WO2018157862A1 - 车型的识别方法和装置、存储介质、电子装置 - Google Patents

车型的识别方法和装置、存储介质、电子装置 Download PDF

Info

Publication number
WO2018157862A1
WO2018157862A1 PCT/CN2018/077898 CN2018077898W WO2018157862A1 WO 2018157862 A1 WO2018157862 A1 WO 2018157862A1 CN 2018077898 W CN2018077898 W CN 2018077898W WO 2018157862 A1 WO2018157862 A1 WO 2018157862A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
picture
neural network
vehicle type
target
Prior art date
Application number
PCT/CN2018/077898
Other languages
English (en)
French (fr)
Inventor
郑克松
张力
徐浩
申玉
Original Assignee
腾讯科技（深圳）有限公司
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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2018157862A1 publication Critical patent/WO2018157862A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Definitions

  • the present application relates to the field of monitoring, and in particular to a method and device for identifying a vehicle type, a storage medium, and an electronic device.
  • vehicle identification technology is an important part of a pre-processing of public security image detection and traffic state analysis.
  • vehicle identification technology has been further developed.
  • the current vehicle identification technology is quite different from the traditional vehicle identification.
  • the vehicle identification can only distinguish the approximate type of the vehicle. Such as small vehicles, medium vehicles and large vehicles.
  • the vehicle identification technology classifies the vehicle model features extracted from the vehicle face region image to determine the brand model to which the vehicle belongs.
  • the vehicle identification technology based on the vehicle face features has gradually become practical, not only can identify the vehicle brand, but also can identify the series and the annual model of the vehicle brand, thus greatly expanding the application of the technology in related fields.
  • the current vehicle identification algorithms mainly include the following two methods: template-based matching methods and statistical pattern recognition-based methods, which have high image requirements (such as illumination, angle, sharpness, occlusion, etc.), and Low recognition rate and lack of robustness.
  • the embodiment of the present application provides a method and device for identifying a vehicle type, a storage medium, and an electronic device, so as to at least solve the technical problem of low accuracy of vehicle type recognition in the related art.
  • a method for identifying a vehicle type includes: obtaining a request for vehicle type recognition of a vehicle in a target picture; and using a preset neural network model to identify a vehicle in the target image as a target vehicle
  • the preset neural network model is obtained by training a deep convolutional neural network model for performing vehicle type recognition using a training set, and the training set is a picture set obtained by performing first preprocessing on pictures of a plurality of vehicle models, A pre-processing is used to enhance the robustness of the preset neural network model, the plurality of models including the target vehicle type; and in response to the request, returning the recognition result including the target vehicle type.
  • an identification device for a vehicle type comprising: an acquisition unit configured to acquire a request for vehicle type recognition of a vehicle in a target picture; and an identification unit for using a preset nerve
  • the network model identifies that the vehicle in the target picture is the target vehicle type, wherein the preset neural network model is obtained by training the deep convolutional neural network model for vehicle type recognition using the training set, and the training set is for multiple models.
  • the picture is subjected to a first pre-processed picture set, the first pre-processing is used to enhance the robustness of the preset neural network model, the plurality of models includes the target vehicle type, and the response unit is configured to return the identification including the target vehicle type in response to the request. result.
  • a storage medium comprising a stored program, wherein the program is configured to execute any of the methods described above at runtime.
  • an electronic device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor being configured to be executed by a computer program Any of the above methods.
  • the deep convolutional neural network model for performing vehicle type recognition is trained by using the training set to obtain a preset neural network model, and when a request for vehicle type recognition of the vehicle in the target picture is obtained, Identification by a preset neural network model, since the training set is a set of pictures obtained by performing first pre-processing on pictures of a plurality of vehicle models, and the first pre-processing can enhance the robustness of the preset neural network model, that is, it can be eliminated.
  • the influence of environment and shooting angle on vehicle identification can solve the technical problem of low accuracy of vehicle identification in related technologies, and further achieve the technical effect of improving the accuracy of vehicle identification.
  • FIG. 1 is a schematic diagram of a hardware environment of a method of identifying a vehicle type according to an embodiment of the present application
  • FIG. 2 is a flow chart of an alternative vehicle type identification method in accordance with an embodiment of the present application.
  • FIG. 3 is a flow chart of an alternative vehicle type identification method in accordance with an embodiment of the present application.
  • FIG. 4 is a flow chart of an alternative vehicle type identification method in accordance with an embodiment of the present application.
  • FIG. 5 is a flow chart of an alternative vehicle type identification method in accordance with an embodiment of the present application.
  • FIG. 6 is a flow chart of an alternative vehicle type identification method in accordance with an embodiment of the present application.
  • FIG. 7 is a schematic diagram of an optional vehicle type identification device according to an embodiment of the present application.
  • FIG. 8 is a schematic diagram of an optional vehicle type identification device according to an embodiment of the present application.
  • FIG. 9 is a structural block diagram of a terminal according to an embodiment of the present application.
  • Robustness It is the transliteration of Robust, which means strong and strong. It is the key to system survival in exceptional and dangerous situations. For example, if the computer software fails to crash or crash under the condition of input error, disk failure, network overload or intentional attack, it is the robustness of the software.
  • the so-called “robustness” refers to the characteristic that the control system maintains some other performance under a certain (structure, size) parameter perturbation. According to different definitions of performance, it can be divided into stable robustness and performance robustness.
  • a fixed controller designed with the robustness of a closed-loop system as a target is called a robust controller.
  • ANN Artificial Neural Networks
  • NNNs neural network
  • Connection Model connection model
  • This kind of network relies on the complexity of the system to adjust the relationship between a large number of internal nodes to achieve the purpose of processing information.
  • a method embodiment of a method for identifying a vehicle type is provided.
  • the identification method of the above-described vehicle type can be applied to a hardware environment constituted by the server 102 and the terminal 104 as shown in FIG. 1.
  • the server 102 is connected to the terminal 104 through a network, and may further include a database 106 for providing a data storage service for the server, including but not limited to: a wide area network, a metropolitan area network, or a local area network, and the terminal 104 is not Limited to PCs, mobile phones, tablets, etc.
  • the identification method of the vehicle type of the embodiment of the present application may be performed by the server 102 (specifically, the following steps S202 to S206 may be performed), may be performed by the terminal 104, or may be performed by the server 102 and the terminal 104 in common.
  • the method for identifying the vehicle type in which the terminal 104 executes the embodiment of the present application may also be performed by a client installed thereon.
  • FIG. 2 is a flow chart of an alternative vehicle type identification method according to an embodiment of the present application. As shown in FIG. 2, the method may include the following steps:
  • Step S202 acquiring a request for vehicle type recognition of the vehicle in the target picture, for example, a request for clicking the "query model" triggered as shown in FIG. 1;
  • Step S204 using a preset neural network model to identify that the vehicle in the target image is the target vehicle type, and the preset neural network model is obtained by training the deep convolutional neural network model for vehicle type recognition using the training set, and the training set is Performing a first pre-processed picture set on a picture of a plurality of vehicle models, the first pre-processing is for enhancing the robustness of the preset neural network model, and the plurality of models includes the target vehicle type;
  • Step S206 in response to the request, returning the recognition result including the target vehicle type, as shown in FIG. 1, the recognition result may be displayed on the user terminal, such as "recognition result: XX brand XX model".
  • the deep convolutional neural network model for performing vehicle type recognition is trained by using the training set to obtain a preset neural network model, and when a request for vehicle type recognition of the vehicle in the target picture is obtained, It can be identified by a preset neural network model.
  • the training set is a set of pictures obtained by performing the first pre-processing on pictures of a plurality of vehicle models
  • the first pre-processing can enhance the robustness of the preset neural network model, that is, It can eliminate the influence of environment and shooting angle on vehicle identification, and can solve the technical problem of low accuracy of vehicle identification in related technologies, and further achieve the technical effect of improving the accuracy of vehicle identification.
  • the above-mentioned target picture is a picture of a car photographed by the user arbitrarily; the pictures of the plurality of models are pre-acquired pictures of the known models, and in order to improve the efficiency and accuracy of the recognition, multiple pictures can be taken from different angles for each model.
  • the picture, and then through the pre-processing can get the above training set.
  • the robustness described above includes performance robustness and stable robustness.
  • the above neural network model refers to a deep convolutional neural network model including a plurality of hidden layers (ie, convolutional layers) and feature extraction layers.
  • the lower neurons and all the upper neurons can form a connection, and the potential problem is the expansion of the number of parameters, which is not only easy to over-fit during training, but also easy to fall into Locally optimal, intrinsic local patterns (such as contours, boundaries, etc.) can be utilized in the image, and the concept of image processing can be combined with neural network technology, and the deep convolutional neural network model of the present application can be realized.
  • Locally optimal, intrinsic local patterns such as contours, boundaries, etc.
  • the deep convolutional neural network model not all upper and lower neurons can be directly connected, but through the "convolution kernel" (ie convolutional layer) as the intermediary, the same convolution kernel is shared in all images.
  • the image retains the original positional relationship after the convolution operation. It is precisely because the deep convolutional neural network model limits the number of parameters and mines the characteristics of the local structure, which can reduce the parameter quantity and improve the robustness of the network. Sex.
  • the Deep Convolutional Neural Network includes a convolutional layer and a pooled layer (ie, a feature classification layer), and a plurality of convolution-pooling units constitute a feature expression, which can be applied to two-dimensional image recognition.
  • the DCNN can be thought of as a DNN with a two-dimensional discrete convolution operation.
  • the structure of the DCNN includes a plurality of feature extraction layers (ie, convolution layers) and feature mapping layers (ie, feature classification layers).
  • feature extraction layers ie, convolution layers
  • feature mapping layers ie, feature classification layers.
  • the input of each neuron is connected to the local accepted domain of the previous layer, and is extracted.
  • the local feature once the local feature is extracted, its positional relationship with other features is also determined; each computing layer of the network is composed of multiple feature maps, each feature map is a plane, on the plane
  • the weights of all neurons are equal.
  • the feature mapping structure can use the sigmoid function which affects the function kernel as the activation function of the convolution network, so that the feature map has displacement invariance.
  • each convolutional layer in the convolutional neural network can be followed by a local average and secondary extraction.
  • the computational layer this unique two feature extraction structure reduces the feature resolution.
  • a template-based matching method can be used.
  • the disadvantage of this method is that the template is difficult to establish, and the vehicle cannot recognize the vehicle when the image rotates or the scale changes in the image, even if a small range of occlusion occurs.
  • the model is recognized normally; a method based on statistical pattern recognition can also be used, which requires that the probability distribution of each category is known, and the number of categories of decision classification is consistent, and the method is not robust to factors such as illumination and occlusion. That is, it is easily affected by factors such as illumination and occlusion.
  • the deep convolution network model of the present application has a better effect on image recognition, and the deep convolutional neural network can solve the problems encountered by the traditional vehicle identification algorithm and solve the above-mentioned vehicle identification scheme.
  • High technical requirements such as illumination, angle, sharpness, occlusion
  • low recognition rate poor robustness, etc., avoiding the influence of illumination, occlusion and other factors on vehicle identification, and improving recognition.
  • Robustness is a better effect on image recognition, and the deep convolutional neural network can solve the problems encountered by the traditional vehicle identification algorithm and solve the above-mentioned vehicle identification scheme.
  • the training may be performed as follows to obtain a preset neural network model: performing a first pre-processing on the pictures of the plurality of vehicle models to obtain a training set.
  • the training set is used to train the deep convolutional neural network model for vehicle type recognition, and a preset neural network model is obtained.
  • performing the first pre-processing on the pictures of the multiple models includes: processing each of the pictures of the plurality of models as follows, wherein each picture is regarded as the current picture: performing the first processing on the current picture
  • the operation and the second processing operation obtain a first picture, wherein the first picture is regarded as a picture in the training set, the first processing operation includes an operation of random rotation and random clipping, and the operation of random rotation and random clipping is used to cancel the image
  • the second processing operation is used to eliminate the impact of the image acquisition environment on the vehicle identification.
