarly, a computer-readable storage medium is disclosed, comprising instructions which, when the program is executed by a computer or computer network, cause the computer or computer network to perform the method for deter mining an absolute velocity of at least one moving object according to the present invention, such as according to any one of the embodiments disclosed above and/or according to any one of the embodiments disclosed in further detail below.

As used herein, the term “computer-readable storage medium” specifically may refer to non- transitory data storage means, such as a hardware storage medium having stored thereon com puter-executable instructions. The computer-readable storage medium specifically may be or may comprise a storage medium such as a random-access memory (RAM) and/or a read-only memory (ROM).

In a further aspect of the present invention, a system for determining an absolute velocity of at least one moving object is disclosed.

As used herein, the term “system” may refer to an arbitrary set of interacting or interdependent components parts forming a whole. Specifically, the components may interact with each other in order to fulfill at least one common function. The components of the system may be handled in dependently or may be coupled or connectable. As an example, the components of the system may be connected with each other such that the system may be handled as a single piece. Al ternatively, the components may be handled independently from each other such that the sys tem may be in a multiple-piece configuration. The system comprises at least one camera for capturing a plurality of images of the moving ob ject within a time frame and for encoding the plurality of images to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plural ity of encoded images comprises a plurality of pixels, wherein the signal further comprises a plu rality of motion vectors, wherein each of the motion vectors is assigned to at least one group of pixels of the encoded image representing the moving object. The system further comprises at least one evaluation device, specifically at least one processor, wherein the evaluation device is configured, specifically by software programming, for retrieving the signal from the camera and evaluating the signal by combining the plurality of the motion vectors, thereby determining the absolute velocity of the moving object.

The system may be configured for performing the methods according to the present invention, such as according to any one of the embodiments disclosed above and/or according to any one of the embodiments disclosed in further detail below. Thus, for definition of terms related to the system reference is made to the description of the methods.

The camera and the evaluation device may be designed as separate elements. For example, the camera may be arranged at a location of the moving object and the evaluation device may be separated from the camera. The evaluation device may be comprised by a cloud-computing system communicating with the camera. The evaluation device may also be comprised by a control system, such as a control system of the chemical or industrial plant. However, embodi ments are feasible in which the camera may comprise the evaluation device.

In a further aspect a use of the system according to the present invention is disclosed for a pur pose of use selected from the group consisting of: a velocity determination of a material flow in industrial plants; a velocity determination of linearly moving and/or rotating objects; a velocity determination of conveying systems; a velocity determination of moving vehicles on roads, lanes and/or tracks; a velocity determination of an ambient flow; a velocity determination of wind; a velocity determination of uniformly and/or randomly moving objects; a velocity determi nation of a moving reference frame.

The methods and devices according to the present invention may provide a large number of ad vantages. Specifically, the methods and devices according to the present invention may provide means for contactless and non-invasively determining the absolute velocity of the moving object while requiring low technical effort and low requirements in terms of technical resources and cost. For example, the method for determining an absolute velocity of at least one moving ob ject may use already existing hardware, such as already existing cameras, for contactless and non-invasively determining the absolute velocity of the moving object.

The method and the system for determining an absolute velocity of at least one moving object according to the present invention, specifically compared with dedicated velocity measurement using for example radar or laser systems, may be a cost-effective method and system for deter mining an absolute velocity of a moving object. Moreover, the method may be performed with a high frequency, for example at least 5 times per second, specifically at least 25 times per sec ond, depending on the frame rate of the camera.

The method and the system for determining an absolute velocity of at least one moving object according to the present invention may provide high flexibility and may be universally usable for determining an absolute velocity of an object. For example, it may be possible to apply the method for determining an absolute velocity of at least one moving object in other industrial pro duction environments, such as for determining the absolute velocity of linearly moving or rotat ing conveying machines and/or for determining an absolute velocity of driving vehicles moving on streets or tracks and/or for determining an absolute velocity of an ambient flow, for example of wind.

The methods and devices according to the present invention may be universally applicable and, thus, may provide a high economic potential and a high technical potential. The method for de termining an absolute velocity of at least one moving object may be applied in industrial produc tion environments as well as in public environments. Specifically, it may be possible to adapt ex isting camera systems to perform the method according to the present invention. Performing the method may specifically require low computing resources and, thus, may be performed directly on the camera, such as on a computing device comprised by the camera. As an example, it may be possible to use a camera of a mobile device, such as a camera of a smartphone or a tablet, and to implement the method in an application running on the mobile device.

As used herein, the terms “have”, “comprise” or “include” or any arbitrary grammatical variations thereof are used in a non-exclusive way. Thus, these terms may both refer to a situation in which, besides the feature introduced by these terms, no further features are present in the en tity described in this context and to a situation in which one or more further features are present. As an example, the expressions “A has B”, “A comprises B” and “A includes B” may both refer to a situation in which, besides B, no other element is present in A (i.e. a situation in which A solely and exclusively consists of B) and to a situation in which, besides B, one or more further elements are present in entity A, such as element C, elements C and D or even further ele ments.

