Generating dynamic correlation signatures

Abstract

To provide an efficient classification system and method in which one of main tasks related to driving is classification.SOLUTION: Wherein a first signature generated in a first iteration comprises a first identifier indicative of at least one of a feature of a road element associated with the first signature or a generated feature of the first signature; The first identifiers are generated in association with each other, and a second signature generated in a second iteration process includes a second identifier indicating a feature of a road element associated with the second signature or a generated feature of the second signature; The second identifiers are generated in association with each other, wherein a second identifier of the second signature is generated independently of a first identifier of the first signature, and wherein the first signature and the second signature collectively represent a sensing information cluster.SELECTED DRAWING: Figure 1

Description

Background Art

[0001] Driving support systems and autonomous driving systems are known in the art. In such systems, systems executed by a computer control (at least to some extent) some or all of the driving functions of a vehicle, such as speed, telemetry, brakes, etc. The vehicle generally comprises one or more sensors so as to provide the system with current information regarding the driving environment. The driving system typically uses the current information of the driving environment to determine how to drive on the road.

[0002] One of the main tasks related to driving is classification.

[0003] There is an increasing need for efficient classification systems and methods.

Summary of the Invention

[0004] In the present application, methods, systems, and non - transient computer - readable media are shown.

Brief Description of the Drawings

[0005] From the following detailed description combined with the drawings, embodiments of the content of the present disclosure will be more comprehensively understood and grasped. [Figure 1] An embodiment of the system. [Figure 2] An embodiment of the system. [Figure 3] An embodiment of the method. [Figure 4] An embodiment of the method. [[ID=4l]] [Figure 5] An embodiment of an identifier and a signature set. [Figure 6] An embodiment of the method [[ID=U6]] [Figure 7] Examples of relationships within a signature and non - relationships within a signature.

Modes for Carrying Out the Invention

[0006] Methods, systems, and computer-readable media are provided.

[0007] The proposed solution provides accurate and robust signatures that enable the detection of road elements (road objects and / or road scenes).

[0008] The proposed solution takes into account the relationships between signature elements (e.g., identifiers), allowing one or more signatures to be associated with each road element, thereby significantly improving the accuracy of classification.

[0009] According to the embodiment, a signature is provided that is generated using at least partially a neural network. The signature includes an identifier.

[0010] According to the embodiment, the identifier indicates at least one of (a) a road element feature associated with the first signature, or (b) a generated feature of the first signature.

[0011] According to the embodiment, the identifier represents a non-zero bit of the sparse representation of the neural network feature vector.

[0012] According to the embodiment, the identifier represents an activated neuron in the neural network.

[0013] According to the embodiment, the identifier represents a non-zero bit of the sparse representation of the neural network feature vector. Different bits are associated with different properties. These properties may be selected in any manner and may be analogous to embedding properties. The identifier may also be a pointer to a non-zero bit.

[0014] According to the embodiment, the identifier represents an activated neuron in the neural network (some of the activated neurons or all of the activated neurons). The activated neuron may be the neuron that has the most impactful response to the sensing information unit supplied to the neural network.

[0015] According to the embodiment, a method is provided which is performed by a computer and used for generating dynamic correlation signatures, the method being A. Generating a first signature in a first iteration, wherein the first signature includes a first identifier that indicates at least one of (a) a road element feature associated with the first signature, or (b) a generated feature of the first signature, wherein the first identifiers are generated in association with each other, and for each iteration of the first iteration, the first identifier is determined based on the relative occurrence of the first identifier with respect to the corresponding first true positive signature set and the corresponding first false positive signature set, such that for each iteration of the first iteration, the first true positive signature set and the first false positive signature set are determined based on the previous first true positive signature set and the previous first false positive signature set, respectively. B. Generating a second signature in a second iteration, the second signature comprising (a) a feature of a road element associated with the second signature, or (b) a second identifier indicating a generated feature of the second signature, wherein the second identifiers are generated in association with each other, and each iteration of the second iteration determines the second identifiers based on the relative occurrence of the second identifiers with respect to a corresponding second true positive signature set and a corresponding second false positive signature set, such that each iteration of the second iteration determines a second true positive signature set and a second false positive signature set based on a previous second true positive signature set and a previous second false positive signature set. The second identifier of the second signature is generated independently of the first identifier of the first signature, and the first signature and the second signature represent a collectively perceived information cluster.

[0016] According to an embodiment, the method includes generating a third signature in a third iteration, the third signature including (a) a feature of a road element associated with the third signature, or (b) a third identifier indicating a generated feature of the third signature, the third identifiers being generated in association with each other, and at each iteration of the third iteration, the relative output of the third identifier in the corresponding third true positive signature set and the corresponding third false positive signature set By determining the third identifier based on the current situation, a third true positive signature set and a third false positive signature set are determined for each iteration of the third iteration process based on the previous third true positive signature set and the previous third false positive signature set, where the third identifier of the third signature is generated independently of the second identifier of the second signature, and the second signature and the third signature represent a collectively perceived information cluster.

[0017] According to the embodiment, the first signature represents the content of multiple sensing information units.

[0018] According to the embodiment, the first identifier represents a non-zero bit of the sparse representation of the neural network feature vector.

[0019] According to the embodiment, the first identifier represents an activated neuron in the neural network.

[0020] According to the embodiment, the method includes generating additional signatures until convergence is reached.

[0021] According to the embodiment, the first signature and the second signature relate to the road element represented by the acquired information.

[0022] According to an embodiment, the first false positive signature set represents a road element similar to the road element.

[0023] According to an embodiment, the method includes generating an additional signature to provide a signature cluster related to the road element and granting access rights to the cluster for an inference process.

[0024] According to an embodiment, for one of a plurality of iterations in the first iterative process, a first true positive signature set and the first false positive signature set are determined in relation to perception data.

[0025] According to an embodiment, for one of a plurality of iterations in the first iterative process, a first true positive signature set and the first false positive signature set are determined in relation to sensed information.

[0026] According to an embodiment, for one iteration of the first iterative process, a first true positive signature set and the first false positive signature set are determined in relation to a target object.

[0027] According to an embodiment, the method includes analyzing the first generated signature and the second generated signature in a real-time application.

[0028] According to an embodiment, the method includes supplying the first generated signature and the second generated signature to an offline application and analyzing the first signature and the second signature in the offline application.