  • performing the first processing operation and the second processing operation on the current picture includes: performing at least one of the following processing on the current picture: size adjustment, random rotation, random clipping, Gaussian smoothing processing, brightness adjustment, and saturation adjustment (ie, the first processing operation), obtaining a second picture; performing histogram equalization processing on the second picture to obtain a third picture; performing whitening processing on the third picture (equalization processing and whitening processing, ie, second processing operation), Get the first picture.
  • one of performing operations such as “sizing, random rotation, random clipping, Gaussian smoothing, brightness adjustment, and saturation adjustment” may be performed, such as only Perform random rotation to improve the ability of the model to identify the vehicle from different angles, perform only brightness adjustment to improve the model's ability to identify the vehicle at different brightness, and only perform dimensional adjustment to improve the ability of the model to identify the vehicle in different appearances. Etc.; You can also perform multiple of these operations. It should be noted that when performing multiple of these operations, you can follow "Size, Random Rotation, Random Crop, Gaussian Smoothing, Brightness Adjustment, and Saturation Adjustment". This sequence is executed. The execution order can also be selected according to the requirements. The selected operation can be size adjustment and random rotation, or random cropping, Gaussian smoothing and brightness adjustment, or size adjustment, random rotation, brightness adjustment. And saturation adjustment, even for size adjustment, random rotation, with Cutting, Gaussian smoothing processing, brightness adjustment and saturation adjustment.
  • one or more of the above operations may be selected according to the ability of the model to be upgraded. If multiple of these operations are selected at the same time, it is equivalent to improving the model after one training (the same training set). A variety of abilities can obviously improve training efficiency.
  • the training set is used to train the deep convolutional neural network model for performing vehicle type recognition
  • the preset neural network model is obtained by: identifying, by the multiple convolution layers of the deep convolutional neural network model, the training set belongs to Multiple first feature information of all pictures of each vehicle type; after extracting the feature set of each vehicle type from all the first feature information of each vehicle type by the feature classification layer of the deep convolutional neural network model, the preset nerve is obtained
  • the network model wherein the feature set includes second feature information for indicating the vehicle type in all the first feature information, and the feature set is saved in the preset neural network model.
  • multiple random rotations can be performed, and each time a random rotation obtains one picture, that is, multiple random rotations can be obtained to obtain multiple pictures; similarly, in random cutting, it can also be performed.
  • Multiple random cropping to get multiple images.
  • step S202 acquiring the request for vehicle type identification of the vehicle in the target picture comprises: receiving a request sent by the first client to the server for performing vehicle type identification, wherein the first client Server connection.
  • a function interface ie, a preset interface for vehicle type identification is provided on the server, so that the server can receive a request sent by the client for vehicle type identification on the preset interface.
  • the function interface is a universal interface, and the client or the webpage can call the interface for vehicle type identification.
  • the function interface is used to send the captured image to the server, and the server recognizes After the result is returned, the recognition result including the target vehicle type is returned to the object calling the preset interface through the preset interface.
  • the second pre-processing of the target image is performed before the vehicle in the target image is identified as the target vehicle model by using the preset neural network model.
  • the preset neural network model is used to identify that the vehicle in the target image is the target vehicle
  • the image data of the second pre-processed target image is used as an input of the preset neural network model to identify the vehicle in the target image as a target. Model.
  • performing the second pre-processing on the target image includes: performing at least one of the following processes on the target image: performing cropping, resizing, Gaussian smoothing, brightness adjustment, and saturation adjustment according to the car frame to obtain the fourth image. For example, performing only the size adjustment, or only performing brightness adjustment, etc., or performing size adjustment and Gaussian smoothing processing, or performing brightness adjustment and saturation adjustment; performing a histogram equalization process on the fourth picture to obtain a fifth picture; The fifth picture is whitened to obtain picture data to be input into the preset neural network model.
  • the picture data of the second preprocessed target picture is used as an input of the preset neural network model to identify that the vehicle in the target picture is the target vehicle type: multiple convolution layers through the preset neural network model Identifying third feature information of the target image; acquiring a matching degree of the third feature information of the target image and the feature information in the feature set of each vehicle type, for example, determining a feature of each of the third feature information of the target image and each vehicle type
  • the number of the feature information in the set is the same, and the ratio of the number to the number of all the feature information in the feature set of each vehicle type is used as the matching degree; and the model corresponding to the target matching degree among the plurality of matching degrees of the plurality of vehicle models is determined.
  • the target matching degree includes the first N matching degrees in the arrangement of the plurality of matching degrees from large to small, and N is a positive integer.
  • N is a positive integer smaller than the number of vehicle models, and the above-described target matching degree is N which is the top of all the matching degrees from large to small.
  • step S206 in response to the request, returning the recognition result including the target vehicle type includes: after obtaining the target matching degree (ie, N large matching degrees), passing the N matching degrees through the function interface. Returned to the client, there is a client to show to the user.
  • the target matching degree ie, N large matching degrees
  • a vehicle identification framework based on deep convolutional neural network is proposed for the vehicle identification problem.
  • the image preprocessing is combined with the traditional digital image processing technology to solve the input picture requirement when the traditional method is used to identify the vehicle. High, and the problem of low recognition rate.
  • the scheme has good robustness when identifying the vehicle model, and is insensitive to factors such as illumination, noise, rotation, partial occlusion, etc., and the recognition rate is greatly improved.
  • the difference from the existing method is that no manual design or extraction is required.
  • the training picture ie, the current picture
  • the training is started, the network parameters are obtained, and saved;
  • the network parameters are reloaded; the user inputs the picture, performs preprocessing, and takes the picture as a network input; obtains various types of probability distributions, and returns the first N largest probability categories as output.
  • Step S302 acquiring a training data set.
  • Step S304 preprocessing the data in the data set.
  • the training picture is preprocessed first.
  • the preprocessing process is very important. Different preprocessing processes have a significant impact on the prediction result.
  • the preprocessing process of the design of the solution It is also an important source of good robustness and other advantages of this solution.
  • Step S306 the preprocessed data is input into the deep convolutional neural network.
  • Deep convolutional neural networks need to pay attention to the selection of networks that can adapt to a large number of categories and can identify the details. Because the category data of the models is large, the difference between the appearance of the cars, especially the different brands of the same brand, is very small. .
  • Pre-select a deep convolutional neural network such as Google's InceptionV3.
  • An important feature of the Inception-V3 network is the decomposition of large convolution kernels into small convolution kernels, such as the solution of 7*7 volume integrals into two one-dimensional convolutions (1*7 and 7*1), which can speed up Calculating the speed, while increasing the depth of the network and the nonlinearity of the network, enhances the feature extraction and presentation capabilities of the network.
  • the convolutional layer can be regarded as a feature extractor.
  • image feature extractor can be used as image pyramid. , whitening and other technologies.
  • these problems can be solved by data preprocessing and appropriate network structure.
  • Inception-V3 adapts to different scale object images through different sizes of convolution kernel stacks.
  • a deep convolutional neural network can be used as a vehicle model image feature extractor, and softmax is used as a classifier.
  • softmax is used as a classifier.
  • During training use a richer pre-processing technique to solve problems such as rotation invariance and illumination.
  • step S308 a deep convolutional neural network is obtained.
  • Step S402 adjusting the size of the picture to be input.
  • the size of the picture can be adjusted to 299 * 299.
  • step S404 in order to enhance the adaptability of the network to the image after the object is rotated, it is necessary to randomly rotate the picture.
  • step S406 in order to enhance the adaptability of the network when the object is partially occluded, the picture may be randomly cropped.
  • step S408 in order to remove the Gaussian noise and enhance the adaptability of the network to the input image, the Gaussian smoothing processing may be performed on the image.
  • step S410 in order to enhance the adaptability to the darker image, the brightness of the picture may be randomly processed.
  • step S412 in order to enhance the adaptability of the network to different saturation images, the saturation of the picture may be adjusted.
  • Step S414 after adjusting the saturation, performing histogram equalization processing, using histogram equalization, enhancing the contrast of the image while making the input pixel values more uniform.
  • Histogram is also called mass distribution map. If the pixels of an image occupy a lot of gray levels and are evenly distributed, such images tend to have high contrast and variable gray tone. Histogram equalization is a transformation function that automatically achieves this effect by simply inputting histogram information. Its basic idea is to broaden the gray level of the number of pixels in the image, and compress the gray level with a small number of pixels in the image, thereby expanding the dynamic range of the original value, and improving the contrast and gray tone. The changes make the image clearer.
  • step S416 a whitening process is performed, that is, the image data is decentralized, and the input can be normalized as an input of the network.
  • the whitening process is similar to the Principal Component Analysis (PCA) algorithm, for example, assuming that the training data is a third image, and is used for training due to strong correlation between adjacent pixels in the third image.
  • the input is redundant, and the purpose of whitening is to reduce the redundancy of the input, that is, decentralization; the input of the deep convolutional neural network through the whitening process has the following properties: correlation between features (images input) Lower, features have the same variance (such as the unit variance set in image processing).
  • the normalization process is a normalization process on image data, including but not limited to length, width, gray value, etc., such as the gray value of the pixel point, the value interval It is 0 to 255.
  • the gray value can be normalized to N/255.
  • Step S502 acquiring parameters of the deep convolutional neural network.
  • Step S504 obtaining a car picture.
  • Step S506 pre-processing the acquired car picture.
  • Step S508 the pre-processed car picture is input into the deep convolutional neural network.
  • step S510 the result of the output of the deep convolutional neural network is obtained.
  • model parameters adopt a Gaussian distribution.
  • a two-dimensional Gaussian distribution is used to initialize the convolution kernel parameters of the corresponding position; various parameters of the preprocessing process, such as random lifting brightness, where random Using a Gaussian distribution, the corresponding parameter is the Gaussian distribution parameter.
  • Step S602 adjusting the size of the picture to be input.
  • Step S604 detecting a rough frame of the car in the picture.
  • step S606 the picture is randomly cropped.
  • Step S608 performing Gaussian smoothing on the picture.
  • step S610 the brightness of the picture is randomly processed.
  • step S612 the saturation of the picture is adjusted.
  • step S614 a histogram equalization process is performed on the picture.
  • step S616 the picture is whitened.
  • the pre-processing in the prediction process does not require rotation and random cropping, but uses a simple car detector to take the approximate location of the car. The reason for this is that if the user is taking pictures, the car is not in the foreground, and the network is likely to cause misclassification.
  • a vehicle identification framework based on deep convolutional neural network is proposed for the vehicle identification problem.
  • the image processing is combined with the traditional digital image processing technology to solve the problem of inputting pictures when the traditional method is used to identify the vehicle.
  • the problem is high and the recognition rate is low.
  • the scheme has good robustness when identifying the vehicle model, and is insensitive to factors such as illumination, noise, rotation, partial occlusion, etc., and the recognition rate is greatly improved.
  • the difference from the existing method is that no manual design or extraction is required.
  • the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in various embodiments of the present application.
  • FIG. 7 is a schematic diagram of an optional vehicle type identification device according to an embodiment of the present application. As shown in FIG. 7, the device may include an acquisition unit 72, an identification unit 74, and a response unit 76.
  • the obtaining unit 72 is configured to acquire a request for vehicle type recognition of the vehicle in the target picture
  • the identifying unit 74 is configured to use the preset neural network model to identify that the vehicle in the target image is the target vehicle type, and the preset neural network model is obtained by training the deep convolutional neural network model for performing vehicle model identification using the training set.
  • the training set is a set of pictures obtained by first pre-processing a picture of a plurality of vehicle models, and the first pre-processing is used to enhance the robustness of the preset neural network model, and the plurality of models include the target vehicle type;
  • the response unit 76 is configured to return a recognition result including the target vehicle type in response to the request.
  • the obtaining unit 72 in this embodiment may be used to perform step S202 in the embodiment of the present application.
  • the identifying unit 74 in this embodiment may be used to perform step S204 in the embodiment of the present application.
  • the response unit 76 can be used to perform step S206 in the embodiment of the present application.
  • the foregoing modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the foregoing embodiments. It should be noted that the foregoing module may be implemented in a hardware environment as shown in FIG. 1 as part of the device, and may be implemented by software or by hardware.