Further, it shall be noted that the terms “at least one”, “one or more” or similar expressions indi cating that a feature or element may be present once or more than once typically are used only once when introducing the respective feature or element. In most cases, when referring to the respective feature or element, the expressions “at least one” or “one or more” are not repeated, nonwithstanding the fact that the respective feature or element may be present once or more than once.

Further, as used herein, the terms "preferably", "more preferably", "particularly", "more particu larly", "specifically", "more specifically" or similar terms are used in conjunction with optional fea tures, without restricting alternative possibilities. Thus, features introduced by these terms are optional features and are not intended to restrict the scope of the claims in any way. The inven tion may, as the skilled person will recognize, be performed by using alternative features. Simi larly, features introduced by "in an embodiment of the invention" or similar expressions are in tended to be optional features, without any restriction regarding alternative embodiments of the invention, without any restrictions regarding the scope of the invention and without any re striction regarding the possibility of combining the features introduced in such way with other optional or non-optional features of the invention.

Summarizing and without excluding further possible embodiments, the following embodiments may be envisaged:

Embodiment 1 : A computer-implemented method for determining an absolute velocity of at least one moving object, comprising: a. capturing a plurality of images of the moving object within a time frame by using at least one camera; b. encoding the plurality of images captured by the camera to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels, wherein the signal further com prises a plurality of motion vectors, wherein each of the motion vectors is assigned to at least one group of pixels of the encoded image representing the moving object; and c. retrieving the signal from the camera via at least one evaluation device and evaluating the signal by combining the plurality of the motion vectors, thereby determining the absolute velocity of the moving object.

Embodiment 2: The method according to the preceding embodiment, wherein the plurality of the motion vectors comprises at least 10 motion vectors, specifically at least 100 motion vec tors, more specifically at least 1000 motion vectors.

Embodiment 3: The method according to the any one of the preceding embodiments, wherein the method comprises contactless determining the absolute velocity of the moving object.

Embodiment 4: The method according to the preceding embodiment, wherein the plurality of encoded images is encoded by using at least one motion compensation, specifically by using at least one block motion compensation.

Embodiment 5: The method according to the preceding embodiment, wherein the camera is configured for providing the plurality of encoded images.

Embodiment 6: The method according to any one of the two preceding embodiments, wherein the plurality of encoded images comprises at least one encoding format that uses motion com pensation as part of the encoding process, specifically at least one encoding format selected from the group consisting of: H.120.V2; H.261 ; H.262; H.263; H.264/AVC; H.265/HEVC; AV1 ; Daala; VP6; VP7; VP8; VP9; VC-1 ; DivX; Theora and similar implementations of the MPEG-4 part 2, part 10, part 29 or part 31..

Embodiment 7: The method according to any one of the preceding embodiments, wherein evaluating the signal comprises applying at least one mathematical operation to the plurality of motion vectors.

Embodiment 8: The method according to the preceding embodiment, wherein the mathemati cal operation comprises at least one of: a unary operation; a binary operation; a logic operation.

Embodiment 9: The method according to any one of the preceding embodiments, wherein step c. comprises extracting the plurality of motion vectors from the signal.

Embodiment 10: The method according to the preceding embodiment, further comprising se lecting motion vectors from the plurality of motion vectors, wherein the selected motion vectors are used for determining the absolute velocity of the moving object.

Embodiment 11 : The method according to the preceding embodiment, wherein motion vectors having a non-zero motion vector are selected.

Embodiment 12: The method according to any one of the two preceding embodiments, wherein motion vectors assigned to a group of pixels from a border area of the image are rejected.

Embodiment 13: The method according to any one of the preceding embodiments, wherein combining the plurality of motion vectors comprises computing a sum of the plurality of motion vectors:

wherein v_abs denotes the absolute velocity of the moving object, v(n) denotes the motion vector assigned to the group of pixel n and N denotes a total number of the plurality of motion vectors.

Embodiment 14: The method according to any one of the preceding embodiments, wherein combining the plurality of motion vectors comprises computing a sum of length of the plurality of motion vectors:

wherein v_abs denotes the absolute velocity of the moving object, \v(n) \ denotes the length of the motion vector assigned to the group of pixel n and N denotes a total number of the plurality of motion vectors.

Embodiment 15: The method according to any one of the preceding embodiments, wherein step c. further comprises filtering the plurality of motion vectors, specifically by only taking into account motion vectors having a velocity value within predetermined and/or determinable boundaries and/or by only taking into account motion vectors having a direction within predeter mined and/or determinable boundaries.

Embodiment 16: The method according to any one of the preceding embodiments, further com prising: d. converting the absolute velocity v_abs of the moving object by using a least one conversion coefficient C, thereby obtaining an converted absolute velocity v_conv of the moving object: vconv — C * V_abs.

Embodiment 17: The method according to the preceding embodiment, wherein the conversion coefficient comprises one or more of a time conversion coefficient C_time and a distance conver sion Coefficient ^_distan_ce·

Embodiment 18: The method according to the preceding embodiment, wherein the conversion coefficient C comprises both, the time conversion coefficient C_time and the distance conversion Coefficient ^_distan_ce

Embodiment 19: The method according to any one of the three preceding embodiments, wherein the conversion coefficient comprises a predetermined conversion coefficient.