[0029] According to the embodiment, a non-temporary computer-readable medium is provided for use in generating dynamic correlation signatures, the non-temporary computer-readable medium stores instructions, and when the instructions are executed by a processing circuit, the processing circuit generates a first signature in a first iterative process, the first signature including a first identifier indicating at least one of (a) a road element feature associated with the first signature, or (b) a generated feature of the first signature, the first identifiers are generated in association with each other, and in each iteration of the first iterative process, the first identifier is determined based on the relative occurrence of the first identifier with respect to the corresponding first true positive signature set and the corresponding first false positive signature set, so that in each iteration of the first iterative process, the first true positive signature set and the first false positive signature set are based on the previous first true positive signature set and the previous first false positive signature set, respectively. (ii) to determine, and (ii) to generate a second signature in a second iteration, the second signature comprising (a) a feature of a road element associated with the second signature, or (b) a generated feature of the second signature, the second identifiers being generated in association with each other, and at each iteration of the second iteration, the relative output of the second identifier to the corresponding second true positive signature set and the corresponding second false positive signature set. By determining the second identifier based on the circumstances, the second true positive signature set and the second false positive signature set are determined based on the previous second true positive signature set and the previous second false positive signature set for each iteration of the second iteration process, the second identifier of the second signature is generated independently of the first identifier of the first signature, and the first signature and the second signature represent a collectively perceived information cluster.

[0030] According to the embodiment, the computer-readable medium stores instructions, which are used to perform a third iteration process to generate a third signature, the third signature including (a) a feature of a road element associated with the third signature, or (b) a third identifier indicating a generated feature of the third signature, the third identifiers being generated in association with each other, and for each iteration of the third iteration process, a corresponding third true positive signature set and a corresponding third false positive signature set By determining the third identifier based on the relative occurrence of the third identifier to the third iteration, a third true positive signature set and a third false positive signature set are determined for each iteration of the third iteration process based on the previous third true positive signature set and the previous third false positive signature set, where the third identifier of the third signature is generated independently of the second identifier of the second signature, and the second signature and the third signature represent a collectively perceived information cluster.

[0031] According to the embodiment, the first signature represents the content of multiple sensing information units.

[0032] According to the embodiment, the first identifier represents a non-zero bit of the sparse representation of the neural network feature vector.

[0033] According to the embodiment, the first identifier represents an activated neuron in the neural network.

[0034] According to one embodiment, the computer-readable medium stores instructions for generating additional signatures until convergence is reached.

[0035] Different drawings illustrate examples of units and / or software and / or information items and / or steps and / or components. These examples are provided for the sake of simplicity of interpretation. At least one of the units and / or software and / or information items and / or steps and / or components is optional or required.

[0036] Figure 1 shows an example of a computerized system 100, which includes a communication system 130, one or more memory and / or storage units 120, and a processing system 124 including a processor 126. The computerized system may be a server, a laptop computer, a desktop computer, or any other computer, and may include or communicate with a sensing unit and / or controller.

[0037] According to one embodiment, the computerized system 100 communicates with the network 132 and one or more other remote computerized systems 134, and the remote computerized systems communicate with the network 132.

[0038] According to one embodiment, the communication system 130 is configured to enable communication between one or more memory and / or storage units 120 and / or sensing systems 110 and / or additional units and / or a network 132 (which communicates with a remote computerized system).

[0039] The memory and / or storage unit 120 is shown as storage software. Any reference to software should be applied mutatis mutandis to code and / or firmware and / or instructions and / or commands, etc.

[0040] The processor 126 includes multiple processing units 126(1) to 126(J), where J is an integer greater than 1. Any reference to one unit or item should apply mutatis mutandis to multiple units or items. For example, any reference to a processor should apply mutatis mutandis to multiple processors, and any reference to a communication system 130 should apply mutatis mutandis to multiple communication systems.

[0041] According to the embodiment, one or more memory and / or storage units 120 include one or more memory units, and each memory unit may include one or more memory banks.

[0042] According to the embodiment, one or more memory and / or storage units 120 include volatile memory and / or non-volatile memory. One or more memory and / or storage units 120 may also be random access memory (RAM) and / or read-only memory (ROM).

[0043] According to the embodiment, the non-volatile memory unit is a high-capacity storage device that can provide non-volatile storage of computer code, computer-readable instructions, data structures, program modules, and other data for the vehicle's processor or any other unit. For example, but not limited to, the high-capacity storage device may be a hard disk, a portable magnetic disk, a portable optical disk, a magnetic tape cassette or other magnetic storage device, a flash memory card, a CD-ROM, a digital versatile disk (DVD) or other optical storage device, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and the like.

[0044] Any content may be stored in any part or in any type of memory and / or storage unit.

[0045] According to the embodiment, at least one memory unit stores at least one database, for example any database known in the art, such as DB2®, Microsoft® Access, Microsoft® SQL Server, Oracle®, MySQL, PostgreSQL, etc.

[0046] Various units and / or components communicate with each other using arbitrary communication elements and / or protocols. An example of a communication system is shown in 130. Other communication elements may be provided.

[0047] The communication system 130 can communicate with the bus 136. The bus represents one or more of several possible types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any one of various bus architectures. For example, such architectures may include the Industry Standard Architecture (ISA) bus, Microchannel Architecture (MCA) bus, Expansion ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, Accelerated Graphics Port (AGP) bus and Peripheral Component Interconnect (PCI), PCI-Express bus, Personal Computer Memory Card International Association (PCMCIA), Universal Serial Bus (USB), etc. The bus and all buses specified herein may be implemented by each subsystem of the wired or wireless network connectivity and subsystems.

[0048] Network 132 is located outside the vehicle and is used for communication between the vehicle and at least one remote computing system. For example, the remote computing system may be a personal computer, laptop computer, portable computer, server, router, network computer, peer-to-peer device, or other common network node. The logical connection between the processor and any one of the remote computing systems may be made via a local area network (LAN) and a general-purpose wide area network (WAN). Such network connections may be made by a network adapter (which may belong to communication system 130), and the network adapter may operate in both wired and wireless environments. Such network environments are common in larger networks such as offices, enterprise-scale computer networks, intranets, and the internet.

[0049] It should be noted that at least a portion of the content indicated to be stored in one or more memory / storage units 120 may be stored outside the vehicle. Furthermore, it should be noted that the processor can evaluate signatures generated by multiple detectors.