  • the deep convolutional neural network model for performing vehicle type recognition is trained by using the training set to obtain a preset neural network model, and the preset can be obtained by obtaining a request for vehicle type recognition of the vehicle in the target picture.
  • the neural network model because the training set is a set of pictures obtained by performing the first pre-processing on the pictures of the plurality of vehicle models, and the first pre-processing can enhance the robustness of the preset neural network model, that is, the environment and the shooting angle can be eliminated.
  • the influence of the vehicle type identification can solve the technical problem of low accuracy of vehicle identification in the related art, and further achieve the technical effect of improving the accuracy of the vehicle identification.
  • the above-mentioned target picture is a picture of a car photographed by the user arbitrarily; the pictures of the plurality of models are pre-acquired pictures of the known models, and in order to improve the efficiency and accuracy of the recognition, multiple pictures can be taken from different angles for each model.
  • the picture, and then through the pre-processing can get the above training set.
  • the robustness described above includes performance robustness and stable robustness.
  • the above neural network model refers to a deep convolutional neural network model including a plurality of hidden layers (ie, convolutional layers) and feature extraction layers.
  • the lower neurons and all the upper neurons can form a connection, and the potential problem is the expansion of the number of parameters, which is not only easy to over-fit during training, but also easy to fall into Locally optimal, there are inherent local patterns (such as contours, boundaries, etc.) in the image. It is obvious that the concept of image processing should be combined with neural network technology, and the deep convolutional neural network model of this application can be used. To achieve the above objectives.
  • the deep convolutional neural network model not all upper and lower neurons can be directly connected, but through the "convolution kernel" (ie convolutional layer) as the intermediary, the same convolution kernel is shared in all images.
  • the image retains the original positional relationship after the convolution operation. It is precisely because the deep convolutional neural network model limits the number of parameters and mines the characteristics of the local structure, which can reduce the parameter quantity and improve the robustness of the network. Sex.
  • the Deep Convolutional Neural Network includes a convolutional layer and a pooled layer (ie, a feature classification layer), and a plurality of convolution-pooling units constitute a feature expression, which can be applied to two-dimensional image recognition.
  • the DCNN can be thought of as a DNN with a two-dimensional discrete convolution operation.
  • the deep convolution network model of the present application has a better effect on image recognition, and the deep convolutional neural network can solve the problems encountered by the traditional vehicle identification algorithm and solve the above-mentioned vehicle identification scheme.
  • High technical requirements such as illumination, angle, sharpness, occlusion
  • low recognition rate poor robustness, etc., avoiding the influence of illumination, occlusion and other factors on vehicle identification, and improving recognition.
  • Robustness is a better effect on image recognition, and the deep convolutional neural network can solve the problems encountered by the traditional vehicle identification algorithm and solve the above-mentioned vehicle identification scheme.
  • High technical requirements such as illumination, angle, sharpness, occlusion
  • low recognition rate poor robustness, etc., avoiding the influence of illumination, occlusion and other factors on vehicle identification, and improving recognition.
  • Robustness Robustness.
  • the apparatus of the present application further includes: a processing unit 82, configured to perform a first pre-processing on the pictures of the plurality of vehicle models before acquiring the request for vehicle type recognition of the vehicle in the target picture. And obtaining a training set; the training unit 84 is configured to train the deep convolutional neural network model for performing vehicle type recognition using the training set to obtain a preset neural network model.
  • the processing unit is further configured to perform processing on each of the pictures of the plurality of vehicle models, where each picture is regarded as a current picture: performing a first processing operation and a second processing operation on the current picture to obtain the first a picture, wherein the first picture is regarded as a picture in the training set, the first processing operation includes a random rotation and a random clipping operation, and the random rotation and the random clipping operation are used to eliminate the influence of the image collection angle on the vehicle type recognition, and second Processing operations are used to eliminate the impact of the image capture environment on vehicle identification.
  • the processing unit includes: a first processing module, configured to perform at least one of the following processes on the current image: size adjustment, random rotation, random cropping, Gaussian smoothing, brightness adjustment, and saturation adjustment, to obtain a second
  • the second processing module is configured to perform a histogram equalization process on the second image to obtain a third image.
  • the third processing module is configured to perform whitening processing on the third image to obtain a first image.
  • the training unit includes: an identification module, configured to identify, by using a plurality of convolution layers of the deep convolutional neural network model, a plurality of first feature information of all pictures belonging to each vehicle type in the training set; After extracting the feature set of each vehicle model from all the first feature information of each vehicle model through the feature classification layer of the deep convolutional neural network model, a preset neural network model is obtained, wherein the feature set includes all the first feature information.
  • the second feature information is used to indicate the vehicle type, and the feature set is saved in the preset neural network model.
  • the identifying unit is further configured to perform a second pre-processing on the target image before using the preset neural network model to identify that the vehicle in the target image is the target vehicle model; and identifying the target image in the target image by using the preset neural network model
  • the picture data of the target picture subjected to the second pre-processing is used as an input of the preset neural network model to identify that the vehicle in the target picture is the target vehicle type.
  • the identifying unit includes a pre-processing module, and the pre-processing module is configured to perform at least one of the following processes on the target image: cutting, resizing, Gaussian smoothing, brightness adjustment, and saturation adjustment according to the automobile frame, Four pictures; the fourth picture is subjected to histogram equalization processing to obtain a fifth picture; the fifth picture is whitened to obtain picture data to be input into the preset neural network model.
  • the pre-processing module is configured to perform at least one of the following processes on the target image: cutting, resizing, Gaussian smoothing, brightness adjustment, and saturation adjustment according to the automobile frame, Four pictures; the fourth picture is subjected to histogram equalization processing to obtain a fifth picture; the fifth picture is whitened to obtain picture data to be input into the preset neural network model.
  • the identifying unit includes an identifying module, configured to identify third feature information of the target image by using multiple convolution layers of the preset neural network model; acquiring third feature information of the target image and characteristics of each vehicle type a matching degree of the feature information in the set; determining a vehicle type corresponding to the target matching degree among the plurality of matching degrees of the plurality of vehicle models as the target vehicle type, wherein the target matching degree includes the plurality of matching degrees in the arrangement of the numerical values from large to small
  • the first N matching degrees, N is a positive integer.
  • the obtaining unit is further configured to receive a request for the vehicle type identification sent by the first client to the server, where the first client connects to the server through the Internet.
  • a function interface ie, a preset interface for vehicle type identification is provided on the server, so that the server can receive a request sent by the client for vehicle type identification on the preset interface.
  • the function interface is a universal interface, and any client or webpage can call the interface for vehicle identification.
  • the function interface is used to send the captured image to the server. After the result is recognized by the server, the object including the recognition result of the target vehicle type is returned to the preset interface through the preset interface.
  • a vehicle identification framework based on deep convolutional neural network is proposed for the vehicle identification problem.
  • the image processing is combined with the traditional digital image processing technology to solve the problem of inputting pictures when the traditional method is used to identify the vehicle.
  • the problem is high and the recognition rate is low.
  • the scheme has good robustness when identifying the vehicle model, and is insensitive to factors such as illumination, noise, rotation, partial occlusion, etc., and the recognition rate is greatly improved.
  • the difference from the existing method is that no manual design or extraction is required.
  • the foregoing modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the foregoing embodiments. It should be noted that the foregoing module may be implemented in a hardware environment as shown in FIG. 1 as part of the device, and may be implemented by software or by hardware, where the hardware environment includes a network environment.
  • a storage medium also referred to as a memory
  • the storage medium comprising a stored program, wherein the program is configured to execute any of the methods described above at runtime.
  • a server or terminal (also referred to as an electronic device) for implementing the identification method of the above-described vehicle type.
  • the terminal may include: one or more (only one shown in FIG. 9) processor 901, memory 903, and transmission device. 905 (such as the transmitting device in the above embodiment), as shown in FIG. 9, the terminal may further include an input/output device 907.
  • the memory 903 can be used to store software programs and modules, such as the identification method of the vehicle type in the embodiment of the present application and the program instructions/modules corresponding to the device, and the processor 901 executes by executing the software program and the module stored in the memory 903.
  • Memory 903 can include high speed random access memory, and can also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • memory 903 can further include memory remotely located relative to processor 901, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission device 905 described above is for receiving or transmitting data via a network, and can also be used for data transmission between the processor and the memory. Specific examples of the above network may include a wired network and a wireless network.
  • the transmission device 905 includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network.
  • the transmission device 905 is a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the memory 903 is configured to store an application.
  • the processor 901 can call the application stored in the memory 903 through the transmission device 905 to perform the steps of: acquiring a request for vehicle type recognition of the vehicle in the target picture; and using the preset neural network model to identify the vehicle in the target picture as The target vehicle model, wherein the preset neural network model is obtained by training a deep convolutional neural network model for vehicle type recognition using a training set, and the training set is a picture set obtained by performing first preprocessing on pictures of a plurality of vehicle models.
  • the first pre-processing is for enhancing the robustness of the preset neural network model, the plurality of models including the target vehicle model; and in response to the request, returning the recognition result including the target vehicle model.
  • the processor 901 is further configured to: perform a first pre-processing on the pictures of the plurality of vehicle models to obtain a training set; and use the training set to train the deep convolutional neural network model for performing the vehicle type recognition to obtain a preset neural network. Network model.
  • the deep convolutional neural network model for performing vehicle type recognition is trained by using the training set to obtain a preset neural network model, and the vehicle neural network model is obtained when the vehicle identification request for the vehicle in the target image is obtained.
  • the preset neural network model because the training set is a set of pictures obtained by performing the first pre-processing on the pictures of the plurality of vehicle models, and the first pre-processing can enhance the robustness of the preset neural network model, that is, the environment can be eliminated, and the shooting can be eliminated.
  • the influence of the angle on the vehicle identification can solve the technical problem of low accuracy of the vehicle identification in the related art, and further achieve the technical effect of improving the accuracy of the vehicle identification.
  • the structure shown in FIG. 9 is only illustrative, and the terminal can be a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palm computer, and a mobile Internet device (MID). Terminal equipment such as PAD.
  • FIG. 9 does not limit the structure of the above electronic device.
  • the terminal may also include more or fewer components (such as a network interface, display device, etc.) than shown in FIG. 9, or have a different configuration than that shown in FIG.
  • Embodiments of the present application also provide a storage medium.
  • the above storage medium may be used to execute a program code of a vehicle type identification method.
  • the foregoing storage medium may be located on at least one of the plurality of network devices in the network shown in the foregoing embodiment.
  • the storage medium is arranged to store program code for performing the following steps:
  • the preset neural network model is obtained by training the deep convolutional neural network model for vehicle type recognition using the training set, and the training set is obtained.
  • the image set obtained by performing the first pre-processing on the pictures of the plurality of models, the first pre-processing is used to enhance the robustness of the preset neural network model, and the plurality of models include the target vehicle type;
  • the foregoing storage medium may include, but not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • a mobile hard disk e.g., a hard disk
  • magnetic memory e.g., a hard disk
  • the integrated unit in the above embodiment if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in the above-described computer readable storage medium.
  • the technical solution of the present application in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product, which is stored in a storage medium.
  • a number of instructions are included to cause one or more computer devices (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the disclosed client may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, unit or module, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