Embodiment 20: The method according to any one of the four preceding embodiments, wherein step d. further comprises applying at least one correction factor to the converted absolute veloc ity of the moving object.

Embodiment 21 : The method according to any one of the preceding embodiments, wherein the method is performed continuously, wherein the continuous performance comprises performing the method with a determination frequency, wherein the determination frequency is dependent on a frame rate of the camera.

Embodiment 22: The method according to any one of the preceding embodiments, wherein the moving object comprises inhomogeneities, specifically one or more of gaseous inhomogeneities and/or solid inhomogeneities, incorporated by at least one flowing fluid, specifically at least one of a liquid fluid and a gaseous fluid.

Embodiment 23: The method according to any one of the preceding embodiments, wherein the moving object comprises at least one flow-indicating device, specifically one or more of a winged wheel, an impeller, a fan and a flow-ball, wherein motion of the flow-indicating device is driven by at least one flowing fluid . Embodiment 24: The method according to any one of the preceding embodiments, wherein the moving object comprises at least one linearly moving device, specifically at least one of a con veyor belt, a chain belt and a transportation device, wherein the linearly moving device is config ured for carrying industrial produced products.

Embodiment 25: The method according to the preceding embodiment, wherein the linearly moving device comprises at least one of a chemical belt-reactor and a continuously operating chemical reactor configured for carrying chemical products.

Embodiment 26: The method according to any one of the preceding embodiments, wherein the moving object comprises at least one rotating equipment within an industrial production environ ment, specifically one or more of a motor, a rotating shaft and a roll.

Embodiment 27: The method according to any one of the preceding embodiments, wherein the moving object comprises a plurality of uniformly or randomly moving objects, specifically one or more of cells, bacteria, animals, people, cars or other driving vehicles.

Embodiment 28: The method according to any one of the preceding embodiments, further com prising determining a velocity of a moving reference frame by evaluating the plurality of motion vectors assigned to at least one group of pixels of the encoded image representing the moving reference frame.

Embodiment 29: A computer-implemented method for determining an absolute velocity of a ma terial flow in a chemical plant, wherein the material flow comprises at least one moving object, wherein the method comprises: a. capturing a plurality of images of the moving object within a time frame by using at least one camera; b. encoding the plurality of images captured by the camera to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels, wherein the signal further com prises a plurality of motion vectors, wherein each of the motion vectors is assigned to at least one group of pixels of the encoded image representing the moving object; and c. retrieving the signal from the camera via at least one evaluation device and evaluating the signal by combining the plurality of the motion vectors, thereby determining the absolute velocity of the material flow.

Embodiment 30: The method according to the preceding embodiment, further comprising the method for determining an absolute velocity of at least one moving object according to any one of the preceding embodiments referring to a method for determining an absolute velocity of at least one moving object.

Embodiment 31 : A computer program comprising instructions which, when the program is exe cuted by a computer or computer network, cause the computer or computer network to perform the method for determining an absolute velocity of at least one moving object according to any one of the preceding embodiments referring to a method for determining an absolute velocity of at least one moving object.

Embodiment 32: A computer-readable storage medium comprising instructions which, when the program is executed by a computer or computer network, cause the computer or computer net work to perform the method for determining an absolute velocity of at least one moving object according to any one of the preceding embodiments referring to a method for determining an absolute velocity of at least one moving object.

Embodiment 33: A system for determining an absolute velocity of at least one moving object, comprising at least one camera for capturing a plurality of images of the moving object within a time frame and for encoding the plurality of images to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of en coded images comprises a plurality of pixels, wherein the signal further comprises a plurality of motion vectors, wherein each of the motion vectors is assigned to at least one group of pixels of the encoded image representing the moving object, further comprising at least one evaluation device, specifically at least one processor, wherein the evaluation device is configured, specifi cally by software programming, for retrieving the signal from the camera and evaluating the sig nal by combining the plurality of the motion vectors, thereby determining the absolute velocity of the moving object.

Embodiment 34: The system according to the preceding embodiment, wherein the camera comprises the evaluation device.

Embodiment 35: A use of the system according to any one of the preceding embodiments refer ring to a system, for a purpose of use selected from the group consisting of: a velocity determi nation of a material flow in industrial plants; a velocity determination of linearly moving and/or rotating objects; a velocity determination of conveying systems; a velocity determination of mov ing vehicles on roads, lanes and/or tracks; a velocity determination of an ambient flow; a veloc ity determination of wind; a velocity determination of uniformly and/or randomly moving objects; a velocity determination of a moving reference frame.

