CN116504057A - Speed estimation method and device, electronic equipment and storage medium - Google Patents

Speed estimation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN116504057A
CN116504057A CN202310413031.9A CN202310413031A CN116504057A CN 116504057 A CN116504057 A CN 116504057A CN 202310413031 A CN202310413031 A CN 202310413031A CN 116504057 A CN116504057 A CN 116504057A
Authority
CN
China
Prior art keywords
data
fusion
modes
running
driving
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310413031.9A
Other languages
Chinese (zh)
Inventor
刘莹
李子烁
武治
白红霞
张岩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202310413031.9A priority Critical patent/CN116504057A/en
Publication of CN116504057A publication Critical patent/CN116504057A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/251—Fusion techniques of input or preprocessed data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Chemical & Material Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Analytical Chemistry (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

The disclosure provides a speed estimation method, a speed estimation device, electronic equipment and a storage medium, relates to the technical field of artificial intelligence, and particularly relates to data processing, deep learning and intelligent traffic technologies. The method comprises the following steps: acquiring running data of multiple modes; extracting characteristics of the running data of the multiple modes to obtain the running characteristic data of the multiple modes; carrying out interactive fusion on the running characteristic data of different modes to obtain running characteristic fusion data of multiple fusion modes; and performing speed estimation according to the driving characteristic fusion data of the multiple fusion modes to obtain a target speed estimated value. According to the method and the device, the multi-mode fusion mode is adopted, the running characteristic data of different modes are fused, the running characteristic data of different modes are interacted, and therefore more representative running characteristic fusion data are obtained, and further more accurate speed estimation and overall transit time estimation can be achieved.

Description

Speed estimation method and device, electronic equipment and storage medium
Technical Field
The disclosure relates to the technical field of artificial intelligence, in particular to data processing, deep learning and intelligent traffic technologies, and especially relates to a speed estimating method, a speed estimating device, electronic equipment and a storage medium.
Background
Currently, mobile phone applications of the map navigation category typically estimate the real-time speed of a vehicle based on the trajectory data of the vehicle. In practical situations, however, speed calculation based on track data is limited by the quality and quantity of tracks, which results in inaccurate estimation of speed and thus of overall transit time.
Disclosure of Invention
Provided are a speed estimation method, a speed estimation device, electronic equipment and a storage medium.
According to a first aspect, there is provided a speed estimation method, including: acquiring running data of multiple modes; extracting characteristics of the running data of the multiple modes to obtain the running characteristic data of the multiple modes; carrying out interactive fusion on the running characteristic data of different modes to obtain running characteristic fusion data of multiple fusion modes; and performing speed estimation according to the driving characteristic fusion data of the multiple fusion modes to obtain a target speed estimated value.
According to a second aspect, there is provided a speed estimation device comprising: the acquisition module is used for acquiring running data of multiple modes; the extraction module is used for carrying out feature extraction on the running data of the multiple modes to obtain the running feature data of the multiple modes; the fusion module is used for carrying out interactive fusion on the running characteristic data of different modes to obtain running characteristic fusion data of multiple fusion modes; and the estimating module is used for estimating the speed according to the driving characteristic fusion data of the multiple fusion modes to obtain a target speed estimated value.
According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of estimating speed according to the first aspect of the present disclosure.
According to a fourth aspect, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of estimating speed according to the first aspect of the present disclosure.
According to a fifth aspect, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of estimating velocity according to the first aspect of the present disclosure.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flow chart of a method of estimating speed according to a first embodiment of the present disclosure;
FIG. 2 is a flow chart of a method of estimating velocity according to a second embodiment of the present disclosure;
FIG. 3 is a flow chart of a method of estimating speed according to a third embodiment of the present disclosure;
FIG. 4 is an overall flow diagram of a method of estimating speed according to a fourth embodiment of the present disclosure;
FIG. 5 is a block diagram of a speed estimation apparatus according to a first embodiment of the present disclosure;
FIG. 6 is a block diagram of a speed estimation apparatus according to a second embodiment of the present disclosure;
fig. 7 is a block diagram of an electronic device for implementing the methods of embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Artificial intelligence (Artificial Intelligence, AI for short) is a technical science that studies, develops theories, methods, techniques and application systems for simulating, extending and expanding human intelligence. At present, the AI technology has the advantages of high automation degree, high accuracy and low cost, and is widely applied.