Landscapes

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

Abstract

本申请公开了一种车型的识别方法和装置、存储介质、电子装置。其中，该方法包括：获取到对目标图片中的车辆进行车型识别的请求；使用预设神经网络模型识别出目标图片中的车辆为目标车型，预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，训练集合是对多个车型的图片进行第一预处理得到的图片集合，第一预处理用于增强预设神经网络模型的鲁棒性，多个车型包括目标车型；响应于请求，返回包括目标车型的识别结果。本申请解决了相关技术中进行车型识别的准确率较低的技术问题。

Description

车型的识别方法和装置、存储介质、电子装置
本申请要求于提交中国专利局，申请号为2017101216098、发明名称“车型的识别方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及监控领域，具体而言，涉及一种车型的识别方法和装置、存储介质、电子装置。
背景技术
在智能视频监控中，车型识别技术是公安图像侦查和交通状态分析的一个前期处理中的重要分体。随着信息技术的发展，车型识别技术也得到了进一步的发展，当前的车型识别技术与传统意义上的车型识别存在着较大的区别，传统意义上的车型识别仅能分辨出车辆的大致类型，如小型车辆、中型车辆和大型车辆。而当前意义上的车型识别技术就是对从车辆的车脸区域图像中提取出的车型特征进行分类，以确定该车辆所属的品牌型号。随着计算机技术的进步，基于车脸特征的车型识别技术逐渐走向实用，不但可以识别车辆品牌，甚至可以识别该车辆品牌旗下的系列和年款，从而大大扩展了该技术在相关领域的应用。
目前的车型识别算法主要包括以下两种：基于模版匹配的方法和基于统计模式识别的方法，这两种方法对图像的要求高(如对光照、角度、清晰度、是否有遮挡等)，且识别率较低、缺乏鲁棒性。
针对相关技术中进行车型识别的准确率较低的问题，目前尚未提出有效的解决方案。
发明内容
本申请实施例提供了一种车型的识别方法和装置、存储介质、电子装置，以至少解决相关技术中进行车型识别的准确率较低的技术问题。
根据本申请实施例的一个方面，提供了一种车型的识别方法，包括：获取到对目标图片中的车辆进行车型识别的请求；使用预设神经网络模型识别出目标图片中的车辆为目标车型，其中，预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，训练集合是对多个车型的图片进行第一预处理得到的图片集合，第一预处理用于增强预设神经网络模型的鲁棒性，多个车型包括目标车型；响应于请求，返回包括目标车型的识别结果。
根据本申请实施例的另一方面，还提供了一种车型的识别装置，包括：获取单元，用于获取到对目标图片中的车辆进行车型识别的请求；识别单元，用于使用预设神经网络模型识别出目标图片中的车辆为目标车型，其中，预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，训练集合是对多个车型的图片进行第一预处理得到的图片集合，第一预处理用于增强预设神经网络模型的鲁棒性，多个车型包括目标车型；响应单元，用于响应于请求，返回包括目标车型的识别结果。
根据本申请实施例的另一方面，还提供了一种存储介质，该存储介质包括存储的程序，其中，该程序被设置为运行时执行上述的任一种方法。
根据本申请实施例的另一方面，还提供了一种电子装置，包括存储器、处理器及存储在存储器上并可在所述处理器上运行的计算机程序，处理器被设置为通过计算机程序执行上述的任一种方法。
在本申请实施例中，通过使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到预设神经网络模型，在获取到对目标图片中的车辆进行车型识别的请求时即可通过预设神经网络模型进行识别，由于训练集合是对多个车型的图片进行第一预处理得到的图片集合，而第一预处理可增强预设神经网络模型的鲁棒性，也即可以消除环境、拍摄角度对 车型识别的影响，可以解决了相关技术中进行车型识别的准确率较低的技术问题，进而达到提升车型识别的准确率的技术效果。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是根据本申请实施例的车型的识别方法的硬件环境的示意图；
图2是根据本申请实施例的一种可选的车型的识别方法的流程图；
图3是根据本申请实施例的一种可选的车型的识别方法的流程图；
图4是根据本申请实施例的一种可选的车型的识别方法的流程图；
图5是根据本申请实施例的一种可选的车型的识别方法的流程图；
图6是根据本申请实施例的一种可选的车型的识别方法的流程图；
图7是根据本申请实施例的一种可选的车型的识别装置的示意图；
图8是根据本申请实施例的一种可选的车型的识别装置的示意图；以及
图9是根据本申请实施例的一种终端的结构框图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语 “第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、***、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
首先，在对本申请实施例进行描述的过程中出现的部分名词或者术语适用于如下解释：
鲁棒性:是Robust的音译，也就是健壮和强壮的意思。它是在异常和危险情况下***生存的关键。比如说，计算机软件在输入错误、磁盘故障、网络过载或有意攻击情况下，能否不死机、不崩溃，就是该软件的鲁棒性。所谓“鲁棒性”，是指控制***在一定(结构，大小)的参数摄动下，维持其它某些性能的特性。根据对性能的不同定义，可分为稳定鲁棒性和性能鲁棒性。以闭环***的鲁棒性作为目标设计得到的固定控制器称为鲁棒控制器。
人工神经网络：Artificial Neural Networks，简写为ANN，也简称为神经网络(NNs)或称作连接模型(Connection Model)，它是一种模仿动物神经网络行为特征，进行分布式并行信息处理的算法数学模型。这种网络依靠***的复杂程度，通过调整内部大量节点之间相互连接的关系，从而达到处理信息的目的。
根据本申请实施例，提供了一种车型的识别方法的方法实施例。
可选地，在本实施例中，上述车型的识别方法可以应用于如图1所示的由服务器102和终端104所构成的硬件环境中。如图1所示，服务器102通过网络与终端104进行连接，还可包括用于为服务器提供数据存储服务的数据库106，上述网络包括但不限于：广域网、城域网或局域网，终端104并不限定于PC、手机、平板电脑等。本申请实施例的车型的识别方法 可以由服务器102来执行(具体可执行下述步骤S202至步骤S206)，也可以由终端104来执行，还可以是由服务器102和终端104共同执行。其中，终端104执行本申请实施例的车型的识别方法也可以是由安装在其上的客户端来执行。
图2是根据本申请实施例的一种可选的车型的识别方法的流程图，如图2所示，该方法可以包括以下步骤：
步骤S202，获取到对目标图片中的车辆进行车型识别的请求，例如图1所示的点击“查询车型”触发的请求；
步骤S204，使用预设神经网络模型识别出目标图片中的车辆为目标车型，预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，训练集合是对多个车型的图片进行第一预处理得到的图片集合，第一预处理用于增强预设神经网络模型的鲁棒性，多个车型包括目标车型；
步骤S206，响应于请求，返回包括目标车型的识别结果，如图1所示，识别结果可显示在用户终端上，如“识别结果：XX品牌XX车型”。
通过上述步骤S202至步骤S206，通过使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到预设神经网络模型，在获取到对目标图片中的车辆进行车型识别的请求时即可通过预设神经网络模型来进行识别，由于训练集合是对多个车型的图片进行第一预处理得到的图片集合，而第一预处理可增强预设神经网络模型的鲁棒性，也即可以消除环境、拍摄角度对车型识别的影响，可以解决了相关技术中进行车型识别的准确率较低的技术问题，进而达到提升车型识别的准确率的技术效果。
上述的目标图片为用户任意拍摄的汽车的图片；多个车型的图片是指预先采集好的知道车型的图片，为了提高识别的效率和准确率，可以针对每个车型从不同角度拍摄到多张图片，然后通过预处理即可得到上述的训练集。
可选地，上述的鲁棒性包括性能鲁棒性和稳定鲁棒性。
上述的神经网络模型是指深度卷积神经网络模型，该神经网络模型包括多个隐层(即卷积层)和特征提取层。
需要说明的是，对于普通的神经网络DNN，其下层神经元和所有上层神经元都能够形成连接，带来的潜在问题是参数数量的膨胀，在训练时不仅容易过拟合，而且极容易陷入局部最优，在图像中有固有的局部模式(比如轮廓、边界等)可以利用，可将图像处理中的概念和神经网络技术相结合，而利用本申请的深度卷积神经网络模型恰恰可以实现上述目的。
在深度卷积神经网络模型中，并不是所有上下层神经元都能直接相连，而是通过“卷积核”(即卷积层)作为中介，同一个卷积核在所有图像内是共享的，图像通过卷积操作后仍然保留原先的位置关系，正是由于深度卷积神经网络模型限制了参数的个数并挖掘了局部结构的这个特点，从而可以减少参数量，并提高网络的鲁棒性。
例如，需要识别一幅彩色图像，这幅图像具有四个通道ARGB(即透明度和红绿蓝，对应了四幅相同大小的图像)，假设卷积核大小为2*2，共使用10个卷积核(w1到w10，每个卷积核用于学习不同的结构特征)，用w1在ARGB图像上进行卷积操作，可以得到隐含层的第一幅图像；这幅隐含层图像左上角第一个像素是四幅输入图像左上角2*2区域内像素的加权求和，以此类推，得到对应该卷积核的其它图像。同理，算上其他卷积核，隐含层对应10幅“图像”。每幅图像对是对原始图像中不同特征的响应，按照这样的结构继续传递下去，另外，在深度卷积神经网络模型中还有max-pooling(特征分类)等操作进一步提高鲁棒性。
深度卷积神经网络DCNN(Deep Convolutional Neural Network)包括卷积层、池化层(即特征分类层)，多个卷积-池化单元构成特征表达，可应用于二维图像识别。可将DCNN看作是带有二维离散卷积操作的DNN。
DCNN的结构包括多个特征提取层(即卷积层)和特征映射层(即特 征分类层)，在卷积层中，每个神经元的输入与前一层的局部接受域相连，并提取该局部的特征，一旦该局部特征被提取后，它与其它特征间的位置关系也随之确定下来；网络的每个计算层由多个特征映射组成，每个特征映射是一个平面，平面上所有神经元的权值相等，特征映射结构可采用影响函数核小的sigmoid函数作为卷积网络的激活函数，使得特征映射具有位移不变性。此外，由于一个映射面上的神经元共享权值，因而减少了网络自由参数的个数，可在卷积神经网络中的每一个卷积层后跟着设置一个用来求局部平均与二次提取的计算层，这种特有的两次特征提取结构减小了特征分辨率。
在进行车型识别时，可使用基于模版匹配的方法，该方法的缺点是模版很难建立，汽车在图像中发生旋转或者尺度反生变化时则无法识别车型，即使发生较小范围的遮挡也无法正常识别车型；还可以使用基于统计模式识别的方法，该方法要求各个类别总体的概率分布是已知的，决策分类的类别数是一致的，该方法对光照、遮挡等因素不具有鲁棒性，即容易受到光照、遮挡等因素的影响。
相对于上述的车型识别方法，使用本申请的深度卷积网络模型，对图片识别具有更好的效果，利用深度卷积神经网络可解决传统车型识别算法遇到的问题，解决上述车型识别方案中对图像的要求高(如对光照、角度、清晰度、是否有遮挡)、识别率较低、鲁棒性不好等技术难题，避免光照、遮挡等因素对车型识别造成的影响，提高识别的鲁棒性。
在上述实施例中，在获取到对目标图片中的车辆进行车型识别的请求之前，可按照如下方式进行训练得到预设神经网络模型：对多个车型的图片进行第一预处理，得到训练集合；使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练，得到预设神经网络模型。