Short description of the Figures

Further optional features and embodiments will be disclosed in more detail in the subsequent description of embodiments, preferably in conjunction with the dependent claims. Therein, the respective optional features may be realized in an isolated fashion as well as in any arbitrary feasible combination, as the skilled person will realize. The scope of the invention is not re stricted by the preferred embodiments. The embodiments are schematically depicted in the Fig ures. Therein, identical reference numbers in these Figures refer to identical or functionally comparable elements. In the Figures:

Figure 1 shows a first embodiment of a system for determining an absolute velocity of at least one moving object in a perspective view;

Figure 2 shows a flow chart of an embodiment of a computer-implemented method for deter mining an absolute velocity of at least one moving object;

Figure 3 shows a diagram of a determined absolute velocity of a moving object using the first embodiment of the system according to Figure 1;

Figure 4 shows an image captured by a second embodiment of a system for determining an absolute velocity of at least one moving object;

Figure 5 shows a diagram of a determined absolute velocity of a moving object using the sec ond embodiment of the system according to Figure 4;

Figure 6 shows a third embodiment of a system for determining an absolute velocity of at least one moving object in a perspective view;

Figure 7 shows a diagram of a determined absolute velocity of a moving object using the third embodiment of the system according to Figure 6; and

Figure 8 shows a flow chart of an embodiment of a computer-implemented method for deter mining an absolute velocity of a material flow in a chemical plant.

Detailed description of the embodiments

In Figure 1, an exemplary embodiment of a system 110 for determining an absolute velocity of at least one moving object 112 is shown in a perspective view. The system 110 comprises at least one camera 114 for capturing a plurality of images of the moving object 112 within a time frame and for encoding the plurality of images to generate at least one signal. The signal com prises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels. The signal further comprises a plurality of motion vectors 116, wherein each of the motion vectors 116 is assigned to at least one group of pixels of the en coded image representing the moving object 112.

The system 110 further comprises at least one evaluation device 118, specifically at least one processor 120. The evaluation device 118 is configured, specifically by software programming, for retrieving the signal from the camera 114 and evaluating the signal by combining the plural ity of the motion vectors 116, thereby determining the absolute velocity of the moving object 112. The system 110 may be configured for performing a computer-implemented method for deter mining an absolute velocity of the moving object 112. The method will be described with refer ence to exemplary embodiment shown in Figure 2. Thus, for the description of the method, ref erence may be made the description of Figure 2.

As shown in Figure 1 , the camera 114 and the evaluation device 118 may be designed as sepa rate elements. For example, the camera 114 may be arranged at a location 122 of the moving object 112 and the evaluation device 118 may be separated from the camera 114. For example, the evaluation device 118 may be comprised by a cloud-computing system (not shown in the Figures) communicating with the camera 114. The evaluation device 118 may also be com prised by a control system (not shown in the Figures), such as a control system of a chemical or industrial plant. Flowever, embodiments may be possible, in which the camera 114 may com prise the evaluation device 118.

The evaluation device 118 may comprise at least one communication interface 124 for ex changing data with at least one further device, for example with the camera 114. The evaluation device 118 may be configured for retrieving the signal from the camera 114 via the communica tion interface 124.

Figure 2 shows a flow chart of an exemplary embodiment of a computer-implemented method for determining an absolute velocity of the moving object 112. The method comprises the follow ing steps, which may specifically be performed in the given order. Still, a different order may also be possible. It may be possible to perform two or more of the method steps fully or partially simultaneously. It may further be possible to perform one, more than one or even all of the method steps once or repeatedly. The method may comprise additional method steps that are not listed.

The method steps of the method are the following: a. (denoted by reference number 126) capturing a plurality of images of the moving object 112 within a time frame by using the at least one camera 114; b. (denoted by reference number 128) encoding the plurality of images captured by the cam era 114 to generate at least one signal, wherein the signal comprises the plurality of en coded images, wherein each image of the plurality of encoded images comprises a plural ity of pixels, wherein the signal further comprises a plurality of motion vectors 116, wherein each of the motion vectors 116 is assigned to at least one group of pixels of the encoded image representing the moving object 112; and c. (denoted by reference number 130) retrieving the signal from the camera 114 via the at least one evaluation device 118 and evaluating the signal by combining the plurality of the motion vectors 116, thereby determining the absolute velocity of the moving object 112. As can be seen in Figure 2, method step c. may comprise one or more further method steps of processing the signal retrieved from the camera 114 via the evaluation device 118. For exam ple, step c. may comprise extracting the plurality of motion vectors 116 from the signal (denoted by reference number 132), such that the plurality of motion vectors 116 may be used for further processing. Extracting the plurality of motion vectors 116 from the signal may specifically refer to a processing of the signal thereby obtaining the plurality of motion vectors 116 independent from the signal. After extracting the plurality of motion vectors 116 from the signal, the motion vectors 116 may be subjected to further processing, specifically to the evaluating performed by the evaluation device 118.

Method step c. may comprise combining all of the motion vectors 116 from the plurality of mo tion vectors 116 comprised by the signal or combining some, in particular selected motion vec tors 116, of the plurality of motion vectors 116 comprised by the signal. For example, step c. may comprise selecting motion vectors 116 from the plurality of motion vectors 116 (denoted by reference number 134). The selected motion vectors 116 may be used for determining the ab solute velocity of the moving object 112. The selection of motion vectors 116 may specifically be performed in the context of evaluating the signal retrieved from the camera 114 via the evalua tion device 118.

