Pedestrian classification recognition method and device based on signal statistical characteristics, electronic equipment and storage medium
Through the pedestrian classification identification method based on signal statistical characteristics, radar detection data and micro Doppler feature extraction technology are used to solve the problem of low detection accuracy for disabled people in the existing technology, and more accurate detection of disabled people is achieved, reducing the sample size requirement.
Patent Information
- Application Number
- CN202311813580.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-26
- Publication Date
- 2025-06-27
AI Technical Summary
Existing deep learning technologies are difficult to obtain accurate detection results for people with disabilities through large-scale training, mainly due to the small sample data for people with disabilities.
The pedestrian classification recognition method based on signal statistical characteristics is adopted. By obtaining radar detection data, micro Doppler features are extracted, including statistical trunk Doppler information, statistical Doppler total bandwidth and statistical limb movement cycle, the signal statistical feature range of different types of pedestrians is determined, and the classification recognition of pedestrians to be detected is achieved.
This method requires a small sample size, which can achieve more accurate detection of people with disabilities and reduces dependence on large-scale training data.
Smart Images
Figure CN120217066A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of artificial intelligence technology, and particularly to a pedestrian classification and recognition method, device, electronic device, and storage medium based on signal statistical features. Background Art
[0002] In recent years, artificial intelligence technology has shown a booming development trend. One of its applications is pedestrian detection through deep learning. This method can obtain relatively accurate pedestrian detection and segmentation accuracy through a large amount of data sampling and neural network training.
[0003] However, for disabled people, due to the small amount of their sample data, it is difficult to obtain good detection and segmentation accuracy through large-scale training of deep learning, and thus it is difficult to achieve accurate detection of disabled people. Summary of the Invention
[0004] The present disclosure is completed to solve the above problems, and its purpose is to provide a pedestrian classification and recognition method, device, electronic device, and storage medium based on signal statistical features. The pedestrian classification and recognition method based on signal statistical features requires a small amount of samples, and thus can achieve relatively accurate detection of disabled people.
[0005] According to one aspect of the present disclosure, a pedestrian classification and recognition method based on signal statistical features is provided, including: obtaining a pedestrian sample data set, which is radar detection data and includes different types of pedestrian samples and corresponding label information; extracting micro-Doppler features from each pedestrian sample in the pedestrian sample data set to obtain signal statistical features of different types of pedestrian samples, where the signal statistical features include statistical torso Doppler information, statistical Doppler total bandwidth, and statistical limb movement period; determining signal statistical feature ranges of different types of pedestrians based on the signal statistical features of different types of pedestrian samples, and storing the signal statistical feature ranges of different types of pedestrians; and classifying and recognizing a to-be-detected pedestrian based on the stored signal statistical feature ranges.
[0006] Preferably, the pedestrian sample data set includes normal pedestrians and disabled people.
[0007] Preferably, the torso Doppler information is torso Doppler frequency.
[0008] Preferably, the torso Doppler information is torso Doppler bandwidth.
[0009] According to another aspect of the present disclosure, there is provided a pedestrian classification and recognition device based on signal statistical features, including: an acquisition module configured to acquire a pedestrian sample data set, which is radar detection data and includes different types of pedestrian samples and corresponding label information; a feature extraction module configured to perform micro-Doppler feature extraction on each pedestrian sample in the pedestrian sample data set to obtain signal statistical features of different types of pedestrian samples, where the signal statistical features include statistical torso Doppler information, statistical Doppler total bandwidth, and statistical limb movement period; a range determination module configured to determine the signal statistical feature ranges of different types of pedestrians based on the signal statistical features of different types of pedestrian samples and store the signal statistical feature ranges of different types of pedestrians; and a classification and recognition module configured to classify and recognize a to-be-detected pedestrian based on the stored signal statistical feature ranges.
[0010] According to another aspect of the present disclosure, there is provided an electronic device, where the electronic device includes a processor and a memory, and at least one instruction or at least one program segment is stored in the memory, and the at least one instruction or the at least one program segment is loaded and executed by the processor to perform the method described in the above aspect.