可选地，对多个车型的图片进行第一预处理包括：对多个车型的图片中的每个图片进行如下处理，其中，每个图片被视为当前图片：对当前图片进行第一处理操作和第二处理操作，得到第一图片，其中，第一图片被 视为训练集合中的图片，第一处理操作包括随机旋转和随机裁剪的操作，随机旋转和随机裁剪的操作用于消除图像采集角度对车型识别的影响，第二处理操作用于消除图像采集环境对车型识别的影响。
可选地，对当前图片进行第一处理操作和第二处理操作包括：对当前图片执行如下处理中的至少之一：尺寸调整、随机旋转、随机裁剪、高斯平滑处理、亮度调整以及饱和度调整(即第一处理操作)，得到第二图片；对第二图片进行直方图均衡化处理，得到第三图片；对第三图片进行白化处理(均衡化处理和白化处理即第二处理操作)，得到第一图片。
可选地，对当前图片进行第一处理操作和第二处理操作时，可以执行“尺寸调整、随机旋转、随机裁剪、高斯平滑处理、亮度调整以及饱和度调整”这些操作中的一个，如仅执行随机旋转以提高模型从不同角度识别出车型的能力、仅执行亮度调整以提高模型在不同亮度下识别车型的能力、仅执行尺寸调整以提高模型在不同外观大小的情况下识别出车型的能力等；也可执行这些操作中的多个，需要说明的是，在执行这些操作中的多个时，可以按照“尺寸调整、随机旋转、随机裁剪、高斯平滑处理、亮度调整以及饱和度调整”这一顺序来执行，也可根据需求来选择执行顺序，所选择的操作可以为尺寸调整和随机旋转，或为随机裁剪、高斯平滑处理以及亮度调整，又或者为尺寸调整、随机旋转、亮度调整以及饱和度调整，甚至为尺寸调整、随机旋转、随机裁剪、高斯平滑处理、亮度调整以及饱和度调整。
需要说明的是，可以根据模型需要提升的能力来选择上述操作中的一种或者多种，若同时选择这些操作中的多种，相当于经过一次训练(同一个训练集)就能提高模型的多种能力，显然可以提高训练效率。
可选地，使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练，得到预设神经网络模型包括：通过深度卷积神经网络模型的多个卷积层识别出训练集合中属于每个车型的所有图片的多个第一特征信息；通过深度卷积神经网络模型的特征分类层从每个车型的所有第一特征 信息中提取出每个车型的特征集合之后，得到预设神经网络模型，其中，特征集合包括所有第一特征信息中用于指示车型的第二特征信息，特征集合保存在预设神经网络模型中。
在上述的随机旋转、随机裁剪中，可进行多次随机旋转，每次随机旋转得到一张图片，也即进行多次随机旋转可以得到多张图片；同理，在随机裁剪时，也可进行多次随机裁剪得到多张图片。通过使用多次随机旋转和随机裁剪之后的图片进行训练，由于包括了更为丰富的拍摄环境(拍摄角度、拍摄到的内容等)，因而可以提取到更为丰富的特征，进而可以学习到更多的特征，以学习到不同车型间的区别，也能更为准确的识别不同角度拍摄到的车辆的车型。
在步骤S202提供的技术方案中，获取到对目标图片中的车辆进行车型识别的请求包括：接收第一客户端向服务器发送的用于进行车型识别的请求，其中，第一客户端通过互联网与服务器连接。
在服务器上提供用于进行车型识别的函数接口(即预设接口)，这样，服务器就可以在预设接口上接收客户端发送的用于进行车型识别的请求。
需要说明的是，该函数接口为一个通用的接口，客户端或者网页可以调用该接口进行车型识别，例如，在即使通讯应用中，利用该函数接口将拍摄到的图片发送给服务器，由服务器识别出结果之后通过预设接口返回包括目标车型的识别结果至调用预设接口的对象。
在步骤S204提供的技术方案中，在使用预设神经网络模型识别出目标图片中的车辆为目标车型之前，对目标图片进行第二预处理。在使用预设神经网络模型识别出目标图片中的车辆为目标车型时，将经过第二预处理的目标图片的图片数据作为预设神经网络模型的输入，以识别出目标图片中的车辆为目标车型。
可选地，对目标图片进行第二预处理包括：对目标图片执行如下处理中的至少之一：按照汽车框架进行裁剪、尺寸调整、高斯平滑处理、亮度 调整以及饱和度调整，得到第四图片，例如，仅执行尺寸调整，或仅进行亮度调整等，又或者执行尺寸调整和高斯平滑处理，或者执行亮度调整和饱和度调整；将第四图片进行直方图均衡化处理，得到第五图片；将第五图片进行白化处理，得到待输入预设神经网络模型的图片数据。
可选地，将经过第二预处理的目标图片的图片数据作为预设神经网络模型的输入，以识别出目标图片中的车辆为目标车型包括：通过预设神经网络模型的多个卷积层识别出目标图片的第三特征信息；获取目标图片的第三特征信息与每个车型的特征集合中的特征信息的匹配度，例如，确定目标图片的第三特征信息中与每个车型的特征集合中的特征信息相同的数量，将该数量与每个车型的特征集合中的所有特征信息的数量的比值作为匹配度；确定与多个车型的多个匹配度中的目标匹配度对应的车型为目标车型，目标匹配度包括多个匹配度中数值从大到小的排列中的前N个匹配度，N为正整数。
上述的N为小于车型数量的正整数，上述的目标匹配度为所有匹配度从大到小排列时靠前的N个。
在步骤S206提供的技术方案中，响应于请求，返回包括目标车型的识别结果包括：在得到了上述的目标匹配度(即N个较大的匹配度)之后，将N个匹配度通过函数接口返回给客户端，有客户端展示给用户。
本申请提供的方法中，针对车型识别问题，提出了一种基于深度卷积神经网络的车型识别框架，结合传统的数字图像处理技术做图像预处理，解决了传统方法识别车型时对输入图片要求高，同时识别率较低的问题。本方案在识别车型时具有很好的鲁棒性，对光照、噪声、旋转、部分遮挡等因素不敏感，并且识别率有大幅度提升，与现有方法的区别是不需要手工设计、提取车型图像特征，采用CNN自动设计、提取、优化特征。不仅减少工作量，并且提升了识别率。
作为一种可选的实施例，在用本申请提供的方法进行图片识别时，将训练图片(即当前图片)预处理之后作为深度卷积神经网络的输入，开始 训练，得到网络参数并保存；线上运营时，重新加载网络参数；用户输入图片，做预处理，将该图片作为网络输入；得到各类的概率分布，将前N个最大的概率的类别作为输出返回。下面结合图3至图6详述本申请的实施例。
步骤S302，获取训练数据集合。
收集训练图片到数据集合，数据集合的收集非常重要，数据集合质量将直接决定模型参数的优劣，实际操作中可以采取人工采集以及与汽车专业网站合作的方式获取各个车型的训练图片。
步骤S304，对数据集合中的数据进行预处理。
在将训练图片输入深度卷积神经网络，先要对训练图片进行预处理，预处理流程是非常重要的，不同的预处理流程对预测结果有显著的影响，同时，本方案设计的预处理流程也是本方案具有很好的鲁棒性以及其他优点的重要来源。
步骤S306，将预处理后的数据输入深度卷积神经网络。
深度卷积神经网络在选择时需要注意选择能够适应类别数量多、能辨识细节特征的网络，因为车型的类别数据较大，同时汽车、特别是同一品牌不同系列的车型在外观上面的差异非常小。
预先选择一个深度卷积神经网络，如***的InceptionV3。Inception-V3网络一个重要的特点是将大卷积核分解为小卷积核，如将7*7的卷积分解成两个一维卷积(1*7和7*1)，从而可以加快计算速度，同时增加了网络的深度以及网络的非线性，从而增强了网络的特征提取以及表示能力。
在深度卷积神经网络中，其卷积层可以看作是一个特征提取器，为了实现特征提取的尺度不变性、旋转不变性、光照等，在图像特征提取器在应用时可采用如图像金字塔、白化等技术。对于深度卷积神经网络，可以通过数据的预处理以及合适的网络结构来解决这些问题，如对于尺度不变 性，Inception-V3通过不同大小的卷积核栈来适应不同尺度的物体图像。
在本方案中，可利用深度卷积神经网络作为车型图像特征提取器，使用softmax作为分类器。在训练时，使用较为丰富的预处理技术，解决诸如旋转不变性、光照等问题。
步骤S308，得到深度卷积神经网络。
进行训练流程的预处理方法如图4所示：
步骤S402，调整待输入图片的尺寸。
为了适应深度卷积网络的输入层，比如其输入层要求为299*299，那么就可以将图片的尺寸调整为299*299。
步骤S404，为了增强网络对于物体被旋转之后的图像的适应性，需要对图片进行随机旋转。
步骤S406，为增强网络对于物体被部分遮挡时的适应性，可对图片进行随机裁剪。
步骤S408，为了去除高斯噪声，增强网络对于输入图像含有较多噪声的适应性，可对图片进行高斯平滑处理。
步骤S410，为了增强对于较暗图像的适应性，可对图片的亮度进行随机处理。
步骤S412，为了增强网络对于不同饱和度图像的适应性，可调整图片的饱和度。
步骤S414，在调整饱和度之后，进行直方图均衡化处理，使用直方图均衡化，增强图像的对比度，同时使得输入像素值更为均匀。
直方图(Histogram)又称质量分布图，如果一副图像的像素占有很多的灰度级而且分布均匀，那么这样的图像往往有高对比度和多变的灰度色调。直方图均衡化就是一种能仅靠输入图像直方图信息自动达到这种效果的 变换函数。它的基本思想是对图像中像素个数多的灰度级进行展宽，而对图像中像素个数少的灰度进行压缩，从而扩展像原取值的动态范围，提高了对比度和灰度色调的变化，使图像更加清晰。
步骤S416，进行白化处理，即将图像数据去中心化，同时可归一化输入，作为网络的输入。
可选地，白化处理与主成分分析PCA(Principal Component Analysis)算法相似，例如，假设训练数据是第三图像，由于第三图像中相邻像素之间具有较强的相关性，所以用于训练时的输入是冗余的，白化的目的就是降低输入的冗余性，即去中心化；通过白化过程使得深度卷积神经网络的输入具有如下性质：特征(所输入的图像)之间相关性较低、特征具有相同的方差(如图像处理中设置的单位方差)。
可选地，上述归一化处理为对图像数据的归一化处理，图像数据包括但不局限于长度、宽度、灰度值等，如对于像素点的灰度值而言，其取值区间是0到255，对于任意一个灰度值为N的像素点，其灰度值可以归一化为N/255。
进行预测的流程如图5所示：
步骤S502，获取深度卷积神经网络的参数。
步骤S504，获取汽车图片。
步骤S506，对获取到的汽车图片进行预处理。
步骤S508，将预处理之后的汽车图片输入深度卷积神经网络。
步骤S510，得到深度卷积神经网络输出的结果。
需要说明的是，模型参数采用高斯分布，如对于卷积核，使用二维高斯分布去初始化相应位置的卷积核参数；预处理过程各种技术的参数，比如随机提升亮度，这里的随机可使用高斯分布，对应的参数即为高斯分布的参数。
进行预测的预处理如图6所示：
步骤S602，调整待输入图片的尺寸。
步骤S604，检测图片中汽车的粗略框架。
步骤S606，对图片进行随机裁剪。
步骤S608，对图片进行高斯平滑处理。
步骤S610，对图片的亮度进行随机处理。
步骤S612，调整图片的饱和度。
步骤S614，对图片进行直方图均衡化处理。
步骤S616，对图片进行白化处理。
需要说明的是，预测流程中的预处理不需要旋转以及随机裁剪，而是用一个简单的汽车检测器，将汽车的大概位置取出来。这么做的原因是如果用户拍照时，汽车并不处于前景中，网络很可能造成误分类。
在本申请提供的方法中，针对车型识别问题，提出了一种基于深度卷积神经网络的车型识别框架，结合传统的数字图像处理技术做图像预处理，解决了传统方法识别车型时对输入图片要求高，同时识别率较低的问题。本方案在识别车型时具有很好的鲁棒性，对光照、噪声、旋转、部分遮挡等因素不敏感，并且识别率有大幅度提升，与现有方法的区别是不需要手工设计、提取车型图像特征，采用CNN自动设计、提取、优化特征。不仅减少工作量，并且提升了识别率。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
根据本申请实施例，还提供了一种用于实施上述车型的识别方法的车型的识别装置。图7是根据本申请实施例的一种可选的车型的识别装置的示意图，如图7所示，该装置可以包括：获取单元72、识别单元74以及响应单元76。
获取单元72，用于获取到对目标图片中的车辆进行车型识别的请求；
识别单元74，用于使用预设神经网络模型识别出目标图片中的车辆为目标车型，预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，训练集合是对多个车型的图片进行第一预处理得到的图片集合，第一预处理用于增强预设神经网络模型的鲁棒性，多个车型包括目标车型；
响应单元76，用于响应于请求，返回包括目标车型的识别结果。
需要说明的是，该实施例中的获取单元72可以用于执行本申请实施例中的步骤S202，该实施例中的识别单元74可以用于执行本申请实施例中的步骤S204，该实施例中的响应单元76可以用于执行本申请实施例中的步骤S206。