Step c. may further comprise filtering the plurality of motion vectors 116 (denoted by reference number 136), specifically by only taking into account motion vectors 116 having a velocity value within predetermined and/or determinable boundaries and/or by only taking into account motion vectors 116 having a direction within predetermined and/or determinable boundaries. The filter ing may specifically be performed with the selected motion vectors 116. As an example, the boundaries for filtering the plurality of motion vectors 116 may be determined or may be set prior to performing the method, thereby specifying the predetermined boundaries. For example, the boundaries for filtering the plurality of motion vectors 116 may be determined based on an analysis of the plurality of motion vectors 116, thereby obtaining the determinable boundaries. For example, the boundaries may be determined such that only motion vectors 116 diverging in their value by not more than one, two, three or more standard deviations from a mean value of the plurality of motion vectors 116 are taken into account for further processing. The boundaries may comprise an upper threshold and/or a lower threshold. The filtering may specifically com prise taking into account motion vectors 116 having a value below the upper threshold and/or above the lower threshold for further processing. The filtering of the plurality of motion vectors 116 may be performed in the context of evaluating the plurality of the motion vectors, specifi cally prior to combining the plurality of motion vectors 116.

Evaluating the signal may comprise applying at least one mathematical operation to the plurality of motion vectors 116, specifically to the filtered motion vectors 116. For example, combining the plurality of motion vectors 116 may comprise computing a sum of the plurality of motion vec tors 116 (denoted by reference number 138) according to: wherein v_abs denotes the absolute velocity of the moving object 112, v( ) denotes the motion vector 116 assigned to the group of pixel n and N denotes a total number of the plurality of mo tion vectors 116. This sum may be computed in case the moving object 112 performs a linear motion. In this example, the motion vectors 116 comprised by the signal may describe the mov ing direction and the speed of the linearly moving object 112.

Additionally, the method may comprise: d. (denoted by reference number 140) converting the absolute velocity v_abs of the moving object 112 by using a least one conversion coefficient C, thereby obtaining an converted absolute velocity v_conv of the moving object 112: vconv — C * V_abs.

The converted absolute velocity may specifically refer to an absolute velocity having a dimen sion of [m/s] or [rad/s]. The conversion coefficient may comprise one or more of a time con version coefficient C_time and a distance conversion coefficient C_distance. For example, the con version coefficient C may comprise both, the time conversion coefficient C_time and the distance conversion coefficient C_distance\

The conversion coefficient may comprise a predetermined conversion coefficient. The method may comprise determining the conversion coefficient, specifically one or more of the time con version coefficient and the distance conversion coefficient, prior to step a.. Examples of deter mining the conversion coefficient will be given in details below.

Figure 3 shows a diagram of a determined absolute velocity using the first embodiment of the system 110 according to Figure 1. In the exemplary embodiment of the system 110 shown in Figure 1 , the moving object 112 may comprise inhomogeneities 142, specifically gaseous inho mogeneities 144, incorporated by at least one flowing fluid 146. The flowing fluid 146 may be at least one of a liquid fluid and a gaseous fluid. The flowing fluid 146 may move the inhomogenei ties 142. The inhomogeneities 142 incorporated by the flowing fluid 146 may be visible to the camera 112, specifically through a sight glass 148. The inhomogeneities 142 may, as an exam ple, comprise gas bubbles 150.

The flowing fluid 146 may flow through a tube 152 comprising the sight glass 148. The camera 114 of the system 110 may be adapted such that a field of view 154 of the camera 114 captures images of the flowing fluid 146 through the sight glass 148. Specifically, the camera 114 may be configured for acquiring a stream of images of the moving object 112. In the example of Figure 1 , the camera 114 may comprise an AXIS® F41 main unit and an AXIS® F1015 sensor unit. A resolution of the camera 114 may amount to 1080p, equivalent to 1920x1080 pixels. A frame rate of the camera 114 may be 30 fps. Thus, the camera 114 may capture 30 images within a time frame of 1 second. The field of view 154 of the camera 114 may have a horizontal field of view of 52° and a vertical field of view of 30°. A size of the field of view 154 may be 5 cm x 2.8 cm. In this example, the time conversion coefficient may be a camera-specific conver sion coefficient. The time conversion coefficient may be determined from the frame rate of the camera 114, i.e. from a number of images captured by the camera 114 within the time frame. The time conversion coefficient C_time may be 29 1/s. The distance conversion coefficient may be determined by a geometric calibration. The geometric calibration may take into account a fixed distance between the camera 114 and the moving object 112, an aperture size of the cam era 114 and a spatial resolution of the camera 114 for determining the distance conversion co efficient. In this example, the distance conversion coefficient C_distancema y be 1920 / 0,05 m = 38400 1/m.