Data Processing (DP) is the collection, storage, retrieval, processing, transformation, and transmission of Data. The basic purpose of data processing is to extract and derive data that is valuable and meaningful to some particular person from a large, possibly unorganized, unintelligible, data. Data processing is a fundamental link of system engineering and automatic control. Data processing extends throughout various areas of social production and social life. The development of data processing technology and the breadth and depth of application thereof greatly influence the progress of human society development.
Deep Learning (DL) is a new research direction in the field of Machine Learning (ML), and learns the internal rules and presentation layers of sample data, and the information obtained in the Learning process is greatly helpful to the interpretation of data such as text, images and sounds. Its final goal is to have the machine have analytical learning capabilities like a person, and to recognize text, image, and sound data. For the specific research content, the method mainly comprises a neural network system based on convolution operation, namely a convolution neural network; a self-encoding neural network based on a plurality of layers of neurons; and (3) pre-training in a multi-layer self-coding neural network mode, and further optimizing a deep confidence network of the neural network weight by combining the identification information. Deep learning has achieved many results in search technology, data mining, machine learning, machine translation, natural language processing, multimedia learning, speech, recommendation and personalization techniques, and other related fields. The deep learning makes the machine imitate the activities of human beings such as audio-visual and thinking, solves a plurality of complex pattern recognition problems, and makes the related technology of artificial intelligence greatly advanced.
Intelligent transportation (Intelligent Traffic System, ITS for short), also called intelligent transportation system (Intelligent Transportation System), is a comprehensive transportation system that uses advanced scientific technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operation study, artificial intelligence, etc.) effectively and comprehensively for transportation, service control and vehicle manufacturing, and enhances the connection among vehicles, roads and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, improves environment and saves energy.
The following describes a speed estimation method, a device, an electronic apparatus, and a storage medium according to an embodiment of the present disclosure with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a speed estimation method according to a first embodiment of the present disclosure.
As shown in fig. 1, the speed estimation method in the embodiment of the disclosure may specifically include the following steps:
s101, acquiring running data of multiple modes.
Specifically, the execution body of the speed estimation method according to the embodiments of the present disclosure may be a speed estimation device provided by the embodiments of the present disclosure, where the speed estimation device may be a hardware device with data information processing capability and/or software necessary for driving the hardware device to work. Alternatively, the execution body may include a workstation, a server, a computer, a user terminal, and other devices. The user terminal comprises, but is not limited to, a mobile phone, a computer, intelligent voice interaction equipment, intelligent household appliances, vehicle-mounted terminals and the like.
In the presently disclosed embodiments, the travel data refers to data related to the travel of the vehicle. The modality, source or form of each type of information, may be referred to as a modality. Multi-modality, i.e., multi-modality, refers to information of at least two modalities, including: text, images, video, audio, etc. The method is used for acquiring running data of multiple modes. Wherein the travel data of the plurality of modalities may specifically include, but is not limited to, at least two of the following modalities: image data, radar data, travel track data, and the like.
The image data are images shot by the camera of the car camera in the running process of the car. It should be noted here that each image is returned with a time stamp returned, because at the last layer of the feature representation using the image data, the features of the image are embedded into the respective time slices.
The radar data is vehicle-mounted radar information, mainly comprises distances and relative speeds between vehicles on the same lane and adjacent lanes, and can well reflect congestion conditions, and abundant road condition information can be obtained from the radar data.
The driving track data is information returned by a user using a navigation product in the driving process and mainly characterizes the speed information of vehicles in the real world, and the speed information of the road section level can be obtained from the driving track data through the speed information of each vehicle of the same road section.
S102, carrying out feature extraction on the running data of multiple modes to obtain the running feature data of the multiple modes.
In the embodiment of the disclosure, the running data of different modes can be respectively subjected to feature extraction, so that the running feature data of different modes, such as the running feature data of an image mode, the running feature data of a radar mode and the running feature data of a running track mode, are obtained.
And S103, carrying out interactive fusion on the running characteristic data of different modes to obtain the running characteristic fusion data of multiple fusion modes.