此处需要说明的是，上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在如图1所示的硬件环境中，可以通过软件实现， 也可以通过硬件实现。
通过上述模块，通过使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到预设神经网络模型，在获取到对目标图片中的车辆进行车型识别的请求时即可通过预设神经网络模型，由于训练集合是对多个车型的图片进行第一预处理得到的图片集合，而第一预处理可增强预设神经网络模型的鲁棒性，也即可以消除环境、拍摄角度对车型识别的影响，可以解决了相关技术中进行车型识别的准确率较低的技术问题，进而达到提升车型识别的准确率的技术效果。
上述的目标图片为用户任意拍摄的汽车的图片；多个车型的图片是指预先采集好的知道车型的图片，为了提高识别的效率和准确率，可以针对每个车型从不同角度拍摄到多张图片，然后通过预处理即可得到上述的训练集。
可选地，上述的鲁棒性包括性能鲁棒性和稳定鲁棒性。
上述的神经网络模型是指深度卷积神经网络模型，该神经网络模型包括多个隐层(即卷积层)和特征提取层。
需要说明的是，对于普通的神经网络DNN，其下层神经元和所有上层神经元都能够形成连接，带来的潜在问题是参数数量的膨胀，在训练时不仅容易过拟合，而且极容易陷入局部最优，在图像中有固有的局部模式(比如轮廓、边界等)可以利用，显然应该将图像处理中的概念和神经网络技术相结合，而利用本申请的深度卷积神经网络模型恰恰可以实现上述目的。
在深度卷积神经网络模型中，并不是所有上下层神经元都能直接相连，而是通过“卷积核”(即卷积层)作为中介，同一个卷积核在所有图像内是共享的，图像通过卷积操作后仍然保留原先的位置关系，正是由于深度卷积神经网络模型限制了参数的个数并挖掘了局部结构的这个特点，从而可以减少参数量，并提高网络的鲁棒性。
深度卷积神经网络DCNN(Deep Convolutional Neural Network)包括卷积层、池化层(即特征分类层)，多个卷积-池化单元构成特征表达，可应用于二维图像识别。可将DCNN看作是带有二维离散卷积操作的DNN。
相对于相关的车型识别方法，使用本申请的深度卷积网络模型，对图片识别具有更好的效果，利用深度卷积神经网络可解决传统车型识别算法遇到的问题，解决上述车型识别方案中对图像的要求高(如对光照、角度、清晰度、是否有遮挡)、识别率较低、鲁棒性不好等技术难题，避免光照、遮挡等因素对车型识别造成的影响，提高识别的鲁棒性。
可选地，如图8所示，本申请的装置还包括：处理单元82，用于在获取到对目标图片中的车辆进行车型识别的请求之前，对多个车型的图片进行第一预处理，得到训练集合；训练单元84，用于使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练，得到预设神经网络模型。
上述的处理单元还用于对多个车型的图片中的每个图片进行如下处理，其中，每个图片被视为当前图片：对当前图片进行第一处理操作和第二处理操作，得到第一图片，其中，第一图片被视为训练集合中的图片，第一处理操作包括随机旋转和随机裁剪的操作，随机旋转和随机裁剪的操作用于消除图像采集角度对车型识别的影响，第二处理操作用于消除图像采集环境对车型识别的影响。
可选地，处理单元包括：第一处理模块，用于对当前图片执行如下处理中的至少之一：尺寸调整、随机旋转、随机裁剪、高斯平滑处理、亮度调整以及饱和度调整，得到第二图片；第二处理模块，用于对第二图片进行直方图均衡化处理，得到第三图片；第三处理模块，用于对第三图片进行白化处理，得到第一图片。
可选地，训练单元包括：识别模块，用于通过深度卷积神经网络模型的多个卷积层识别出训练集合中属于每个车型的所有图片的多个第一特征信息；训练模块，用于通过深度卷积神经网络模型的特征分类层从每个车型的所有第一特征信息中提取出每个车型的特征集合之后，得到预设神 经网络模型，其中，特征集合包括所有第一特征信息中用于指示车型的第二特征信息，特征集合保存在预设神经网络模型中。
可选地，识别单元还用于在使用预设神经网络模型识别出目标图片中的车辆为目标车型之前，对目标图片进行第二预处理；在使用预设神经网络模型识别出目标图片中的车辆为目标车型时，将经过第二预处理的目标图片的图片数据作为预设神经网络模型的输入，以识别出目标图片中的车辆为目标车型。
可选地，识别单元包括预处理模块，预处理模块用于对目标图片执行如下处理中的至少之一：按照汽车框架进行裁剪、尺寸调整、高斯平滑处理、亮度调整以及饱和度调整，得到第四图片；将第四图片进行直方图均衡化处理，得到第五图片；将第五图片进行白化处理，得到待输入预设神经网络模型的图片数据。
可选地，识别单元包括识别模块，识别模块用于通过预设神经网络模型的多个卷积层识别出目标图片的第三特征信息；获取目标图片的第三特征信息与每个车型的特征集合中的特征信息的匹配度；确定与多个车型的多个匹配度中的目标匹配度对应的车型为目标车型，其中，目标匹配度包括多个匹配度中数值从大到小的排列中的前N个匹配度，N为正整数。
上述的获取单元还用于接收第一客户端向服务器发送的用于进行车型识别的请求，其中，第一客户端通过互联网与服务器连接。
在服务器上提供用于进行车型识别的函数接口(即预设接口)，这样，服务器就可以在预设接口上接收客户端发送的用于进行车型识别的请求。
需要说明的是，该函数接口为一个通用的接口，任意的客户端或者网页均可以调用该接口进行车型识别，例如，在即使通讯应用中，利用该函数接口将拍摄到的图片发送给服务器，由服务器识别出结果之后通过预设接口返回包括目标车型的识别结果至调用预设接口的对象。
在本申请提供的方法中，针对车型识别问题，提出了一种基于深度卷 积神经网络的车型识别框架，结合传统的数字图像处理技术做图像预处理，解决了传统方法识别车型时对输入图片要求高，同时识别率较低的问题。本方案在识别车型时具有很好的鲁棒性，对光照、噪声、旋转、部分遮挡等因素不敏感，并且识别率有大幅度提升，与现有方法的区别是不需要手工设计、提取车型图像特征，采用CNN自动设计、提取、优化特征。不仅减少工作量，并且提升了识别率。
此处需要说明的是，上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在如图1所示的硬件环境中，可以通过软件实现，也可以通过硬件实现，其中，硬件环境包括网络环境。
根据本申请实施例的另一方面，还提供了一种存储介质(也称为存储器)，该存储介质包括存储的程序，其中，该程序被设置为运行时执行上述的任一种方法。
根据本申请实施例，还提供了一种用于实施上述车型的识别方法的服务器或终端(也称为电子装置)。
图9是根据本申请实施例的一种终端的结构框图，如图9所示，该终端可以包括：一个或多个(图9中仅示出一个)处理器901、存储器903、以及传输装置905(如上述实施例中的发送装置)，如图9所示，该终端还可以包括输入输出设备907。
其中，存储器903可用于存储软件程序以及模块，如本申请实施例中的车型的识别方法和装置对应的程序指令/模块，处理器901通过运行存储在存储器903内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的车型的识别方法。存储器903可包括高速随机存储器，还可以包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器903可进一步包括相对于处理器901远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通 信网及其组合。
上述的传输装置905用于经由一个网络接收或者发送数据，还可以用于处理器与存储器之间的数据传输。上述的网络具体实例可包括有线网络及无线网络。在一个实例中，传输装置905包括一个网络适配器(Network Interface Controller，NIC)，其可通过网线与其他网络设备与路由器相连从而可与互联网或局域网进行通讯。在一个实例中，传输装置905为射频(Radio Frequency，RF)模块，其用于通过无线方式与互联网进行通讯。
其中，可选地，存储器903用于存储应用程序。
处理器901可以通过传输装置905调用存储器903存储的应用程序，以执行下述步骤：获取到对目标图片中的车辆进行车型识别的请求；使用预设神经网络模型识别出目标图片中的车辆为目标车型，其中，预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，训练集合是对多个车型的图片进行第一预处理得到的图片集合，第一预处理用于增强预设神经网络模型的鲁棒性，多个车型包括目标车型；响应于请求，返回包括目标车型的识别结果。
处理器901还用于执行下述步骤：对多个车型的图片进行第一预处理，得到训练集合；使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练，得到预设神经网络模型。
采用本申请实施例，通过使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到预设神经网络模型，在获取到对目标图片中的车辆进行车型识别的请求时即可通过预设神经网络模型，由于训练集合是对多个车型的图片进行第一预处理得到的图片集合，而第一预处理可增强预设神经网络模型的鲁棒性，也即可以消除环境、拍摄角度对车型识别的影响，可以解决了相关技术中进行车型识别的准确率较低的技术问题，进而达到提升车型识别的准确率的技术效果。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例， 本实施例在此不再赘述。
本领域普通技术人员可以理解，图9所示的结构仅为示意，终端可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。图9其并不对上述电子装置的结构造成限定。例如，终端还可包括比图9中所示更多或者更少的组件(如网络接口、显示装置等)，或者具有与图9所示不同的配置。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
本申请的实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以用于执行车型的识别方法的程序代码。
可选地，在本实施例中，上述存储介质可以位于上述实施例所示的网络中的多个网络设备中的至少一个网络设备上。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：
S1，获取到对目标图片中的车辆进行车型识别的请求；
S2，使用预设神经网络模型识别出目标图片中的车辆为目标车型，其中，预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，训练集合是对多个车型的图片进行第一预处理得到的图片集合，第一预处理用于增强预设神经网络模型的鲁棒性，多个车型包括目标车型；
S3，响应于请求，返回包括目标车型的识别结果。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例在此不再赘述。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
上述实施例中的集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在上述计算机可读取的存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在存储介质中，包括若干指令用以使得一台或多台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。
在本申请的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的客户端，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的 部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
以上所述仅是本申请的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本申请原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本申请的保护范围。