In the diagram of Figure 3, the absolute velocity of the moving object 112 determined by per forming the method according to Figure 2 is shown on the y-axis 156 in m/min. The absolute velocity of the flowing fluid 146 determined based on a volume flow rate of the flowing fluid 146 is shown on the x-axis 158 in m/min. The volume flow rate of the flowing fluid 146 may be con trolled by a pump, such as a gear pump or the like. The results of the determination of the abso lute velocity of the moving object 112 are shown as data points 157. The dashed line shown in Figure 3 describes a relationship 160 between the determined absolute velocity of the moving object 112 and the velocity determined based on the volume flow rate of the flowing fluid 146. The linear relationship 160 between the determined absolute velocity of the moving object 112 and the velocity determined based on the volume flow rate of the flowing fluid 146 may indicate the highly accurate and precise determination of the absolute velocity of the moving object 112 by the method as exemplarily shown in Figure 2.

Flowever, a systematic deviation between the determined absolute velocity of the moving object 112 and the velocity determined based on the volume flow rate of the flowing fluid 146 may be visible. Therefore, step d. may additionally comprise applying at least one correction factor to the converted absolute velocity of the moving object 112. The correction factor may specifically be a constant correction factor. The correction factor may correct the absolute velocity, specifi cally the converted absolute velocity, for systematic measurement errors. In this example, the correction factor may comprise a constant correction factor of 1.2.

By determining the absolute velocity of the moving object 112, for example the absolute velocity of the inhomogeneities 142 comprised by the flowing fluid 146, it may be possible to determine a volume flow rate of the flowing fluid 146.

In Figure 4, an image 162 captured by a second embodiment of a system 110 for determining the absolute velocity of the moving object 112 is shown. The system 110 may be embodied sim ilar as shown in Figure 1 . Flowever, in this exemplary embodiment, the moving object 112 may comprise chemical products 164 carried by a chemical belt reactor 166. The chemical belt reac tor 166 may be a linearly moving device. The chemical products 164 may be inhomogeneously distributed on the chemical belt reactor 166. In this example, the camera 114 may comprise an AXIS® P1265 network camera. A resolution of the camera 114 may amount to 1080p, equivalent to 1920x1080 pixels. A frame rate of the camera 114 may be 30 fps. Thus, the camera 114 may capture 30 images within a time frame of 1 second. The field of view 154 of the camera 114 may have a horizontal field of view of 91° and a vertical field of view of 45°. The time conversion coefficient C_time may be 29 1/s and the distance conversion coefficient C_distancema y be 27421/m. In this example, the distance conver sion coefficient may be determined by a distance calibration. The distance calibration may com prise determining a size of a known length scale in the images 162 captured by the camera 114.

The camera 114, specifically the field of view 154 of the camera 114, may be rotated with re spect to the chemical belt reactor by an angle of approximately 65°. Thus, as can be seen in Figure 4, a border area 168 of the image 162 may appear distorted through the lens of the cam era 114. The method for determining the absolute velocity of the moving object 112 may be adapted to avoid such distortions. Specifically, as outlined above, the method may comprise se lecting motion vectors 116 from the plurality of motion vectors 116. In this example, motion vec tors 116 assigned to a group of pixels from the border area 168 of the image 162 may be re jected. Each of the captured images may comprise a central image region 170 and the border area 168. Thus, in the method, only motion vectors 116 from the central image region 170 may be selected and may be used for determining the absolute velocity of the moving object 112.

The results of the determination of the absolute velocity for this example can be seen in Figure 5. Figure 5 shows a diagram of a determined absolute velocity of the moving object 112 using the second embodiment of the system 110 as described with respect to Figure 4. The absolute velocity of the moving object 112 determined by performing the method according to Figure 2 is shown on the y-axis 156 in m/s. The absolute velocity of the chemical belt reactor 166 is shown on the x-axis 158 in m/s and is adjusted to values of 0 m/s, 0.05 m/s, 0.1 m/s and 0.2 m/s. The results of the determination of the absolute velocity of the moving object 112 are shown as data points 157.

The absolute velocity may be determined based on the selected motion vectors 116 and may be converted by using the time conversion coefficient and the distance conversion coefficient as described with respect to Figure 4. As shown in the diagram, the determination of the absolute velocity of the moving object 112, specifically of the chemical belt reactor 166, may be a precise method for contactless determining the absolute velocity useful in particular in the field of chem ical plants.

Figure 6 shows a third embodiment of the system 110 for determining the absolute velocity of the moving object 112 in a perspective view. The system 110 may be embodied similar as shown in Figure 1. Flowever, in this exemplary embodiment, the moving object 112 may com prise at least one flow-indicating device 172. As an example, the flow-indicating device 172 may comprise a winged wheel 174. The motion of the flow-indicating device 172 may be driven by the flowing fluid 146. It may be possible to detect motion of the flow-indicating device 172 by us ing the method according to Figure 2, thereby determining the absolute velocity of the flowing fluid 146.

In this example, the moving object 112 may perform a rotational motion. The motion vectors 116 may be added by the length in order to determine the angular velocity of the rotationally moving object 112. Thus, as an example, combining the plurality of motion vectors 116 may comprise computing a sum of length of the plurality of motion vectors 116 according to:

wherein v_abs denotes the absolute velocity of the moving object 112, \v(n) \ denotes the length of the motion vector 116 assigned to the group of pixel n and N denotes a total number of the plurality of motion vectors 116.