[0011] According to another aspect of the present disclosure, there is provided a computer storage medium, where at least one instruction or at least one program segment is stored in the storage medium, and the at least one instruction or the at least one program segment is loaded and executed by a processor to perform the method described in the above aspect as claimed. Description of the Drawings
[0012] The drawings exemplarily show embodiments and form part of the specification, and are used together with the written description of the specification to explain the exemplary embodiments of the embodiments. The shown embodiments are for illustrative purposes only and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.
[0013] Figure 1 It shows a schematic flowchart of the pedestrian classification and recognition method based on signal statistical features provided by an embodiment of the present disclosure;
[0014] Figure 2 It shows a structural block diagram of the pedestrian classification and recognition device provided by an embodiment of the present disclosure;
[0015] Figure 3 It shows a structural block diagram of the electronic device provided by an embodiment of the present disclosure. Detailed Embodiments
[0016] Next, the present disclosure will be further described in detail with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention, rather than limiting the invention. Additionally, it should be noted that for the sake of description, only the parts related to the relevant invention are shown in the drawings.
[0017] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It will also be understood that when the terms "comprises" and / or "consists of" are used in this specification, the specified features, wholes, steps, operations, elements, and / or components are present, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their groups.
[0018] The embodiments described herein can be described with reference to plan views and / or cross-sectional views using ideal schematic diagrams of the present disclosure. Therefore, the example illustrations can be modified according to manufacturing techniques and / or tolerances. Thus, the embodiments are not limited to the embodiments shown in the drawings, but include modifications to the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be restrictive.
[0019] Unless otherwise defined, the meanings of all terms (including technical and scientific terms) used herein are the same as those commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in common dictionaries should be interpreted as having meanings consistent with their meanings in the context of the relevant art and the present disclosure, and will not be interpreted as having idealized or overly formal meanings unless clearly defined herein.
[0020] The disabled are a major social issue worldwide. In particular, the disabled have difficulty in moving, and face many challenges in road traffic, requiring special attention from drivers. However, at present, there is very little research on pedestrian recognition for the disabled, and due to the small amount of sample data of the disabled, it is difficult to obtain good detection and segmentation accuracy through large-scale training of deep learning.
[0021] The present disclosure provides a pedestrian classification and recognition method, device, electronic device, and storage medium based on signal statistical features, which require a small amount of samples, thereby enabling more accurate detection of the disabled.
[0022] Figure 1The flowchart shows the pedestrian classification and recognition method based on signal statistical features provided by the embodiments of the present disclosure. This specification provides method operation steps such as in the embodiments or flowcharts, but based on routine or non-creative labor, there can be more or fewer operation steps. The step order listed in the embodiments is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual system or server product executes, it can be executed in the order shown in the embodiments or the drawings, or executed in parallel (such as in an environment with parallel processors or multi-threaded processing).
[0023] S101: Obtain a pedestrian sample dataset, which is radar detection data containing different types of pedestrian samples and corresponding label information.
[0024] Among them, the pedestrian sample dataset includes normal pedestrians and disabled persons. Here, the disabled persons mainly refer to pedestrians with disabilities and inconvenient mobility. Moreover, all pedestrian samples in the pedestrian sample dataset have been pre-annotated with corresponding label information. Through this label information, it can be known which type of pedestrian a pedestrian sample belongs to, whether it is a normal pedestrian or a disabled person.
[0025] In addition, the pedestrian sample dataset here includes radar detection data, which is obtained by receiving the echo of the electromagnetic wave emitted by the radar device and can calculate information such as the distance and speed of the object.
[0026] S102: Extract the micro-Doppler features of each pedestrian sample in the pedestrian sample dataset to obtain the signal statistical features of different types of pedestrian samples. The signal statistical features include statistical torso Doppler information, statistical Doppler total bandwidth, and statistical limb movement period.
[0027] Specifically, the micro-Doppler feature extraction refers to the following processing.
[0028] First, perform range-Doppler processing on each pedestrian sample (radar detection data) in the pedestrian sample dataset.