Claims (17)

  1. 一种车型的识别方法，包括：
    获取到对目标图片中的车辆进行车型识别的请求；
    使用预设神经网络模型识别出所述目标图片中的车辆为目标车型，其中，所述预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，所述训练集合是对多个车型的图片进行第一预处理得到的图片集合，所述第一预处理用于增强所述预设神经网络模型的鲁棒性，多个所述车型包括所述目标车型；
    响应于所述请求，返回包括所述目标车型的识别结果。
  2. 根据权利要求1所述的方法，其中，在获取到对目标图片中的车辆进行车型识别的请求之前，所述方法还包括：
    对多个所述车型的图片进行所述第一预处理，得到所述训练集合；
    使用所述训练集合对用于进行车型识别的所述深度卷积神经网络模型进行训练，得到所述预设神经网络模型。
  3. 根据权利要求2所述的方法，其中，对多个所述车型的图片进行所述第一预处理包括：
    对多个所述车型的图片中的每个图片进行如下处理，其中，所述每个图片被视为当前图片：
    对所述当前图片进行第一处理操作和第二处理操作，得到第一图片，其中，所述第一图片被视为所述训练集合中的图片，所述第一处理操作包括随机旋转和随机裁剪的操作，所述随机旋转和所述随机裁剪的操作用于消除图像采集角度对车型识别的影响，所述第二处理操作用于消除图像采集环境对车型识别的影响。
  4. 根据权利要求3所述的方法，其中，对所述当前图片进行第一处理操作和第二处理操作包括：
    对所述当前图片执行如下处理中的至少之一：尺寸调整、随机旋 转、随机裁剪、高斯平滑处理、亮度调整以及饱和度调整，得到第二图片；
    对所述第二图片进行直方图均衡化处理，得到第三图片；
    对所述第三图片进行白化处理，得到所述第一图片。
  5. 根据权利要求2所述的方法，其中，使用所述训练集合对用于进行车型识别的所述深度卷积神经网络模型进行训练，得到所述预设神经网络模型包括：
    通过所述深度卷积神经网络模型的多个卷积层识别出所述训练集合中属于每个所述车型的所有图片的多个第一特征信息；
    通过所述深度卷积神经网络模型的特征分类层从每个所述车型的所有所述第一特征信息中提取出每个所述车型的特征集合之后，得到所述预设神经网络模型，其中，所述特征集合包括所有所述第一特征信息中用于指示所述车型的第二特征信息，所述特征集合保存在所述预设神经网络模型中。
  6. 根据权利要求1所述的方法，其中，
    在使用预设神经网络模型识别出所述目标图片中的车辆为目标车型之前，所述方法还包括：对所述目标图片进行第二预处理；
    使用预设神经网络模型识别出所述目标图片中的车辆为目标车型包括：将经过所述第二预处理的所述目标图片的图片数据作为所述预设神经网络模型的输入，以识别出所述目标图片中的车辆为所述目标车型。
  7. 根据权利要求6所述的方法，其中，对所述目标图片进行第二预处理包括：
    对所述目标图片执行如下处理中的至少之一：按照汽车框架进行裁剪、尺寸调整、高斯平滑处理、亮度调整以及饱和度调整，得到第四图片；
    将所述第四图片进行直方图均衡化处理，得到第五图片；
    将所述第五图片进行白化处理，得到待输入所述预设神经网络模型的图片数据。
  8. 根据权利要求6所述的方法，其中，将经过所述第二预处理的所述目标图片的图片数据作为所述预设神经网络模型的输入，以识别出所述目标图片中的车辆为所述目标车型包括：
    通过所述预设神经网络模型的多个卷积层识别出所述目标图片的第三特征信息；
    获取所述目标图片的第三特征信息与每个所述车型的特征集合中的特征信息的匹配度；
    确定与多个所述车型的多个所述匹配度中的目标匹配度对应的所述车型为所述目标车型，其中，所述目标匹配度包括多个所述匹配度中数值从大到小的排列中的前N个所述匹配度，N为正整数。
  9. 根据权利要求1至8中任意一项所述的方法，其中，获取到对目标图片中的车辆进行车型识别的请求包括：
    接收第一客户端向服务器发送的用于进行车型识别的所述请求，其中，所述第一客户端通过互联网与所述服务器连接。
  10. 根据权利要求1至8中任意一项所述的方法，其中，
    获取到对目标图片中的车辆进行车型识别的请求包括：在预设接口上接收向服务器发送的用于进行车型识别的所述请求，其中，所述预设接口为所述服务器提供的用于进行车型识别的函数接口；
    响应于所述请求，返回包括所述目标车型的识别结果包括：响应于所述请求，通过所述预设接口返回包括所述目标车型的识别结果至调用所述预设接口的对象。
  11. 一种车型的识别装置，包括：
    获取单元，被设置为获取到对目标图片中的车辆进行车型识别的请求；
    识别单元，被设置为使用预设神经网络模型识别出所述目标图片中的车辆为目标车型，其中，所述预设神经网络模型是使用训练集合对用于进行车型识别的深度卷积神经网络模型进行训练得到的，所述训练集合是对多个车型的图片进行第一预处理得到的图片集合，所述第一预处理用于增强所述预设神经网络模型的鲁棒性，多个所述车型包括所述目标车型；
    响应单元，被设置为响应于所述请求，返回包括所述目标车型的识别结果。
  12. 根据权利要求11所述的装置，其中，所述装置还包括：
    处理单元，被设置为在获取到对目标图片中的车辆进行车型识别的请求之前，对多个所述车型的图片进行所述第一预处理，得到所述训练集合；
    训练单元，被设置为使用所述训练集合对用于进行车型识别的所述深度卷积神经网络模型进行训练，得到所述预设神经网络模型。
  13. 根据权利要求12所述的装置，其中，所述处理单元还被设置为对多个所述车型的图片中的每个图片进行如下处理，其中，所述每个图片被视为当前图片：对所述当前图片进行第一处理操作和第二处理操作，得到第一图片，其中，所述第一图片被视为所述训练集合中的图片，所述第一处理操作包括随机旋转和随机裁剪的操作，所述随机旋转和所述随机裁剪的操作用于消除图像采集角度对车型识别的影响，所述第二处理操作用于消除图像采集环境对车型识别的影响。
  14. 根据权利要求13所述的装置，其中，所述处理单元包括：
    第一处理模块，被设置为对所述当前图片执行如下处理中的至少之一：尺寸调整、随机旋转、随机裁剪、高斯平滑处理、亮度调整以及饱和度调整，得到第二图片；
    第二处理模块，被设置为对所述第二图片进行直方图均衡化处理，得到第三图片；
    第三处理模块，被设置为对所述第三图片进行白化处理，得到所述第一图片。
  15. 根据权利要求12所述的装置，其中，所述训练单元包括：
    识别模块，被设置为通过所述深度卷积神经网络模型的多个卷积层识别出所述训练集合中属于每个所述车型的所有图片的多个第一特征信息；
    训练模块，被设置为通过所述深度卷积神经网络模型的特征分类层从每个所述车型的所有所述第一特征信息中提取出每个所述车型的特征集合之后，得到所述预设神经网络模型，其中，所述特征集合包括所有所述第一特征信息中用于指示所述车型的第二特征信息，所述特征集合保存在所述预设神经网络模型中。
  16. 一种存储介质，其中，所述存储介质中存储有计算机程序，所述计算机程序被设置为运行时执行权利要求1至10中任意一项所述的方法。
  17. 一种电子装置，包括存储器和处理器，其中，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序，以执行权利要求1至10中任意一项所述的方法。
PCT/CN2018/077898 2017-03-02 2018-03-02 车型的识别方法和装置、存储介质、电子装置 WO2018157862A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710121609.8A CN108304754A (zh) 2017-03-02 2017-03-02 车型的识别方法和装置
CN201710121609.8 2017-03-02

Publications (1)

Publication Number Publication Date
WO2018157862A1 true WO2018157862A1 (zh) 2018-09-07

Family

ID=62872501

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/077898 WO2018157862A1 (zh) 2017-03-02 2018-03-02 车型的识别方法和装置、存储介质、电子装置

Country Status (2)

Country Link
CN (1) CN108304754A (zh)
WO (1) WO2018157862A1 (zh)

Cited By (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109508672A (zh) * 2018-11-13 2019-03-22 云南大学 一种实时的视频目标检测方法
CN109543526A (zh) * 2018-10-19 2019-03-29 谢飞 基于深度差异性特征的真假面瘫识别***
CN109635627A (zh) * 2018-10-23 2019-04-16 中国平安财产保险股份有限公司 图片信息提取方法、装置、计算机设备及存储介质
CN109670532A (zh) * 2018-11-23 2019-04-23 腾讯科技（深圳）有限公司 生物体器官组织图像的异常识别方法、装置及***
CN109726712A (zh) * 2018-11-13 2019-05-07 平安科技（深圳）有限公司 文字识别方法、装置及存储介质、服务器
CN109800796A (zh) * 2018-12-29 2019-05-24 上海交通大学 基于迁移学习的船舶目标识别方法
CN109948610A (zh) * 2019-03-14 2019-06-28 西南交通大学 一种基于深度学习的视频中车辆细粒度分类方法
CN110348398A (zh) * 2019-07-15 2019-10-18 上海点积实业有限公司 一种神经网络模型确定方法和***
CN110705847A (zh) * 2019-09-18 2020-01-17 中国南方电网有限责任公司超高压输电公司广州局 一种基于图像识别技术的变电站智能巡检方法及***
CN110807123A (zh) * 2019-10-29 2020-02-18 中国科学院上海微***与信息技术研究所 车辆长度计算方法、装置、***、计算机设备及存储介质
CN111104952A (zh) * 2018-10-25 2020-05-05 珠海格力电器股份有限公司 识别食物种类的方法、***及装置、冰箱
CN111127541A (zh) * 2018-10-12 2020-05-08 杭州海康威视数字技术股份有限公司 车辆尺寸的确定方法、装置及存储介质
CN111241953A (zh) * 2020-01-03 2020-06-05 秒针信息技术有限公司 洗消验证方法和装置、存储介质及电子装置
CN111291812A (zh) * 2020-02-11 2020-06-16 浙江大华技术股份有限公司 属性类别的获取方法及装置、存储介质、电子装置
CN111310516A (zh) * 2018-12-11 2020-06-19 杭州海康威视数字技术股份有限公司 一种行为识别方法和装置
CN111383325A (zh) * 2018-12-29 2020-07-07 顺丰科技有限公司 车厢三维图像生成方法及装置
CN111401396A (zh) * 2019-01-03 2020-07-10 阿里巴巴集团控股有限公司 图像识别方法及装置
CN111507141A (zh) * 2019-01-31 2020-08-07 阿里巴巴集团控股有限公司 图片识别方法、服务界面显示方法、***及设备
CN111814592A (zh) * 2020-03-31 2020-10-23 同济大学 一种基于可叠加胶囊网络的植物叶片识别方法
CN111860077A (zh) * 2019-04-30 2020-10-30 北京眼神智能科技有限公司 人脸检测方法、装置、计算机可读存储介质及设备
CN112101246A (zh) * 2020-09-18 2020-12-18 济南博观智能科技有限公司 一种车辆识别方法、装置、设备及介质
CN112329772A (zh) * 2020-11-06 2021-02-05 浙江大搜车软件技术有限公司 车辆部件识别方法、装置、电子装置和存储介质
CN112417922A (zh) * 2019-08-20 2021-02-26 杭州海康威视数字技术股份有限公司 目标识别方法和装置
CN112541564A (zh) * 2019-09-20 2021-03-23 腾讯科技（深圳）有限公司 降低贝叶斯深度神经网络计算复杂度的方法和装置
CN112990240A (zh) * 2019-12-13 2021-06-18 搜狗（杭州）智能科技有限公司 一种确定车型的方法及相关装置
CN113076983A (zh) * 2021-03-26 2021-07-06 北京明略软件***有限公司 一种图像的识别方法和装置
CN113159081A (zh) * 2020-01-23 2021-07-23 华为技术有限公司 一种图像处理方法以及相关设备
CN113283466A (zh) * 2021-04-12 2021-08-20 开放智能机器（上海）有限公司 一种仪表读数识别方法及装置、可读存储介质
CN113392739A (zh) * 2021-06-02 2021-09-14 中南民族大学 滚动轴承状态的监测方法、装置、设备及存储介质
CN113807133A (zh) * 2020-06-12 2021-12-17 广州极飞科技股份有限公司 植物生长区域的灌水状态的识别方法、装置和存储介质
CN113837272A (zh) * 2021-09-23 2021-12-24 中汽创智科技有限公司 一种自动驾驶长尾数据增强方法
CN114943868A (zh) * 2021-05-31 2022-08-26 阿里巴巴新加坡控股有限公司 图像处理方法、装置、存储介质及处理器
CN117953460A (zh) * 2024-03-26 2024-04-30 江西众加利高科技股份有限公司 基于深度学习的车辆轮轴识别方法及装置