For example, the flow-indicating device 172 may comprise a laboratory flow meter “flow indica tor" with a blue winged wheel made by Burkle®. The camera 114 may comprise an AXIS® Q1659 camera with 20MP. A resolution of the camera may amount to 2160p, corresponding to 3840x2160 pixels. A frame rate of the camera 114 may be 25 fps. Thus, the camera 114 may capture 25 images within a time frame of 1 second. The camera 114 may have a Canon® EF- S55-250mm f/4-5.6 lens. The field of view 154 of the camera 114 may have a horizontal field of view of 10.4° and a vertical field of view of 7.4°.

The results of the determination of the absolute velocity of the moving object using this exem plary embodiment can be seen in Figure 7. Figure 7 shows a diagram of a determined absolute velocity of the moving object 112 using the third embodiment of the system 110 according to Figure 6. The absolute velocity of the moving object 112 determined by performing the method according to Figure 2 is shown on the y-axis 156. The volume flow rate of the flowing fluid 146 is shown on the x-axis 158 in ml/min and is adjusted to values of 0, 100, 200, 300, 400, 500 and 600 ml/min. The results of the determination of the absolute velocity of the moving object 112 are shown as data points 157.

In this example, the determined absolute velocity may be a dimensionless quantity. Flowever, it may be possible, such as by using an appropriate conversion coefficient, to convert the abso lute velocity in a rotational velocity having a dimension of [1/s] and/or in an angular velocity having a dimension of [rad/s\ . The plurality of motion vectors 116 comprised by the signal may be used for determining the absolute velocity of the moving object 116. Specifically, in this ex ample, all of the motion vectors 116 comprised by the signal may be selected for further pro cessing. The angular velocity of the moving object 112 was varied by applying different volume flow rates of the flowing fluid 146 adjusted by using a gear pump.

As can be seen in Figure 7, the flow-indicating device 172 started moving at a volume flow rate of 200 ml/min. A deviation of the determined absolute velocity from a linear relationship, shown as a dashed line 176 in Figure 7, can be observed at high volume flow rates of above 500 ml/min. The non-linear behavior of the determined absolute velocity of the moving object 112 can be seen from the solid line 178 in Figure 7. It may be possible that the observed devia tion is due to a non-linearity of the flow-indicating device 172. It may also be possible to account for this deviation by using a higher frame rate of the camera 114 and/or by selecting only motion vectors 116 from a central image region 170. However, disregarding the non-linearity of the de termined absolute velocity of the moving object 112 in this example, it may be possible to deter mine the absolute velocity of rotationally moving objects 112 by applying the method for deter mining the absolute velocity of the moving object 112 as exemplarily shown in Figure 2.

In Figure 8, a flow chart of an exemplar embodiment of a computer-implemented method for de termining an absolute velocity of a material flow in a chemical plant is shown. The material flow comprises the at least one moving object 116. Specifically, the material flow may comprise in corporated inhomogeneities, specifically one or more of gaseous inhomogeneities and/or solid inhomogeneities, being transported by the material flow. The inhomogeneities incorporated by the material flow may be visible to the cameral 14.

The method comprises the following steps, which may specifically be performed in the given or der. Still, a different order may also be possible. It may be possible to perform two or more of the method steps fully or partially simultaneously. It may further be possible to perform one, more than one or even all of the method steps once or repeatedly. The method may comprise additional method steps that are not listed.

The method comprises: a. (denoted by reference number 180) capturing a plurality of images of the moving object 112 within a time frame by using the at least one camera 114; b. (denoted by reference number 182) encoding the plurality of images captured by the cam era 114 to generate at least one signal, wherein the signal comprises the plurality of en coded images, wherein each image of the plurality of encoded images comprises a plural ity of pixels, wherein the signal further comprises a plurality of motion vectors 116, wherein each of the motion vectors 116 is assigned to at least one group of pixels of the encoded image representing the moving object 112; and c. (denoted by reference number 184) retrieving the signal from the camera 114 via the at least one evaluation device 118 and evaluating the signal by combining the plurality of the motion vectors 116, thereby determining the absolute velocity of the material flow.

The method may specifically comprise the method for determining an absolute velocity of at least one moving object according to the present invention, such as exemplarily shown in Figure 2. Thus, for possible embodiments of the method for determining an absolute velocity of a mate rial flow in a chemical plant, reference is made to the description of Figure 2. List of reference numbers system moving object camera motion vectors evaluation device processor location communication interface capturing a plurality of images encoding the plurality of images retrieving and evaluating the signal extracting the plurality of motion vectors from the signal selecting motion vectors from the plurality of motion vectors filtering the plurality of motion vectors computing a sum of the plurality of motion vectors converting the absolute velocity inhomogeneities gaseous inhomogeneities flowing fluid sight glass gas bubbles tube field of view y-axis data points x-axis relationship image chemical products chemical belt reactor border area central image region flow-indicating device winged wheel linear relationship non-linear relationship capturing a plurality of images encoding the plurality of images retrieving and evaluating the signal

Claims

1. A computer-implemented method for determining an absolute velocity of at least one mov ing object (112), comprising: a. capturing a plurality of images of the moving object (112) within a time frame by us ing at least one camera (114); b. encoding the plurality of images captured by the camera (114) to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels, wherein the signal further comprises a plurality of motion vectors (116), wherein each of the motion vectors (116) is assigned to at least one group of pixels of the encoded image representing the moving object (112); and c. retrieving the signal from the camera (114) via at least one evaluation device (118) and evaluating the signal by combining the plurality of the motion vectors (116), thereby determining the absolute velocity of the moving object (112).