[0050] According to the embodiment, the memory and / or storage unit 120 stores an operating system 194, acquired information 181, a true positive signature set 182, a false positive signature set 183, signatures 184 generated in an iterative process (using the true positive signature set 182 and the false positive signature set 183), true positive / false positive (TP / FP) generation software 185 for generating at least a portion of the true positive signature set 182 and the false positive signature set 183, signature generation software 186, identifier generation software 187, and additional software 188.

[0051] Using software, the processing system is configured to perform method 200 and / or step 300 and / or method 800.

[0052] The computerized system may be located anywhere, for example, inside a vehicle, between vehicles, or outside a vehicle.

[0053] Figure 2 shows an example of a vehicle 400, a network 432, and a remote computerization system 434.

[0054] The vehicle 400 includes a (one) sensing system 410, a communication system 430, one or more memory and / or storage units 420, and an additional unit, the additional unit including a control unit 425, an advanced driver-assistance system (ADAS) control unit 423, an autonomous driving control unit 422, and a processing system 424 including a processor 426. The network 423 communicates with the vehicle and a remote computerization system 434, such as a server or cloud computer.

[0055] The communication system 430, one or more memory and / or storage units 420, and the processing system 434 can form a computerized system. The computerized system may include one or more other systems and / or units, such as a sensing system 410.

[0056] The communication system 430 is configured to enable communication between one or more memory and / or storage units 420, and / or sensing systems 410, and / or additional units, and / or a network 432 (which communicates with a remote computerized system).

[0057] The control unit 425 can cooperate with the advanced driver-assistance system (ADAS) control unit 423 and the autonomous driving control unit 422, and / or control other vehicle components (including the vehicle computer 421) or communicate with other vehicle components.

[0058] One or more memories and / or storage units 420 are shown to store an operating system 494, software 493 (in particular software necessary for performing perception tasks and / or classification tasks and / or tasks affecting vehicle driving operations), clusters 481 generated by performing methods 200 and / or 800, classifier software 482 for classifying road elements perceived during a vehicle driving period, perception software 483 for providing and processing information about the environment around the vehicle, and perception information 484 perceived by the sensing system 410.

[0059] The sensing system 410 may include an optical device, a group of sensing elements, a readout circuit, and an image signal processor. Following the optical device is a group of sensing elements, for example, a row of sensing elements or an array of sensing elements forming the group of sensing elements. Following the group of sensing elements is a readout circuit that reads the detection signal generated by the group of sensing elements. The image signal processor is configured to perform initial processing on the detection signal, such as improving the quality of the detection information or reducing noise. The sensing system 410 is configured to output one or more sensing information units (SIUs).

[0060] The communication system 430 is configured to enable communication between one or more memory and / or storage units 420, and / or sensing systems 410, and / or any one of the additional units, and / or a network 432 (which communicates with a remote computerized system 434, which may include a computerized system 400).

[0061] The controller 425 is configured to control the operation of the sensing system 410 and / or one or more memory and / or storage units 420 and / or one or more additional units (other than the controller).

[0062] The ADAS control unit 423 is configured to control ADAS operations.

[0063] The autonomous driving control unit 422 is configured to control the autonomous driving of the autonomous vehicle.

[0064] The vehicle computer 421 is configured to control the operation of the vehicle, and in particular to control the engine, transmission, and any other vehicle systems or components.

[0065] The processing system 424 may include a processor 426 and one or more other processors and is configured to perform any method shown in the specification.

[0066] One or more memory and / or storage units 420 are configured to store firmware and / or software, one or more operating systems, data and metadata, necessary for performing any of the methods referred to in this application.

[0067] The vehicle computer 421 can communicate with the engine control module, transmission control module, powertrain control module, and the like.

[0068] The memory and / or storage unit 420 is shown as storage software. Any reference to software should be applied mutatis mutandis to code and / or firmware and / or instructions and / or commands, etc.

[0069] The processor 426 includes multiple processing units 426(1) to 426(J), where J is an integer greater than 1. Any reference to one unit or item should apply mutatis mutandis to multiple units or items. For example, any reference to a processor should apply to multiple processors, and any reference to a communication system 430 should apply mutatis mutandis to multiple communication systems.

[0070] According to the embodiment, one or more memory and / or storage units 420 include one or more memory units, and each memory unit may include one or more memory banks.

[0071] According to the embodiment, one or more memory and / or storage units 420 include volatile memory and / or non-volatile memory. One or more memory and / or storage units 420 may also be random access memory (RAM) and / or read-only memory (ROM).

[0072] According to the embodiment, the non-volatile memory unit is a high-capacity storage device that can provide non-volatile storage of computer code, computer-readable instructions, data structures, program modules and other data for the vehicle's processor or any other unit. For example, but not limited to, the high-capacity storage device may be a hard disk, a portable magnetic disk, a portable optical disk, a magnetic tape cassette or other magnetic storage device, a flash memory card, a CD-ROM, a digital versatile disk (DVD) or other optical storage device, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and the like.

[0073] Any content may be stored in any part or in any type of memory and / or storage unit.

[0074] According to the embodiment, at least one memory unit stores at least one database, for example any database known in the art, such as DB2®, Microsoft® Access, Microsoft® SQL Server, Oracle®, MySQL, PostgreSQL, etc.

[0075] Various units and / or components communicate with each other using arbitrary communication elements and / or protocols. An example of a communication system is shown in 430. Other communication elements may be provided.

[0076] Figure 2 shows various processors and / or units, and a communication system 430 communicating with the network 432.

[0077] The communication system 430 may include a bus. The bus represents one or more of several possible types of bus structures and includes a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any one of various bus architectures. For example, such architectures may include the Industry Standard Architecture (ISA) bus, Microchannel Architecture (MCA) bus, Expansion ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, Accelerated Graphics Port (AGP) bus and Peripheral Component Interconnect (PCI), PCI-Express bus, Personal Computer Memory Card International Association (PCMCIA), Universal Serial Bus (USB), and the like. The bus and all buses specified herein may be performed by each subsystem of the wired or wireless network connectivity and subsystems.

[0078] Network 432 is located outside the vehicle and is used for communication between the vehicle and at least one remote computing system. For example, the remote computing system may be a personal computer, laptop computer, portable computer, server, router, network computer, peer-to-peer device, or other common network node. The logical connection between the processor and any one of the remote computing systems may be made via a local area network (LAN) and a general-purpose wide area network (WAN). Such network connections may be made by a network adapter (which may belong to communication system 430), and the network adapter may operate in both wired and wireless environments. Such network environments are common in larger networks such as offices, enterprise-scale computer networks, intranets, and the internet.