In the embodiment of the disclosure, the running characteristic data of different modes can be fused in pairs to obtain the running characteristic fusion data of different fusion modes, such as the running characteristic fusion data of an image radar fusion mode, the running characteristic fusion data of an image running track fusion mode and the running characteristic fusion data of a radar running track fusion mode. The method adopts a multi-mode fusion mode to fuse the running characteristic data, namely the characteristic representation of the image, the radar and the running track, and the characteristic representation of the image, the radar signal and the running track data are interacted, so that the more representative characteristic representation, namely the running characteristic fusion data is obtained.
S104, speed estimation is carried out according to the driving characteristic fusion data of the multiple fusion modes, and a target speed estimated value is obtained.
In the embodiment of the present disclosure, speed estimation is performed based on the driving feature fusion data of the multiple fusion modes obtained in step S103, so as to obtain a final speed estimated value, that is, a target speed estimated value.
In summary, according to the speed estimation method in the embodiment of the present disclosure, feature extraction is performed on running data of multiple modes to obtain running feature data of multiple modes, running feature data of different modes are interactively fused to obtain running feature fusion data of multiple fusion modes, and speed estimation is performed according to the running feature fusion data of multiple fusion modes to obtain a target speed estimated value. The disclosed embodiment adopts a multi-mode fusion mode, fuses the running characteristic data of different modes, and interacts the running characteristic data of different modes, so that more representative running characteristic fusion data is obtained, more accurate speed estimation and overall transit time estimation can be realized, meanwhile, the timeliness problem of congestion aggregation and dissipation is reduced, the rationality of a user on road selection is ensured, the travel of the user is scientifically guided, the travel time of the user is saved, and the perception experience of the overall transit time estimation of the user is continuously improved.
Fig. 2 is a flowchart illustrating a speed estimation method according to a second embodiment of the present disclosure.
As shown in fig. 2, on the basis of the embodiment shown in fig. 1, the speed estimation method according to the embodiment of the disclosure may specifically include the following steps:
s201, acquiring running data of multiple modes.
In the embodiment of the present disclosure, step S201 is the same as step S101 in the above embodiment, and will not be described here again.
Step S102 "in the above embodiment performs feature extraction on the running data of multiple modes to obtain running feature data of multiple modes", and may specifically include the following step S202.
S202, carrying out feature extraction on the driving data by adopting a feature extraction model to obtain the driving feature data.
In the embodiment of the disclosure, the pre-training large model can be used as a feature extraction model to perform feature extraction on the driving data, so as to obtain the driving feature data. The pre-training large model is a model obtained by training massive data in advance, for example, the model can be pre-trained by accumulating 5 years of driving data of three sources of images, radars and driving tracks, and general traffic law characteristics and traffic trend characteristics can be learned by learning multi-source massive data.
For image data, an image feature extraction model, such as a ResNet 152 model, can be used to perform feature extraction on the image data to obtain running feature data of an image mode. The ResNet 152 model is a FAST-RNN model, and recognizes the distance between the current vehicle and the front 3 vehicles on the same lane based on the image data, and the distance is used as the characteristic representation of the image data, namely, the driving characteristic data of the image mode.
For the radar data and the running track data, a time sequence model such as a transducer model can be adopted to perform feature extraction on the radar data and the running track data, so as to obtain running feature data of a radar mode and running feature data of a running track mode.
Step S103 "the running feature data of different modes are interactively fused to obtain running feature fusion data of multiple fusion modes" in the above embodiment may specifically include the following step S203.
And S203, adopting a twin network model to interactively fuse the running characteristic data of different modes to obtain the running characteristic fusion data of multiple fusion modes.
In the embodiment of the disclosure, a twin network model is a twin tower network model, driving characteristic data of two different modes are respectively input into the twin network model, and the twin network model carries out interactive fusion on the driving characteristic data of the two modes to obtain driving characteristic fusion data of a fusion mode. For example: when the twin network model encodes the driving characteristic data of the image mode, the driving characteristic data of the radar mode or the driving characteristic data of the driving track mode can be fused.
Step S104 "in the above embodiment performs speed estimation according to the driving feature fusion data of multiple fusion modes to obtain the target speed predicted value" may specifically include the following step S204.
S204, inputting the driving characteristic fusion data of the multiple fusion modes into the same speed estimation model to perform speed estimation, and obtaining a target speed estimated value.