[0029] Then, perform time-Doppler processing. Specifically, after range-Doppler processing, n range-Doppler maps are obtained. Each element in the range-Doppler map is called a "range cell". Then, for each range-Doppler map, the range cells are added together along the range axis to form a vector e. Finally, n temporally consecutive frames are combined together to form a time-Doppler spectrogram E with a time length of n frames.
[0030] Finally, after the above distance-Doppler processing and time-Doppler processing, combined with the label information of each pedestrian sample, the processed result signals of different types of pedestrian samples are analyzed and statistically processed to obtain the signal statistical characteristics of different types of pedestrian samples. Here, the processed result signals include the result signals of distance-Doppler processing and the result signals of time-Doppler processing. In addition, the signal statistical characteristics include statistical torso Doppler information, statistical Doppler total bandwidth, and statistical limb movement period. They are respectively statistically obtained according to the torso Doppler information, Doppler total bandwidth, and limb movement period of different types of pedestrian samples. For example, the statistical torso Doppler information, statistical Doppler total bandwidth, and statistical limb movement period of normal pedestrians are statistically obtained according to normal pedestrian samples, and the statistical torso Doppler information, statistical Doppler total bandwidth, and statistical limb movement period of disabled persons are statistically obtained according to disabled person samples.
[0031] (I) The torso Doppler information can be the torso Doppler frequency x1, which corresponds to the torso velocity of the pedestrian. The human torso velocity is a very basic but important piece of information. For different activities, there are significant differences in the torso velocity, which is shown in the following formula (1):
[0032]
[0033] where, dopplerArgmax(e i ) represents the Doppler frequency shift corresponding to the maximum signal intensity in the vector e, V i represents the torso movement velocity in one frame, λ represents the wavelength. Z represents the total number of frames in the entire observation period.
[0034] In addition, the Doppler information can also be the torso Doppler bandwidth.
[0035] (II) The total bandwidth x2 of the Doppler signal is related to the movement velocity of the limbs. Rapidly swinging the arms or legs will result in a larger bandwidth. It is shown in the following formula (2):
[0036]
[0037] where, is the time-Doppler spectrogram with a time window size of T w . and respectively represent extracting the upper envelope and the lower envelope within the time window.
[0038] (III) The limb movement period x3 corresponds to the swinging rate of the arms and legs, and it is shown in the following formula (3):
[0039]
[0040] where, Indicates the number of extreme points of the upper envelope and the lower envelope within the time window.
[0041] S103: Determine the signal statistical feature ranges of different types of pedestrians based on the signal statistical features of different types of pedestrian samples, and store the signal statistical feature ranges of different types of pedestrians.
[0042] After obtaining the signal statistical features of different types of pedestrian samples through step S102, the signal statistical feature ranges of different types of pedestrians can be determined based on the signal statistical features of different types of pedestrian samples, and the signal statistical feature ranges can be stored, which can be used for subsequent pedestrian classification and recognition.
[0043] S104: Classify and recognize the pedestrians to be detected based on the stored signal statistical feature ranges.
[0044] Each pedestrian sample (radar detection data) in the present disclosure is data detected under relatively long-distance conditions, so that the presence of disabled persons can be detected with a certain lead and early warning and other processes can be carried out.
[0045] According to the present disclosure, relatively accurate detection of disabled persons can be achieved with a small sample size.
[0046] Figure 2 Shows the structural block diagram of the pedestrian classification and recognition device provided by the embodiment of the present disclosure. As Figure 3 shown, the pedestrian classification and recognition device 200 includes: an acquisition module 201, a feature extraction module 202, a range determination module 203, and a classification and recognition module 204.
[0047] Among them, the acquisition module 201 is used to acquire a pedestrian sample data set, which includes different types of pedestrian samples and corresponding label information. The feature extraction module 202 is used to perform micro-Doppler feature extraction on each pedestrian sample in the pedestrian sample data set to obtain the signal statistical features of different types of pedestrian samples, and the signal statistical features include torso Doppler information, Doppler total bandwidth, and limb movement period. The range determination module 203 is used to determine the signal statistical feature ranges of different types of pedestrians based on the signal statistical features of different types of pedestrian samples, and store the signal statistical feature ranges of different types of pedestrians. The classification and recognition module 204 is used to classify and recognize the pedestrians to be detected based on the stored signal statistical feature ranges.