[0079] It should be noted that at least a portion of the content indicated to be stored in one or more memory / storage units 420 may be stored outside the vehicle. Furthermore, it should be noted that the processor may evaluate signatures generated by multiple detectors.

[0080] According to the embodiment, the processor is configured as described above.

[0081] Figure 3 shows an example of a method 200 that is executed by a computer and used to generate dynamic correlation signatures.

[0082] According to the embodiment, method 200 includes an initialization step 205.

[0083] According to the embodiment, the initialization step 205 includes at least one of the following items: A. Obtain the initial first true positive signature set and the initial first false positive signature set used in the first iteration of the first iteration process. B. Obtain the initial signatures of the road elements, and based on the initial signatures, generate an initial first true positive signature set and an initial first false positive signature set.

[0084] According to the embodiment, the following step 210 follows the initialization step. Step 210 generates a first signature associated with the acquired information. The first signature includes a first identifier, which is determined by creating a first true positive signature set and a first false positive signature set in a first iteration. Each first true positive signature set and each first false positive signature set in a corresponding iteration is determined in relation to a previous first true positive signature set and a previous first false positive signature set in an iteration prior to the first iteration.

[0085] According to the embodiment, each first identifier in a corresponding iteration is determined based on the relative occurrence of the first identifier with respect to a first set of true positive signatures and a first set of false positive signatures in the corresponding iteration.

[0086] According to the embodiment, each first identifier in a corresponding iteration is determined based on a trade-off between the relative occurrence of the first identifier in the corresponding iteration relative to the first set of true positive signatures and the relative occurrence of the first identifier in the corresponding iteration relative to the first set of false positive signatures.

[0087] According to the example, the first true positive signature set in the corresponding iteration is included in the previous first true positive signature set in the previous iteration.

[0088] According to the example, another first true positive signature set in another corresponding iteration only partially overlaps with another previous first true positive signature set in another previous iteration.

[0089] According to the embodiment, step 210 is completed when the first iteration reaches convergence. An example of such convergence includes finding that (i) the first true positive signature set and the first false positive signature set in the corresponding iteration are approximately equal to (ii) the first true positive signature set and the first false positive signature set in the iterations following the corresponding iteration.

[0090] According to the embodiment, step 210 is followed by step 220. Step 220 generates a second signature including a second identifier, the second identifier being determined by creating a second true positive signature set and a second false positive signature set in a second iteration. The second signature is generated independently of the first signature by determining each second true positive signature set and each second false positive signature set in the corresponding iteration in relation to the previous second true positive signature set and the previous second false positive signature set in the iteration prior to the second iteration.

[0091] According to the embodiment, method 200 includes obtaining an initial first true positive signature set and an initial first false positive signature set associated with the first iteration in the first iteration process. The first identifier is associated with the first signature true positive signature subset and the first signature first false positive signature subset.

[0092] According to an embodiment, step 220 includes (i) generating an initial second true positive signature set related to the first iteration of the second iteration by removing from an initial first true positive signature set any signatures that match the first signature (matching may include causing at least a predetermined number of identifiers to appear in the first signature and the initial first true positive signature), and (ii) generating an initial second false positive signature set related to the first iteration of the second iteration by removing from an initial first false positive signature set any signatures that match the first signature (matching may include causing at least a predetermined number of identifiers, or at least a predetermined percentage, e.g., at least 60, 65, 70, 75, 80, 85, 90, 95 percent, to appear in the first signature and the initial first false positive signature).

[0093] If the aforementioned removal is performed each time a new signature is generated, it will render different signatures irrelevant.

[0094] Steps 210 and 220 include generating a first signature and a second signature, but according to the embodiment, method 200 is performed to generate one or more additional signatures, each signature being generated independently of the previous signatures.

[0095] According to the embodiment, the method includes generating additional signatures until convergence is reached. An example of convergence may include associating all or most of the signatures defined in the initial first true positive signature set and the initial first false positive signature set with the signatures generated in method 200. The generation of additional signatures is described in step 230 below. Step 230 generates additional signatures that include additional identifiers, which are determined by creating additional true positive signature sets and additional false positive signature sets in additional iterations. Each additional true positive signature set and each additional false positive signature set in the corresponding iteration is determined in association with the previous additional true positive signature sets and previous additional false positive signature sets in the iteration prior to the additional iteration, thereby generating the additional signatures independently of any of the previously generated signatures.

[0096] According to the example, step 230 is followed by step 240. Step 240 determines whether to generate another additional signature; if YES, proceed to step 230; otherwise, terminate signature generation.

[0097] According to the embodiment, the signatures generated by method 200 form signature clusters related to road elements.

[0098] By repeating method 200 in relation to different road elements, multiple signature clusters related to different road elements can be provided.

[0099] According to the embodiment, method 200 includes a step 250 in response to the completion of signature generation.

[0100] Step 250 may include at least one of the following items: A. Place the cluster formed by the generated signatures into the database. B. The generated signature is transmitted to one or more vehicles associated with the road elements related to the generated signature. C. Grant access rights to one or more clusters generated during the period in which Method 200 is performed. Access rights may be provided for inference processing to classify the road elements sensed by the vehicle. D. Determine whether to repeat the method or another road element, and selectively repeat the method based on the determination. E. The first generated signature and the second generated signature are analyzed in a real-time application. The analysis may include checking whether the signature is accurate, for example, whether the signature accurately represents the captured item, or whether the signature is true positive, true negative, false positive, or false negative. The real-time application may be related to vehicle driving. F. The first generated signature and the second generated signature are supplied to an offline application for analysis of the first and second signatures in the offline application. The analysis may include checking whether the signatures are accurate, for example, whether the signatures accurately represent the captured item, or whether the signatures are true positive, true negative, false positive, or false negative. The real-time application may be related to vehicle driving.

[0101] According to the embodiment, the first set of false positive signatures represents other road elements similar to the road element. In this case, similarity means that the other road elements may be mistaken for the road element of interest. Similarity can be determined manually or automatically, for example, by analyzing the false positive signatures of road elements that are different from the road element of interest but were mistakenly identified as the road element of interest.

[0102] According to the examples, any signature is based on a cropped sensing information unit. U.S. Patent Application 18 / 595,368, filed March 3, 2024, describes a method for generating a signature based on a cropped image, which is incorporated herein by reference.