2. The method according to the preceding claim, wherein the plurality of the motion vectors (116) comprises at least 10 motion vectors (116), preferably at least 100 motion vectors (116), more preferably at least 1000 motion vectors (116).

3. The method according to any one of the preceding claims, wherein the plurality of en coded images is encoded by using at least one motion compensation, wherein the camera (114) is configured for providing the plurality of encoded images.

4. The method according to any one of the preceding claims, wherein evaluating the signal comprises applying at least one mathematical operation to the plurality of motion vectors (116).

5. The method according to any one of the preceding claims, wherein step c. comprises ex tracting the plurality of motion vectors (116) from the signal, further comprising selecting motion vectors (116) from the plurality of motion vectors (116), wherein the selected mo tion vectors (116) are used for determining the absolute velocity of the moving object

(112).

6. The method according to any one of the preceding claims, wherein combining the plurality of motion vectors (116) comprises computing a sum of the plurality of motion vectors (116):

wherein v_abs denotes the absolute velocity of the moving object (112), v( ) denotes the motion vector (116) assigned to the group of pixel n and N denotes a total number of the plurality of motion vectors (116). 7. The method according to any one of the preceding claims, wherein combining the plurality of motion vectors (116) comprises computing a sum of length of the plurality of motion vectors (116):

wherein v_abs denotes the absolute velocity of the moving object (112), \v(n) \ denotes the length of the motion vector (116) assigned to the group of pixel n and N denotes a total number of the plurality of motion vectors (116).

8. The method according to any one of the preceding claims, wherein step c. further com prises filtering the plurality of motion vectors (116).

9. The method according to any one of the preceding claims, further comprising: d. converting the absolute velocity v_abs of the moving object (112) by using a least one conversion coefficient C, thereby obtaining an converted absolute velocity v_conv of the moving object (112):

10. The method according to the preceding claim, wherein the conversion coefficient com prises one or more of a time conversion coefficient C_time and a distance conversion coeffi cient C_distance, wherein the conversion coefficient C comprises both, the time conversion coefficient C_time and the distance conversion coefficient C_{distance \}

11. A computer-implemented method for determining an absolute velocity of a material flow in a chemical plant, wherein the material flow comprises at least one moving object (112), wherein the method comprises: a. capturing a plurality of images of the moving object (112) within a time frame by us ing at least one camera (114); b. encoding the plurality of images captured by the camera (114) to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels, wherein the signal further comprises a plurality of motion vectors (116), wherein each of the motion vectors (116) is assigned to at least one group of pixels of the encoded image representing the moving object (112); and c. retrieving the signal from the camera (114) via at least one evaluation device (118) and evaluating the signal by combining the plurality of the motion vectors (116), thereby determining the absolute velocity of the material flow.

12. A computer program comprising instructions which, when the program is executed by a computer or computer network, cause the computer or computer network to perform the method for determining an absolute velocity of at least one moving object (112) according to any one of the preceding claims referring to a method for determining an absolute ve locity of at least one moving object (112).

13. A computer-readable storage medium comprising instructions which, when the program is executed by a computer or computer network, cause the computer or computer network to perform the method for determining an absolute velocity of at least one moving object (112) according to any one of the preceding claims referring to a method for determining an absolute velocity of at least one moving object (112).

14. A system (110) for determining an absolute velocity of at least one moving object (112), comprising at least one camera (114) for capturing a plurality of images of the moving ob ject (112) within a time frame and for encoding the plurality of images to generate at least one signal, wherein the signal comprises the plurality of encoded images, wherein each image of the plurality of encoded images comprises a plurality of pixels, wherein the signal further comprises a plurality of motion vectors (116), wherein each of the motion vectors (116) is assigned to at least one group of pixels of the encoded image representing the moving object (112), further comprising at least one evaluation device (118), wherein the evaluation device (118) is configured, for retrieving the signal from the camera (114) and evaluating the signal by combining the plurality of the motion vectors (116), thereby deter mining the absolute velocity of the moving object (112).

15. A use of the system (110) according to any one of the preceding claims referring to a sys tem (110), for a purpose of use selected from the group consisting of: a velocity determi nation of a material flow in industrial plants; a velocity determination of linearly moving and/or rotating objects; a velocity determination of conveying systems; a velocity determi nation of moving vehicles on roads, lanes and/or tracks; a velocity determination of an ambient flow; a velocity determination of wind; a velocity determination of uniformly and/or randomly moving objects; a velocity determination of a moving reference frame.