In the embodiment of the present disclosure, the driving feature fusion data of multiple fusion modes obtained in step S203 may be input into the same speed estimation model, and the speed estimation model performs speed estimation based on the input data, and outputs a target speed estimated value. The velocity estimation model may specifically be a time series model such as a transducer model. For running characteristic data of different sources, a multi-mode fusion mode is adopted, visual road state depiction of image data, more accurate vehicle distance and relative speed depiction of radar data and speed depiction of running track data are combined, and through combination of modes, a speed estimation model can learn information from different sources, so that more accurate real-time speed estimation is realized.
It should be noted that, the correlation of the running data between the multiple modes is higher, but the problem that the data sources of the multiple modes cannot be synchronized exists, and according to the problem, the data of different modes can be subjected to independent speed estimation, and then a final speed estimated value is obtained in an integrated mode. Specifically, step S104 "speed estimation is performed according to the driving feature fusion data of the multiple fusion modes to obtain the target speed predicted value" in the above embodiment may include the following steps S301 to S302:
s301, inputting the driving characteristic fusion data of the multiple fusion modes into different speed estimation models according to the fusion modes to perform speed estimation, and obtaining initial speed estimated values of the multiple fusion modes.
In the embodiment of the present disclosure, the running feature fusion data of multiple fusion modes obtained in step S203 may be input into the same speed estimation model according to different fusion modes, the running feature fusion data of the same fusion mode is input into different speed estimation models, the speed estimation model performs speed estimation based on the input data, and an initial speed estimated value corresponding to the fusion mode is output.
S302, determining a target speed predicted value according to the initial speed predicted values of the multiple fusion modes.
In the embodiment of the present disclosure, the initial speed predicted values of the multiple fusion modes obtained in step S301 may be subjected to rule fusion to obtain a target speed predicted value. The rule fusion may specifically include, but is not limited to, any one of the following fusion modes: maximum value fusion, average value fusion, etc.
In summary, the speed estimation method in the embodiment of the present disclosure adopts a multi-mode fusion manner to fuse the running feature data of different modes, so as to interact the running feature data of different modes, thereby obtaining more representative running feature fusion data, further realizing more accurate speed estimation and overall traffic time estimation, simultaneously reducing the timeliness problem of congestion aggregation and dissipation, guaranteeing the rationality of the user in road selection, guiding the travel of the user scientifically, saving the travel time of the user, and continuously improving the perception experience of the overall traffic time estimation of the user. The characteristics are extracted by adopting the pre-training large model, and the universal traffic law characteristics and traffic trend characteristics can be learned by the pre-training large model through the learning of multi-source mass data, so that the representation of the extracted driving characteristic data is improved, and more accurate speed estimation and overall traffic time estimation can be realized. For running characteristic data of different sources, a multi-mode fusion mode is adopted, visual road state depiction of image data, more accurate vehicle distance and relative speed depiction of radar data and speed depiction of running track data are combined, and through combination of modes, a speed estimation model can learn information from different sources, so that more accurate real-time speed estimation is realized.
To clearly illustrate the speed estimation method according to the embodiments of the present disclosure, a detailed description will be given with reference to fig. 4, and fig. 4 is an overall flowchart of the speed estimation method according to the embodiments of the present disclosure.
As shown in fig. 4, the running data of multiple modes is exemplified by image data, which is the running data of an image mode, radar data, which is the running data of a radar mode, and running track data, which is the running data of a running track mode, the image data is subjected to feature extraction by using a res net 152 model to obtain the running feature data of the image mode, which is the image feature data, the radar data and the running track data are subjected to feature extraction by using a transducer model to obtain the running feature data of the radar mode, which is the radar feature data, and the running feature data of the running track mode, which is the running track feature data, and the running feature data of three modes are subjected to pairwise interaction fusion by using a twin network model to obtain the running feature fusion data of the three fusion modes, and the running feature fusion data is input into a speed prediction model to perform speed prediction to obtain the target speed pre-estimation value.
Fig. 5 is a block diagram of a speed estimation apparatus according to a first embodiment of the present disclosure.
As shown in fig. 5, a speed estimation device 500 according to an embodiment of the disclosure includes: an acquisition module 501, an extraction module 502, a fusion module 503 and an estimation module 504.
The acquiring module 501 is configured to acquire driving data of multiple modes.
The extracting module 502 is configured to perform feature extraction on running data of multiple modes, so as to obtain running feature data of multiple modes.
And the fusion module 503 is configured to interactively fuse the driving feature data of different modes to obtain driving feature fusion data of multiple fusion modes.