[0103] Figure 4 includes step 300, which generates a signature. Step 300 is an example of any one of steps 210, 200, or 230 in method 200.

[0104] According to the embodiment, step 300 includes a series of steps 302, 304, 306, and 308.

[0105] The index n indicates the order of the signatures, as well as the order of the iterative processes applied during the signature generation process.

[0106] The index k indicates the order in which the identifiers are identified.

[0107] According to the embodiment, step 302 includes obtaining an initial nth true positive signature set and an initial nth false positive signature set. If n is equal to 1, step 302 is linked to step 205 of method 200. If n is greater than 1, step 302 includes obtaining an initial signature set that is independent of the generation of one or more previous signatures.

[0108] In an embodiment, step 304 includes determining a first identifier in the nth signature based on (i) the relative occurrence of the first identifier in the initial nth true positive signature set and (ii) the relative occurrence of the first identifier in the initial nth false positive signature set. Step 304 provides a trade-off between (i) and (ii), which may be a weighting and / or any other function, the weighting and / or any other function aimed at selecting an identifier that has a high relative occurrence in the initial nth true positive signature set and a low relative occurrence in the initial nth false positive signature set.

[0109] According to the embodiment, step 306 includes generating a (k,n)th true positive signature set and a corresponding (k,n)th false positive signature set in relation to the previous nth true positive signature set and the previous nth false positive signature set in the previous iteration.

[0110] According to an embodiment, step 308 includes determining the (k,n)th first identifier in the nth signature based on the relative occurrence of the (k,n)th identifier with respect to the (k,n)th true positive signature set and the (k,n)th false positive signature set.

[0111] Steps 306 and 308 (with different values ​​for index k) may be repeated until the signature generation is complete.

[0112] Figure 5 shows examples of true positive signature sets, false positive signature sets, and identifiers associated with the generation of the first signature.

[0113] The true positive signature set includes the initial, first, second, third, fourth, and fifth true positive signature sets: 910(0,1), 910(1,1), 910(2,1), 910(3,1), 910(4,1), and 910(5,1).

[0114] The false positive signature set includes the initial, first, second, third, fourth, and fifth false positive signature sets: 920(0,1), 920(1,1), 920(2,1), 920(3,1), 920(4,1), and 920(5,1).

[0115] The first identifier includes 930(1,1), 930(2,1), 930(3,1), 930(4,1), and 930(5,1), which are the first, second, third, fourth, and fifth identifiers of the first signature.

[0116] According to the examples, A. The first TP signature set includes all the signatures of the initial TP signature set, including the first identifier 930(1,1) of the first signature. B. The first FP signature set includes all signatures of the initial FP signature set except for the first identifier 930(1,1) of the first signature. C. The second TP signature set includes all the signatures of the first TP signature set, including the second identifier 930(2,1) of the first signature. D. The second FP signature set includes all the signatures of the first FP signature set except for the second identifier 930(2,1) of the first signature. E. The third TP signature set includes all the signatures of the second TP signature set, including the third identifier 930(3,1) of the first signature. F. The third FP signature set includes all the signatures of the second FP signature set, excluding the third identifier 930(3,1) of the first signature. G. The fourth TP signature set includes all the signatures of the initial TP signature set, which include at least half of the identifiers generated before the first signature (in this case, at least two of the first, second, and third identifiers of the first signature). H. The fourth FP signature set includes all the signatures of the initial FP signature set, excluding at least half of the identifiers generated before the first signature (in this case, at least two of the first, second, and third identifiers of the first signature). I. The fifth TP signature set includes all the signatures of the initial TP signature set, which include at least half of the previously generated identifiers of the first signature (in this case, at least two of the first, second, third, and fourth identifiers of the first signature). J. The fifth FP signature set includes all the signatures of the initial FP signature set, but does not include at least half of the identifiers generated before the first signature (in this case, at least two of the first, second, third, and fourth identifiers of the first signature).

[0117] Figure 6 shows an example of a computer-based method 800 used to generate dynamic correlation signatures.

[0118] According to the embodiment, method 800 includes an initialization step 805.

[0119] According to the embodiment, the initial step 805 includes at least one of the following items: A. Obtain the initial first true positive signature set and the initial first false positive signature set used in the first iteration of the first iteration process. B. Obtain the initial signatures of the road elements and, based on the initial signatures, generate the initial first true positive signature set and the initial first false positive signature set.

[0120] According to the embodiment, step 805 is followed by step 810, which (i) generates a first signature in a first iteration, the first signature including a first identifier that indicates at least one of (a) a road element feature associated with the first signature, or (b) a generated feature of the first signature, the first identifiers being generated in association with each other, and determining the first identifiers in each iteration of the first iteration based on the relative occurrence of the first identifiers with respect to the corresponding first true positive signature set and the corresponding first false positive signature set, so that in each iteration of the first iteration, the first true positive signature set and the first false positive signature set are determined based on the previous first true positive signature set and the previous first false positive signature set, respectively.

[0121] According to the embodiment, step 810 may be preceded by step 802.

[0122] According to the embodiment, step 810 is followed by step 820, which is the generation of a second signature in a second iteration, the second signature including a second identifier indicating (a) a road element feature associated with the second signature, or (b) a generated feature of the second signature, the second identifiers being generated in association with each other, and determining the second identifiers in each iteration of the second iteration based on the relative occurrence of the second identifiers with respect to the corresponding second true positive signature set and the corresponding second false positive signature set, thereby determining the second true positive signature set and the second false positive signature set in each iteration of the second iteration based on the previous second true positive signature set and the previous second false positive signature set.

[0123] According to the embodiment, the second identifier of the second signature is generated independently of the first identifier of the first signature.

[0124] According to the embodiment, the first signature and the second signature collectively represent a cluster of sensing information.

[0125] According to the embodiment, step 830 generates additional signatures in an additional iteration process, the additional signatures including (a) features of road elements associated with the additional signature, or (b) additional identifiers indicating the generated features of the additional signature, the additional identifiers being generated in association with each other, and determining the additional identifiers in each iteration of the additional iteration process based on the relative occurrence of the additional identifiers with respect to the corresponding additional set of true positive signatures and the corresponding additional set of false positive signatures, so that in each iteration of the additional iteration process the additional set of true positive signatures and the additional set of false positive signatures are determined based on the previous additional set of true positive signatures and the previous additional set of false positive signatures, where the additional identifiers of the additional signatures are generated independently of the second identifier of the second signature, and the second signature and the additional signatures together represent a cluster of sensing information. The additional signature may be a third signature or a signature generated after the third signature has been created.