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109766915A (zh) * 2018-12-14 2019-05-17 深圳壹账通智能科技有限公司 基于图像识别的测试方法、装置、计算机设备及存储介质
CN111126224A (zh) * 2019-12-17 2020-05-08 成都通甲优博科技有限责任公司 车辆检测方法及分类识别模型训练方法
CN111104523A (zh) * 2019-12-20 2020-05-05 西南交通大学 基于语音辅助的视听协同学习机器人及学习方法
CN114419856A (zh) * 2021-11-25 2022-04-29 珠海格力电器股份有限公司 一种踢被检测预警***及其控制方法和空调器
CN115761659B (zh) * 2023-01-09 2023-04-11 南京隼眼电子科技有限公司 识别模型构建方法、车型识别方法、电子设备及存储介质
CN116342676A (zh) * 2023-05-31 2023-06-27 广州市杜格科技有限公司 一种交通的全息车辆外廓尺寸测量方法、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100278436A1 (en) * 2009-04-30 2010-11-04 Industrial Technology Research Institute Method and system for image identification and identification result output
CN104463241A (zh) * 2014-10-31 2015-03-25 北京理工大学 一种智能交通监控***中的车辆类型识别方法
CN105389593A (zh) * 2015-11-16 2016-03-09 上海交通大学 基于surf特征的图像物体识别方法
CN105894045A (zh) * 2016-05-06 2016-08-24 电子科技大学 一种基于空间金字塔池化的深度网络模型的车型识别方法
CN106295541A (zh) * 2016-08-03 2017-01-04 乐视控股（北京）有限公司 车辆类型识别方法及***

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106446834A (zh) * 2016-09-27 2017-02-22 东软集团股份有限公司 一种基于图像的车型识别方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100278436A1 (en) * 2009-04-30 2010-11-04 Industrial Technology Research Institute Method and system for image identification and identification result output
CN104463241A (zh) * 2014-10-31 2015-03-25 北京理工大学 一种智能交通监控***中的车辆类型识别方法
CN105389593A (zh) * 2015-11-16 2016-03-09 上海交通大学 基于surf特征的图像物体识别方法
CN105894045A (zh) * 2016-05-06 2016-08-24 电子科技大学 一种基于空间金字塔池化的深度网络模型的车型识别方法
CN106295541A (zh) * 2016-08-03 2017-01-04 乐视控股（北京）有限公司 车辆类型识别方法及***

Cited By (50)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111127541B (zh) * 2018-10-12 2024-02-27 杭州海康威视数字技术股份有限公司 车辆尺寸的确定方法、装置及存储介质
CN111127541A (zh) * 2018-10-12 2020-05-08 杭州海康威视数字技术股份有限公司 车辆尺寸的确定方法、装置及存储介质
CN109543526A (zh) * 2018-10-19 2019-03-29 谢飞 基于深度差异性特征的真假面瘫识别***
CN109635627A (zh) * 2018-10-23 2019-04-16 中国平安财产保险股份有限公司 图片信息提取方法、装置、计算机设备及存储介质
CN111104952A (zh) * 2018-10-25 2020-05-05 珠海格力电器股份有限公司 识别食物种类的方法、***及装置、冰箱
CN109726712A (zh) * 2018-11-13 2019-05-07 平安科技（深圳）有限公司 文字识别方法、装置及存储介质、服务器
CN109508672A (zh) * 2018-11-13 2019-03-22 云南大学 一种实时的视频目标检测方法
CN109670532A (zh) * 2018-11-23 2019-04-23 腾讯科技（深圳）有限公司 生物体器官组织图像的异常识别方法、装置及***
CN109670532B (zh) * 2018-11-23 2022-12-09 腾讯医疗健康(深圳)有限公司 生物体器官组织图像的异常识别方法、装置及***
CN111310516B (zh) * 2018-12-11 2023-08-29 杭州海康威视数字技术股份有限公司 一种行为识别方法和装置
CN111310516A (zh) * 2018-12-11 2020-06-19 杭州海康威视数字技术股份有限公司 一种行为识别方法和装置
CN111383325B (zh) * 2018-12-29 2023-06-30 深圳市丰驰顺行信息技术有限公司 车厢三维图像生成方法及装置
CN109800796A (zh) * 2018-12-29 2019-05-24 上海交通大学 基于迁移学习的船舶目标识别方法
CN111383325A (zh) * 2018-12-29 2020-07-07 顺丰科技有限公司 车厢三维图像生成方法及装置
CN111401396B (zh) * 2019-01-03 2023-04-18 阿里巴巴集团控股有限公司 图像识别方法及装置
CN111401396A (zh) * 2019-01-03 2020-07-10 阿里巴巴集团控股有限公司 图像识别方法及装置
CN111507141B (zh) * 2019-01-31 2023-04-18 阿里巴巴集团控股有限公司 图片识别方法、服务界面显示方法、***及设备
CN111507141A (zh) * 2019-01-31 2020-08-07 阿里巴巴集团控股有限公司 图片识别方法、服务界面显示方法、***及设备
CN109948610A (zh) * 2019-03-14 2019-06-28 西南交通大学 一种基于深度学习的视频中车辆细粒度分类方法
CN111860077A (zh) * 2019-04-30 2020-10-30 北京眼神智能科技有限公司 人脸检测方法、装置、计算机可读存储介质及设备
CN110348398A (zh) * 2019-07-15 2019-10-18 上海点积实业有限公司 一种神经网络模型确定方法和***
CN110348398B (zh) * 2019-07-15 2022-12-13 上海点积实业有限公司 一种神经网络模型确定方法和***
CN112417922A (zh) * 2019-08-20 2021-02-26 杭州海康威视数字技术股份有限公司 目标识别方法和装置
CN110705847A (zh) * 2019-09-18 2020-01-17 中国南方电网有限责任公司超高压输电公司广州局 一种基于图像识别技术的变电站智能巡检方法及***
CN112541564B (zh) * 2019-09-20 2024-02-20 腾讯科技（深圳）有限公司 降低贝叶斯深度神经网络计算复杂度的方法和装置
CN112541564A (zh) * 2019-09-20 2021-03-23 腾讯科技（深圳）有限公司 降低贝叶斯深度神经网络计算复杂度的方法和装置
CN110807123A (zh) * 2019-10-29 2020-02-18 中国科学院上海微***与信息技术研究所 车辆长度计算方法、装置、***、计算机设备及存储介质
CN112990240A (zh) * 2019-12-13 2021-06-18 搜狗（杭州）智能科技有限公司 一种确定车型的方法及相关装置
CN112990240B (zh) * 2019-12-13 2024-05-03 北京搜狗科技发展有限公司 一种确定车型的方法及相关装置
CN111241953A (zh) * 2020-01-03 2020-06-05 秒针信息技术有限公司 洗消验证方法和装置、存储介质及电子装置
CN111241953B (zh) * 2020-01-03 2023-11-10 河北太行农牧供应链有限公司 洗消验证方法和装置、存储介质及电子装置
CN113159081A (zh) * 2020-01-23 2021-07-23 华为技术有限公司 一种图像处理方法以及相关设备
CN111291812A (zh) * 2020-02-11 2020-06-16 浙江大华技术股份有限公司 属性类别的获取方法及装置、存储介质、电子装置
CN111291812B (zh) * 2020-02-11 2023-10-17 浙江大华技术股份有限公司 属性类别的获取方法及装置、存储介质、电子装置
CN111814592A (zh) * 2020-03-31 2020-10-23 同济大学 一种基于可叠加胶囊网络的植物叶片识别方法
CN111814592B (zh) * 2020-03-31 2024-04-26 同济大学 一种基于可叠加胶囊网络的植物叶片识别方法
CN113807133A (zh) * 2020-06-12 2021-12-17 广州极飞科技股份有限公司 植物生长区域的灌水状态的识别方法、装置和存储介质
CN113807133B (zh) * 2020-06-12 2023-09-01 广州极飞科技股份有限公司 植物生长区域的灌水状态的识别方法、装置和存储介质
CN112101246A (zh) * 2020-09-18 2020-12-18 济南博观智能科技有限公司 一种车辆识别方法、装置、设备及介质
CN112329772B (zh) * 2020-11-06 2024-03-05 浙江大搜车软件技术有限公司 车辆部件识别方法、装置、电子装置和存储介质
CN112329772A (zh) * 2020-11-06 2021-02-05 浙江大搜车软件技术有限公司 车辆部件识别方法、装置、电子装置和存储介质
CN113076983A (zh) * 2021-03-26 2021-07-06 北京明略软件***有限公司 一种图像的识别方法和装置
CN113283466A (zh) * 2021-04-12 2021-08-20 开放智能机器（上海）有限公司 一种仪表读数识别方法及装置、可读存储介质
CN114943868B (zh) * 2021-05-31 2023-11-14 阿里巴巴新加坡控股有限公司 图像处理方法、装置、存储介质及处理器
CN114943868A (zh) * 2021-05-31 2022-08-26 阿里巴巴新加坡控股有限公司 图像处理方法、装置、存储介质及处理器
CN113392739B (zh) * 2021-06-02 2022-09-30 中南民族大学 滚动轴承状态的监测方法、装置、设备及存储介质
CN113392739A (zh) * 2021-06-02 2021-09-14 中南民族大学 滚动轴承状态的监测方法、装置、设备及存储介质
CN113837272B (zh) * 2021-09-23 2024-03-26 中汽创智科技有限公司 一种自动驾驶长尾数据增强方法
CN113837272A (zh) * 2021-09-23 2021-12-24 中汽创智科技有限公司 一种自动驾驶长尾数据增强方法
CN117953460A (zh) * 2024-03-26 2024-04-30 江西众加利高科技股份有限公司 基于深度学习的车辆轮轴识别方法及装置

Also Published As

Publication number Publication date
CN108304754A (zh) 2018-07-20

Similar Documents

Publication Publication Date Title
WO2018157862A1 (zh) 车型的识别方法和装置、存储介质、电子装置
US11830230B2 (en) Living body detection method based on facial recognition, and electronic device and storage medium
KR102138082B1 (ko) 다수의 이미지 일치성을 바탕으로 보험클레임 사기 방지를 실현하는 방법, 시스템, 기기 및 판독 가능 저장매체
CN110852160B (zh) 以图像为基准的生物识别***及计算机实施方法
WO2018188453A1 (zh) 人脸区域的确定方法、存储介质、计算机设备
US10534957B2 (en) Eyeball movement analysis method and device, and storage medium
US10635946B2 (en) Eyeglass positioning method, apparatus and storage medium
WO2020000908A1 (zh) 一种人脸活体检测方法及装置
US20170213080A1 (en) Methods and systems for automatically and accurately detecting human bodies in videos and/or images
CN112052831B (zh) 人脸检测的方法、装置和计算机存储介质
CN111444744A (zh) 活体检测方法、装置以及存储介质
CN108416291B (zh) 人脸检测识别方法、装置和***
CN111008935B (zh) 一种人脸图像增强方法、装置、***及存储介质
CN111814620A (zh) 人脸图像质量评价模型建立方法、优选方法、介质及装置
EP3674973A1 (en) Method and apparatus with liveness detection and object recognition
WO2022247539A1 (zh) 活体检测方法、估算网络处理方法、装置、计算机设备和计算机可读指令产品
CN107169458A (zh) 数据处理方法、装置及存储介质
US10915739B2 (en) Face recognition device, face recognition method, and computer readable storage medium
CN112052830B (zh) 人脸检测的方法、装置和计算机存储介质
WO2020224221A1 (zh) 跟踪方法、装置、电子设备及存储介质
CN111191521B (zh) 人脸活体检测方法、装置、计算机设备及存储介质
CN112651333B (zh) 静默活体检测方法、装置、终端设备和存储介质
CN111626163A (zh) 一种人脸活体检测方法、装置及计算机设备
CN113642639B (zh) 活体检测方法、装置、设备和存储介质
WO2023279799A1 (zh) 对象识别方法、装置和电子***

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18761921

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18761921

Country of ref document: EP

Kind code of ref document: A1