The estimating module 504 is configured to perform speed estimation according to the driving feature fusion data of the multiple fusion modes, so as to obtain a target speed estimated value.
It should be noted that the explanation of the above embodiment of the speed estimation method is also applicable to the speed estimation device of the embodiment of the present disclosure, and the specific process is not repeated here.
In summary, the speed estimation device in the embodiment of the present disclosure performs feature extraction on running data of multiple modes to obtain running feature data of multiple modes, performs interactive fusion on the running feature data of different modes to obtain running feature fusion data of multiple fusion modes, and performs speed estimation according to the running feature fusion data of multiple fusion modes to obtain a target speed estimated value. The disclosed embodiment adopts a multi-mode fusion mode, fuses the running characteristic data of different modes, and interacts the running characteristic data of different modes, so that more representative running characteristic fusion data is obtained, more accurate speed estimation and overall transit time estimation can be realized, meanwhile, the timeliness problem of congestion aggregation and dissipation is reduced, the rationality of a user on road selection is ensured, the travel of the user is scientifically guided, the travel time of the user is saved, and the perception experience of the overall transit time estimation of the user is continuously improved.
Fig. 6 is a block diagram of a speed estimation apparatus according to a second embodiment of the present disclosure.
As shown in fig. 6, a speed estimation device 600 according to an embodiment of the present disclosure includes: the device comprises an acquisition module 601, an extraction module 602, a fusion module 603 and an estimation module 604.
The acquiring module 601 has the same structure and function as the acquiring module 501 in the previous embodiment, the extracting module 602 has the same structure and function as the extracting module 502 in the previous embodiment, the merging module 603 has the same structure and function as the merging module 503 in the previous embodiment, and the estimating module 604 has the same structure and function as the estimating module 504 in the previous embodiment.
Further, the multi-modal travel data includes at least two of the following modalities: image data, radar data, and travel track data.
Further, the fusion module 603 includes: and the fusion unit 6031 is used for interactively fusing the running characteristic data of different modes by adopting the twin network model to obtain the running characteristic fusion data of multiple fusion modes.
Further, the estimating module 604 is further configured to: and inputting the driving characteristic fusion data of the multiple fusion modes into the same speed estimation model to perform speed estimation, so as to obtain a target speed estimated value.
Further, the estimating module 604 is further configured to: inputting the driving characteristic fusion data of the multiple fusion modes into different speed estimation models according to the fusion modes to perform speed estimation, and obtaining initial speed estimated values of the multiple fusion modes; and determining a target speed predicted value according to the initial speed predicted values of the multiple fusion modes.
Further, the estimating module 604 is further configured to: performing rule fusion on initial speed pre-estimation values of multiple fusion modes to obtain a target speed pre-estimation value, wherein the rule fusion comprises any one of the following fusion modes: maximum value fusion and average value fusion.
Further, the extraction module 602 is further configured to: and carrying out feature extraction on the driving data by adopting a feature extraction model to obtain the driving feature data.
Further, the extraction module 602 is further configured to: and carrying out feature extraction on the image data by adopting an image feature extraction model to obtain driving feature data.
Further, the extraction module 602 is further configured to: and carrying out feature extraction on the radar data or the driving track data by adopting a time sequence model to obtain driving feature data.
It should be noted that the explanation of the above embodiment of the speed estimation method is also applicable to the speed estimation device of the embodiment of the present disclosure, and the specific process is not repeated here.
In summary, the speed estimating device disclosed by the embodiment of the disclosure adopts a multi-mode fusion mode to fuse the running characteristic data of different modes, and interacts the running characteristic data of different modes, so that more representative running characteristic fusion data is obtained, more accurate speed estimation and overall transit time estimation can be realized, meanwhile, the timeliness problem of congestion aggregation and dissipation is reduced, the rationality of a user on road selection is ensured, the travel of the user is guided scientifically, the travel time of the user is saved, and the perception experience of the overall transit time estimation of the user is continuously improved. The characteristics are extracted by adopting the pre-training large model, and the universal traffic law characteristics and traffic trend characteristics can be learned by the pre-training large model through the learning of multi-source mass data, so that the representation of the extracted driving characteristic data is improved, and more accurate speed estimation and overall traffic time estimation can be realized. For running characteristic data of different sources, a multi-mode fusion mode is adopted, visual road state depiction of image data, more accurate vehicle distance and relative speed depiction of radar data and speed depiction of running track data are combined, and through combination of modes, a speed estimation model can learn information from different sources, so that more accurate real-time speed estimation is realized.