[0126] According to the embodiment, method 800 may continue to generate additional information until convergence is reached.

[0127] According to the embodiment, step 830 is followed by step 840. Step 840 determines whether to generate another additional signature; if YES, proceed to step 830; otherwise, terminate signature generation.

[0128] According to the embodiment, once all signatures have been generated, the process moves from step 840 to step 850, which responds to the signature generation.

[0129] According to the embodiment, step 850 may include at least one of the following items: A. Place the cluster formed by the generated signatures into the database. B. The generated signature is transmitted to one or more vehicles associated with the road elements related to the generated signature. C. Grant access rights to one or more clusters generated during the period in which Method 200 is performed. Access rights may be provided for inference processing to classify the road elements sensed by the vehicle. D. Determine whether to repeat the method or another road element, and selectively repeat the method based on the determination. E. The first generated signature and the second generated signature are analyzed in a real-time application. The analysis may include checking whether the signature is accurate, for example, whether the signature accurately represents the captured item, or whether the signature is true positive, true negative, false positive, or false negative. The real-time application may be related to vehicle driving. F. The first generated signature and the second generated signature are supplied to an offline application for analysis of the first and second signatures in the offline application. The analysis may include checking whether the signatures are accurate, for example, whether the signatures accurately represent the captured item, or whether the signatures are true positive, true negative, false positive, or false negative. The real-time application may be related to vehicle driving.

[0130] According to the embodiment, the first signature represents the content of multiple sensing information units.

[0131] According to the embodiment, the first identifier represents a non-zero bit of the sparse representation of the neural network feature vector. Different bits are associated with different properties. These properties may be selected in any manner and may be analogous to embedding properties. The first identifier may also be a pointer to the non-zero bit.

[0132] According to the embodiment, the first identifier represents an activated neuron in the neural network (some activated neurons or all activated neurons). The activated neuron may be the neuron that has the most impactful response to the sensing information unit supplied to the neural network.

[0133] According to the embodiment, the first signature and the second signature relate to the road element represented by the acquired information.

[0134] According to the embodiment, the first false positive signature set represents a road element similar to the road element.

[0135] According to an embodiment, the method includes generating additional signatures to provide a signature cluster associated with the road element, and granting the inference process access to the cluster.

[0136] According to the embodiment, for one iteration of the first iteration process, the first true positive signature set and the first false positive signature set are determined in relation to the perception data.

[0137] According to the embodiment, for one iteration of the first iterative processing, the first true positive signature set and the first false positive signature set are determined in relation to the sensing information.

[0138] According to the embodiment, for one iteration of the first iteration process, the first true positive signature set and the first false positive signature set are determined in relation to the target object.

[0139] Without the intention to limit, computer-readable media may include, for example, “computer storage media” and “communication media.” “Computer storage media” includes volatile and non-volatile media, movable and immovable media, for storing information such as computer-readable instructions, data structures, program modules, or other data, implemented in any way or technique. Illustrative computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical storage devices, magnetic tape cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be used to store desired information and are computer-accessible.

[0140] According to the embodiment, the object classification system computer 701 is configured to perform any method shown in the present application.

[0141] According to the embodiment, the object classification system computer 701 communicates with one or more sensors of one or more types related to the vehicle.

[0142] According to the embodiment, the object classification system computer 701 communicates with other vehicle computers, such as control computers (e.g., engine control computer, powertrain control computer) configured to control one or more vehicle units, and / or an autonomous driving unit configured to control autonomous driving, an ADAS unit configured to control ADAS operations, a route unit configured to navigate the vehicle, and so on. Each unit includes processing circuitry and / or stores software and / or firmware and / or code and / or instructions for performing the unit's role in a non-temporary computer-readable medium.

[0143] Figure 7 shows examples of each of the following items: (a) the relationships between the first to fifth identifiers of the first signature (930(1,1) to 930(5,1)), (b) the relationships between the first to fifth identifiers of the second signature (930(1,2) to 930(5,2)), and (c) the relationships between the identifiers of the first signature and the identifiers of the second signature.

[0144] Any combination of any step of any method shown in this application is provided.

[0145] According to the embodiment, a method is provided which is executed by a computer and used to generate dynamic correlation signatures, the method comprising (i) generating a first signature associated with acquired information, the first signature comprising a first identifier, the first identifier being determined by creating a first true positive signature set and a first false positive signature set in a first iteration, where each first true positive signature set and each first false positive signature set in a corresponding iteration is determined in association with a previous first true positive signature set and a previous first false positive signature set in an iteration prior to the first iteration. (ii) to determine and generate a second signature, wherein the second identifier is determined by creating a second set of true positive signatures and a second set of false positive signatures in a second iteration, wherein each second set of true positive signatures and each second set of false positive signatures in the corresponding iteration is determined in relation to a previous set of second true positive signatures and a previous set of second false positive signatures in an iteration prior to the second iteration, thereby generating the second signature independently of the first signature.

[0146] According to the embodiment, each first identifier in a corresponding iteration is determined based on the relative occurrence of the first identifier with respect to the first true positive signature set and the first false positive signature set in the corresponding iteration.

[0147] According to the embodiment, each first identifier in a corresponding iteration is determined based on a trade-off between the relative occurrence of the first identifier with respect to the first set of true positive signatures in the corresponding iteration and the relative occurrence of the first identifier with respect to the first set of false positive signatures in the corresponding iteration.

[0148] According to the example, the first true positive signature set in the corresponding iteration is included in the previous first true positive signature set in the previous iteration.

[0149] According to the example, another first true positive signature set in another corresponding iteration only partially overlaps with another previous first true positive signature set in another previous iteration.

[0150] According to the embodiment, the method includes obtaining an initial first true positive signature set and an initial first false positive signature set to be used in the first iteration period of the first iteration process.

[0151] According to the embodiment, the method includes obtaining an initial signature of a road element and generating an initial first true positive signature set and an initial first false positive signature set based on the initial signature.

[0152] The method according to the claim includes completing a first iteration if (i) the first set of true positive signatures and the first set of false positive signatures in a corresponding iteration are substantially equal to (ii) the first set of true positive signatures and the first set of false positive signatures in an iteration following the corresponding iteration.