[0048] Figure 3 Shows the structural block diagram of the electronic device provided by the embodiment of the present disclosure. As Figure 3As shown, the present disclosure also provides an electronic device 300, which includes a processor and a memory. At least one instruction or at least one program segment is stored in the memory, and the at least one instruction or the at least one program segment is loaded and executed by the processor to implement the method described in the above embodiments.
[0049] The present disclosure also provides a computer storage medium, in which at least one instruction or at least one program segment is stored, and the at least one instruction or the at least one program segment is loaded and executed by a processor to implement the method described in the above embodiments.
[0050] Optionally, in this embodiment, the above storage medium may be located in at least one of multiple network servers in a computer network. Optionally, in this embodiment, the above storage medium may include, but is not limited to: various media capable of storing program codes such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs.
[0051] Those skilled in the art should be able to realize that the modules, units, and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.
[0052] Although the present disclosure has been described with reference to current specific embodiments, those of ordinary skill in the art in this technical field should recognize that the scope of the invention involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the present disclosure.
Claims
1. A pedestrian classification and recognition method based on signal statistical features, characterized in that Including: Obtain a pedestrian sample dataset, which is radar detection data and contains different types of pedestrian samples and corresponding label information; Extract micro-Doppler features from each pedestrian sample in the pedestrian sample dataset to obtain signal statistical features of different types of pedestrian samples. The signal statistical features include statistical torso Doppler information, statistical total Doppler bandwidth, and statistical limb movement period; Determine the signal statistical feature ranges of different types of pedestrians based on the signal statistical features of different types of pedestrian samples, and store the signal statistical feature ranges of different types of pedestrians; And Classify and identify the pedestrians to be detected based on the stored signal statistical feature ranges.
2. The pedestrian classification and recognition method according to claim 1, characterized in that, When extracting micro-Doppler features from each pedestrian sample in the pedestrian sample dataset to obtain signal statistical features of different types of pedestrian samples, it includes: Perform range-Doppler processing on each pedestrian sample in the pedestrian sample dataset; Perform time-Doppler processing based on the results of the range-Doppler processing; and Combine the label information of each pedestrian sample to analyze and statistically process the processed result signals of different types of pedestrian samples, so as to obtain the signal statistical features of different types of pedestrian samples.
3. The pedestrian classification and identification method according to claim 1 or 2, wherein The pedestrian sample dataset includes normal pedestrians and disabled persons.
4. The pedestrian classification and identification method according to claim 1 or 2, wherein The torso Doppler information is the torso Doppler frequency.
5. The pedestrian classification and identification method according to claim 1 or 2, wherein The torso Doppler information is the torso Doppler bandwidth.
6. A pedestrian classification and recognition device based on signal statistical features, characterized in that, Including: An acquisition module, configured to acquire a pedestrian sample dataset, which is radar detection data and contains different types of pedestrian samples and corresponding label information; A feature extraction module, configured to extract micro-Doppler features from each pedestrian sample in the pedestrian sample dataset to obtain signal statistical features of different types of pedestrian samples. The signal statistical features include statistical torso Doppler information, statistical total Doppler bandwidth, and statistical limb movement period; A range determination module, configured to determine the signal statistical feature ranges of different types of pedestrians based on the signal statistical features of different types of pedestrian samples, and store the signal statistical feature ranges of different types of pedestrians; And A classification and identification module, configured to classify and identify the pedestrians to be detected based on the stored signal statistical feature ranges.
7. An electronic device, characterized in that, The electronic device includes a processor and a memory. At least one instruction or at least one program segment is stored in the memory, and the at least one instruction or the at least one program segment is loaded and executed by the processor to perform the method according to any one of claims 1 to 5.
8. A computer storage medium, characterized in that, At least one instruction or at least one program segment is stored in the storage medium, and the at least one instruction or the at least one program segment is loaded and executed by the processor to perform the method according to any one of claims 1 to 5.