In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 7 illustrates a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the electronic device 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data required for the operation of the electronic device 700 may also be stored. The computing unit 701, the ROM702, and the RAM703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices through a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 701 performs the respective methods and processes described above, such as the estimation method of the velocity shown in fig. 1 to 4. For example, in some embodiments, the method of estimating speed may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 700 via the ROM702 and/or the communication unit 709. When a computer program is loaded into RAM703 and executed by computing unit 701, one or more steps of the semantic parsing method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the method of estimating the speed in any other suitable way (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
According to an embodiment of the present disclosure, the present disclosure further provides a computer program product comprising a computer program, wherein the computer program when executed by a processor implements the steps of the method of estimating velocity according to the above embodiments of the present disclosure.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims (21)

1. A method of speed estimation, comprising:
acquiring running data of multiple modes;
extracting characteristics of the running data of the multiple modes to obtain the running characteristic data of the multiple modes;
carrying out interactive fusion on the running characteristic data of different modes to obtain running characteristic fusion data of multiple fusion modes; and
and carrying out speed estimation according to the driving characteristic fusion data of the multiple fusion modes to obtain a target speed predicted value.
2. The predictive method of claim 1, wherein the plurality of modalities of travel data includes at least two of the following modalities:
image data, radar data, and travel track data.
3. The prediction method of claim 1, wherein the performing interactive fusion on the driving feature data of different modes to obtain driving feature fusion data of multiple fusion modes includes:
and adopting a twin network model to interactively fuse the running characteristic data of different modes to obtain the running characteristic fusion data of the multiple fusion modes.
4. The estimating method according to claim 1, wherein the estimating the speed according to the driving feature fusion data of the multiple fusion modes to obtain the target speed estimated value includes:
and inputting the driving characteristic fusion data of the multiple fusion modes into the same speed estimation model to perform speed estimation, so as to obtain the target speed estimated value.
5. The estimating method according to claim 1, wherein the estimating the speed according to the driving feature fusion data of the multiple fusion modes to obtain the target speed estimated value includes:
inputting the driving characteristic fusion data of the multiple fusion modes into different speed estimation models according to the fusion modes to perform speed estimation, so as to obtain initial speed estimated values of the multiple fusion modes; and
and determining the target speed predicted value according to the initial speed predicted values of the multiple fusion modes.
6. The method of estimating according to claim 5, wherein said determining the target speed estimate from the initial speed estimates of the plurality of fusion modalities comprises:
performing rule fusion on the initial speed pre-estimation values of the multiple fusion modes to obtain the target speed pre-estimation value, wherein the rule fusion comprises any one of the following fusion modes: maximum value fusion and average value fusion.
7. The predicting method according to claim 2, wherein the feature extracting the running data of multiple modes to obtain running feature data of multiple modes includes:
and carrying out feature extraction on the driving data by adopting a feature extraction model to obtain the driving feature data.
8. The pre-estimation method of claim 7, wherein the feature extraction of the driving data using the feature extraction model to obtain the driving feature data includes:
and carrying out feature extraction on the image data by adopting an image feature extraction model to obtain the driving feature data.
9. The pre-estimation method of claim 7, wherein the feature extraction of the driving data using the feature extraction model to obtain the driving feature data includes:
and carrying out feature extraction on the radar data or the driving track data by adopting a time sequence model to obtain the driving feature data.
10. A speed estimation device, comprising:
the acquisition module is used for acquiring running data of multiple modes;
the extraction module is used for carrying out feature extraction on the running data of the multiple modes to obtain the running feature data of the multiple modes;
the fusion module is used for carrying out interactive fusion on the running characteristic data of different modes to obtain running characteristic fusion data of multiple fusion modes; and
and the estimating module is used for estimating the speed according to the driving characteristic fusion data of the multiple fusion modes to obtain a target speed estimated value.
11. The predictive device of claim 10, wherein the plurality of modalities of travel data includes at least two of the following modalities:
image data, radar data, and travel track data.
12. The predictor device of claim 10, wherein the fusion module comprises:
and the fusion unit is used for carrying out interactive fusion on the running characteristic data of different modes by adopting a twin network model to obtain the running characteristic fusion data of the multiple fusion modes.