[0153] According to an embodiment, the method includes obtaining an initial first true positive signature set and an initial first false positive signature set associated with a first iteration of a first iteration, where the first identifier is associated with a first signature true positive signature subset and a first signature first false positive signature subset.

[0154] According to an embodiment, the method includes (i) generating an initial second true positive signature set related to the first iteration of the second iteration by removing any signatures that appear in the first signature true positive signature subset from an initial first true positive signature set, and (ii) generating an initial second false positive signature set related to the first iteration of the second iteration by removing any signatures that appear in the first signature false positive signature subset from an initial first false positive signature set.

[0155] According to the embodiment, the method includes generating additional signatures until convergence is reached.

[0156] According to the embodiment, the first signature and the second signature relate to the road element represented by the acquired information.

[0157] According to the embodiment, the first false positive signature set represents a road element similar to the road element.

[0158] According to an embodiment, the method includes generating additional signatures to provide a signature cluster associated with the road element, and granting the inference process access to the cluster.

[0159] According to the embodiment, a non-temporary computer-readable medium is provided for use in generating dynamic correlation signatures, wherein the non-temporary computer-readable medium stores instructions, and when the instructions are executed by a processing circuit, the processing circuit (i) generates a first signature associated with the acquired information, wherein the first signature includes a first identifier, the first identifier being determined by creating a first true positive signature set and a first false positive signature set in a first iteration, where each first true positive signature set and each first false positive signature set in a corresponding iteration is determined in relation to a previous first true positive signature set and a previous first false positive signature set in an iteration prior to the first iteration. (ii) To generate a second signature including a second identifier, wherein the second identifier is determined by creating a second set of true positive signatures and a second set of false positive signatures in a second iteration, wherein each second set of true positive signatures and each second set of false positive signatures in a corresponding iteration is determined in relation to a previous set of second true positive signatures and a previous set of second false positive signatures in an iteration prior to the second iteration. The second signature is generated independently of the first signature.

[0160] According to the embodiment, each first identifier in a corresponding iteration is determined based on the relative occurrence of the first identifier with respect to the first true positive signature set and the first false positive signature set in the corresponding iteration.

[0161] According to the embodiment, each first identifier in a corresponding iteration is determined based on a trade-off between the relative occurrence of the first identifier with respect to the first set of true positive signatures in the corresponding iteration and the relative occurrence of the first identifier with respect to the first set of false positive signatures in the corresponding iteration.

[0162] According to the example, the first true positive signature set in the corresponding iteration is included in the previous first true positive signature set in the previous iteration.

[0163] According to the example, another first true positive signature set in another corresponding iteration only partially overlaps with another previous first true positive signature set in another previous iteration.

[0164] According to the embodiment, a non-temporary computer-readable medium stores instructions, which are used to obtain an initial first true positive signature set and an initial first false positive signature set to be used in the first iteration period of a first iteration process.

[0165] According to the embodiment, the non-temporary computer-readable medium stores instructions, which are used to obtain initial signatures of road elements and to generate the initial first true positive signature set and the initial first false positive signature set based on the initial signatures.

[0166] According to the embodiment, a non-temporary computer-readable medium stores instructions, which are used to complete a first iteration when (i) the first true positive signature set and the first false positive signature set in a corresponding iteration are approximately equal to (ii) the first true positive signature set and the first false positive signature set in an iteration following the corresponding iteration.

[0167] According to the embodiment, a non-temporary computer-readable medium stores instructions, which are used to obtain an initial first true positive signature set and an initial first false positive signature set associated with a first iteration of a first iteration process, where a first identifier is associated with a first signature true positive signature subset and a first signature false positive signature subset.

[0168] According to the embodiment, a non-temporary computer-readable medium stores instructions, which are used to (i) generate an initial second true positive signature set associated with a first iteration of a second iteration by removing any signatures appearing in the first signature true positive signature subset from an initial first true positive signature set, and (ii) generate an initial second false positive signature set associated with a first iteration of a second iteration by removing any signatures appearing in the first signature false positive signature subset from an initial first false positive signature set.

[0169] According to one embodiment, the non-temporary computer-readable medium stores instructions for generating additional signatures until convergence is reached.

[0170] According to the embodiment, the first signature and the second signature relate to the road element represented by the acquired information.

[0171] According to the embodiment, the first false positive signature set represents a road element similar to the road element.

[0172] According to the embodiment, the non-temporary computer-readable medium is used to store instructions, which are used to generate additional signatures to provide a signature cluster associated with the road element and to grant inference processing access to the cluster.

[0173] The detailed description above includes many specific details to provide a deeper understanding of the present invention. However, as those skilled in the art will understand, the present invention can be practiced even without these specific details. In other cases, well-known methods, programs, and components are not described in detail so as not to obscure the present invention.

[0174] The conclusion of the specification specifically points out and explicitly requests protection relating to the subject matter of the present invention. However, when reading in conjunction with the drawings, the organization and operation method and their purpose, features and advantages of the present invention can be best understood by referring to the following specific embodiments.

[0175] To ensure clarity and conciseness, the elements depicted are not necessarily drawn to scale. For example, for clarity, the size of some elements may be enlarged relative to others. Furthermore, where appropriate, symbols may be repeated in the diagram to indicate corresponding or similar elements.

[0176] Since most of the embodiments of the present invention can be carried out using electronic components and circuits known to those skilled in the art, we will not describe them in more detail than deemed necessary, so as to allow you to understand and recognize the basic idea of ​​the present invention and so as not to obscure or disperse the teachings of the present invention.

[0177] Any reference to a method in this specification should apply to a device or system capable of performing the method, and / or to a non-temporary computer-readable medium storing instructions for performing the method.

[0178] Any reference in the specification to a system or device should be applied mutatis mutandis to a method that can be performed by the system, and / or to a non-temporary computer-readable medium that stores instructions that can be performed by the system.

[0179] Any reference in this specification to non-temporary computer-readable media should be applied mutatis mutandis to a device or system capable of executing instructions stored on non-temporary computer-readable media, and / or to a method for executing such instructions.

[0180] Any combination of any one of the drawings, any part of the specification, and / or any module or unit listed in any claim may be provided.

[0181] Any one of the conversion module, active learning module, or clustering module, or any other module described herein, may be executed by hardware and / or code, instructions and / or commands stored on a non-temporary computer-readable medium, and may be contained within a vehicle, outside a vehicle, within a mobile device, within a server, etc.

[0182] The vehicle may be any type of vehicle, such as a ground transport vehicle, an air transport vehicle, or a water vessel.

[0183] The specification and / or drawings may relate to images. Images are examples of media units. Any reference to images may also apply to media units. Media units may also be examples of sensing information. Any reference to media units may also apply to any type of natural signal, including, but not limited to, naturally generated signals, signals indicating human behavior, signals indicating operations correlated with stock markets, medical signals, financial sequences, ground measurement signals, geophysical, chemical, molecular, text and digital signals, time sequences, etc. Any reference to media units may also apply to sensing information. Sensing information may be of any kind and may be sensed by any type of sensor, such as a visible light camera, audio sensor, senseable infrared, radar image, ultrasound, electro-optics, radiography, laser radar (light detection and ranging), etc. Sensing may include generating samples (e.g., pixels, audio signals) that indicate signals that are transmitted or otherwise reach the sensor.

[0184] The specification and / or drawings may relate to span elements. Span elements may be implemented as software or hardware. Different span elements in a particular iteration are configured to apply different mathematical functions to the inputs they receive. Non-restrictive examples of mathematical functions include filtering, but other functions may also be applied.

[0185] The specification and / or drawings may relate to a conceptual structure. The conceptual structure may include one or more clusters. Each cluster may include signatures and associated metadata. Each citation to one or more clusters may apply to a citation to the conceptual structure.

[0186] The specification and / or drawings may relate to a processor. The processor may also be a processing circuit. The processing circuit may be implemented as a central processing unit (CPU) and / or one or more other integrated circuits, such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), custom integrated circuits, or a combination of such integrated circuits.

[0187] Any combination of any steps of any method shown in the specification and / or figures may be provided.

[0188] Any combination of any theme of any claim may be provided.

[0189] Any combination of systems, units, components, processors, and sensors shown in the specification and / or figures may be provided.

[0190] Any reference to an object can be applied to a pattern. Therefore, any reference to object detection can be applied to pattern detection.

[0191] A situation can be a single location / combination of characteristics at a given point in time. A scene is a series of events that logically occur within a causal reference framework. Any reference to a scene is applied mutatis mutandis to a situation.

[0192] The sensing information unit may be sensed by one or more sensors of one or more types. One or more sensors may belong to the same device or system, or to different devices or systems.

[0193] A perception unit may be provided, and prior to the perception unit, there may be one or more sensors and / or one or more interfaces that receive one or more perception information units from there. The perception unit may be configured to receive perception information units from the I / O interfaces and / or sensors. Following the perception unit, there may be multiple AI agents in the narrow sense, also called a set of AI agents in the narrow sense.

[0194] The sensing information unit may or may not be processed before reaching the perception unit. Optional processing, such as filtering or noise reduction, may be provided.

Claims

1. A computer-based method used to generate dynamic correlation signatures, The first iteration involves generating a first signature, the first signature comprising a first identifier that indicates at least one of (a) a road element feature associated with the first signature, or (b) a generated feature of the first signature, the first identifiers being generated in association with each other, and the generation of the first signature comprising, for each iteration of the first iteration, (i) determining the first identifier based on a trade-off between the relative occurrence of the identifier in a previous first true positive signature set and the relative occurrence of the identifier in a previous first false positive signature set, and (ii) determining the current first true positive signature set and the current first false positive signature set based on the determined first identifier, the previous first true positive signature set and the previous first false positive signature set. The generation of a second signature in a second iteration process includes: (a) a feature of a road element associated with the second signature; or (b) a second identifier indicating a generated feature of the second signature, wherein the second identifiers are generated in association with each other; and the generation of the second signature includes, for each iteration of the second iteration process, (i) determining the second identifier based on a trade-off between the relative occurrence of the identifier in a previous second true positive signature set and the relative occurrence of the identifier in a previous second false positive signature set; and (ii) determining the current second true positive signature set and the current second false positive signature set based on the determined second identifier, the previous second true positive signature set and the previous second false positive signature set. The second identifier of the second signature is generated independently of the first identifier of the first signature, and the first signature and the second signature together represent a sensing information cluster. method.

2. The third iteration further includes generating a third signature, the third signature including (a) a feature of a road element associated with the third signature, or (b) a third identifier indicating a generated feature of the third signature, the third identifiers being generated in association with each other, and the generation of the third signature includes, for each iteration of the third iteration, (i) determining the third identifier based on a trade-off between the relative occurrence of the identifier in a previous third true positive signature set and the relative occurrence of the identifier in a previous third false positive signature set, and (ii) determining the current third true positive signature set and the current third false positive signature set based on the determined third identifier, the previous third true positive signature set and the previous third false positive signature set. The third identifier of the third signature is generated independently of the second identifier of the second signature, and the second signature and the third signature together represent a sensing information cluster. The method according to claim 1.

3. The first signature represents the content of multiple sensing information units. The method according to claim 1.

4. The first identifier described above represents the non-zero bits of the sparse representation of the neural network feature vector. The method according to claim 1.

5. The first identifier described above represents an activated neuron in the neural network. The method according to claim 1.

6. The process further includes generating additional signatures until all or defined portions of the signatures in the initial first true positive signature set and the initial first false positive signature set are associated with the generated signatures. The method according to claim 1.

7. The method according to claim 1, wherein the first signature and the second signature relate to road elements represented by acquired information.

8. The first false positive signature set represents a road element similar to the road element, The method according to claim 7.

9. The method further includes generating additional signatures to provide a signature cluster associated with the road element, and granting the inference process access to the signature cluster. The method according to claim 7.

10. For one iteration of the first iteration process, the first true positive signature set and the first false positive signature set are determined in relation to the perception data. The method according to claim 1.

11. For one iteration of the first iteration process, the first true positive signature set and the first false positive signature set are determined in relation to the sensed information. The method according to claim 1.

12. For each iteration of the first iteration process, the first true positive signature set and the first false positive signature set are determined in relation to the target object. The method according to claim 1.

13. Further includes analyzing the first generated signature and the second generated signature in a real-time application. The method according to claim 1.

14. The method further includes supplying the first generated signature and the second generated signature to an offline application and analyzing the first signature and the second signature in the offline application. The method according to claim 1.

15. A non-temporary computer-readable medium used for generating dynamic correlation signatures, wherein the non-temporary computer-readable medium stores instructions, and when an instruction is executed by a processing circuit, the processing circuit carries out the method according to any one of claims 1 to 14. A non-temporary computer-readable medium.

Images