13. The predictive device of claim 10, wherein the predictive module is further configured to:
and inputting the driving characteristic fusion data of the multiple fusion modes into the same speed estimation model to perform speed estimation, so as to obtain the target speed estimated value.
14. The predictive device of claim 10, wherein the predictive module is further configured to:
inputting the driving characteristic fusion data of the multiple fusion modes into different speed estimation models according to the fusion modes to perform speed estimation, so as to obtain initial speed estimated values of the multiple fusion modes; and
and determining the target speed predicted value according to the initial speed predicted values of the multiple fusion modes.
15. The predictive device of claim 14, wherein the predictive module is further configured to:
performing rule fusion on the initial speed pre-estimation values of the multiple fusion modes to obtain the target speed pre-estimation value, wherein the rule fusion comprises any one of the following fusion modes: maximum value fusion and average value fusion.
16. The predictive device of claim 11, wherein the extraction module is further configured to:
and carrying out feature extraction on the driving data by adopting a feature extraction model to obtain the driving feature data.
17. The predictive device of claim 16, wherein the extraction module is further configured to:
and carrying out feature extraction on the image data by adopting an image feature extraction model to obtain the driving feature data.
18. The predictive device of claim 16, wherein the extraction module is further configured to:
and carrying out feature extraction on the radar data or the driving track data by adopting a time sequence model to obtain the driving feature data.
19. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.
20. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-9.
21. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method according to any one of claims 1-9.
CN202310413031.9A 2023-04-18 2023-04-18 Speed estimation method and device, electronic equipment and storage medium Pending CN116504057A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310413031.9A CN116504057A (en) 2023-04-18 2023-04-18 Speed estimation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310413031.9A CN116504057A (en) 2023-04-18 2023-04-18 Speed estimation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116504057A true CN116504057A (en) 2023-07-28

Family

ID=87324075

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310413031.9A Pending CN116504057A (en) 2023-04-18 2023-04-18 Speed estimation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116504057A (en)

Similar Documents

Publication Publication Date Title
CN112560496A (en) Training method and device of semantic analysis model, electronic equipment and storage medium
KR20220122566A (en) Text recognition model training method, text recognition method, and apparatus
EP4116940A2 (en) Method and apparatus for processing image, electronic device and storage medium
KR20230004391A (en) Method and apparatus for processing video, method and apparatus for querying video, training method and apparatus for video processing model, electronic device, storage medium, and computer program
US20230009547A1 (en) Method and apparatus for detecting object based on video, electronic device and storage medium
CN113392253B (en) Visual question-answering model training and visual question-answering method, device, equipment and medium
JP2023022185A (en) Map data processing method and device, electronic equipment, storage medium, and computer program
CN115860102B (en) Pre-training method, device, equipment and medium for automatic driving perception model
CN114715145B (en) Trajectory prediction method, device and equipment and automatic driving vehicle
CN115907009A (en) Migration method, device, equipment and medium for automatic driving perception model
US20230245429A1 (en) Method and apparatus for training lane line detection model, electronic device and storage medium
CN116092055A (en) Training method, acquisition method, device, equipment and automatic driving vehicle
CN116363459A (en) Target detection method, model training method, device, electronic equipment and medium
CN116749996A (en) Track prediction method, track prediction device, electronic equipment and storage medium
CN115687764B (en) Training method of vehicle track evaluation model, vehicle track evaluation method and device
JP2023036795A (en) Image processing method, model training method, apparatus, electronic device, storage medium, computer program, and self-driving vehicle
CN116246287A (en) Target object recognition method, training device and storage medium
CN114416941B (en) Knowledge graph-fused dialogue knowledge point determination model generation method and device
CN116504057A (en) Speed estimation method and device, electronic equipment and storage medium
CN113344121A (en) Method for training signboard classification model and signboard classification
CN114111813A (en) High-precision map element updating method and device, electronic equipment and storage medium
CN116168366B (en) Point cloud data generation method, model training method, target detection method and device
CN115661238B (en) Method and device for generating travelable region, electronic equipment and computer readable medium
CN116946159A (en) Motion trail prediction method, device, equipment and medium based on dynamic local map
CN117493888A (en) Early warning model training and early warning method, device, equipment and automatic driving vehicle

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination