CN109932695A - A method and device for improving target recognition speed - Google Patents

Abstract

The invention discloses a kind of methods for improving object recognition speed, comprising the following steps: frequency mixing stages: after receiving echo-signal, echo-signal is mixed with local oscillation signal to obtain intermediate-freuqncy signal；Sampling step: digitized processing is carried out to intermediate-freuqncy signal by sampling module；Clutter cancellation step: clutter cancellation processing is carried out to the intermediate-freuqncy signal for being digitized processing；Adding window step: windowing process is carried out to the intermediate-freuqncy signal by clutter cancellation processing；Difference frequency obtaining step: the intermediate-freuqncy signal after windowing process is handled to obtain beat frequency by Fast Fourier Transform (FFT) and frequency spectrum refinement algorithm；It calculates step: the speed and distance of corresponding object being calculated according to object calculation formula.The method of raising object recognition speed of the invention is handled echo-signal by using Fast Fourier Transform (FFT) and frequency spectrum refinement algorithm, so that signal processing computation amount, effectively reduces the calculating cost of system.

Description

A method and device for improving target recognition speed

technical field

The present invention relates to the technical field of automobiles, and in particular, to a method and device for improving the recognition speed of a target.

Background technique

At present, with the development of science and technology and the progress of the times, smart cars have become an inevitable trend of future car development. At the same time, with the development of smart car technology, traditional car technology is facing more and more challenges, and the development space of various research fields in the automotive industry is also growing. Intelligent vehicles mainly acquire key performance parameters quickly during starting, driving and braking, and the acquisition of these key parameters relies on the application of high-sensitivity automotive sensors. Among them, the on-board radar sensor is one of the key sensors in the intelligent vehicle system. Millimeter-wave radar, as the backbone of vehicle-mounted radar sensors, has always been a research hotspot in vehicle-mounted sensor technology.

The key to the realization of its function of the vehicle-mounted millimeter-wave radar is to effectively process the various information obtained from the radar sensor in a short time. Some of the received information contains target information, and some only have clutter noise and various interference components. It is crucial to filter out the interference and noise components mixed in the echo signal, convert the signal into an easily analyzable form, and prepare the car for its active safety functions. Therefore, we need to adopt a variety of methods to process the signal, reduce the reaction time, improve the accuracy of recognition, reduce false alarms, and improve the reliability of the entire system to ensure the safety of the car.

For the signal processing of the vehicle-mounted millimeter-wave radar, the traditional signal processing method is to obtain the target parameters from the time domain, and measure the distance of the static target according to the method of measuring the average frequency of the echo intermediate frequency; the subsequent signal processing method is to obtain the distance from the frequency domain. The parameters of moving targets and multi-targets usually adopt the structure of "beat-Fourier transform", which is the best detection and receiving system for the effective segment of the target echo signal in the middle of the stationary white Gaussian noise, but at the same time, there are several significant disadvantages,

1. If there are too many signal processing points, the operation speed of the system will be greatly reduced, which will affect the real-time performance of the system.

Second, the precision and accuracy of target recognition and measurement are not high.

3. In the practical application of vehicle-mounted millimeter-wave radar, due to the ever-changing road environment, the signal is often submerged in noise, so it is difficult to identify the real signal from the noise, and there are often missed or false alarms. Therefore, some methods are needed to remove the influence of noise to improve the stability and accuracy of the radar system under complex road conditions.

4. When the vehicle is driving on the real road, the radar installed in front of the vehicle will identify all the targets within the detection range, including the interference information of lane vehicles, guardrails, green plants, etc. Due to the performance limitations of the radar itself, the actual target will be lost in a short time, so the data returned by the radar cannot be directly used for effective target screening. Therefore, an effective tracking algorithm is needed to continuously track the target.

SUMMARY OF THE INVENTION

In order to overcome the deficiencies of the prior art, one of the objectives of the present invention is to provide a method for improving the speed of target object recognition.

Another object of the present invention is to provide an electronic device.

A third object of the present invention is to provide a computer-readable storage medium.

One of the objects of the present invention adopts the following technical scheme to realize:

A method for improving target recognition speed, comprising the following steps:

Mixing step: after receiving the echo signal, mix the echo signal with the local oscillator signal to obtain the intermediate frequency signal;

Sampling step: digitally process the intermediate frequency signal through the sampling module;

Clutter cancellation step: perform clutter cancellation processing on the digitally processed intermediate frequency signal;

Windowing step: windowing the intermediate frequency signal processed by clutter cancellation;

The step of obtaining the difference frequency: the intermediate frequency signal after the windowing process is processed through the fast Fourier transform and the spectral refinement algorithm to obtain the difference frequency frequency;

Calculation step: calculate the speed and distance of the corresponding target according to the target calculation formula; the target calculation formula is:

Among them, V _f is the speed of the target object, c is the speed of light, f ₀ is the center frequency of the transmitted wave, f ₊ is the positive difference frequency value, f _- is the negative difference frequency value, T is the modulation signal period, B is the modulation bandwidth, R is the distance to the target.

Further, in the step of obtaining the difference frequency, the spectrum refinement algorithm is the CZT algorithm, and the step of obtaining the difference frequency specifically includes the following substeps:

Fourier transform step: perform N-point fast Fourier transform on the intermediate frequency signal after windowing, and find the maximum point P of the spectral line amplitude;

Frequency calculation steps: Calculate the frequency values f1 and f2 of the two points (P-1) and (P+1).

Calculation steps of beat frequency: Do M-point CZT transformation operation in the interval from f1 to f2, find the point P1 with the maximum amplitude of the spectrum line, and calculate the frequency value of this point, which is the beat frequency.

Further, in the Fourier transform step: the intermediate frequency signal processed by the fast Fourier transform is detected by the horizontal false alarm detection module.

Further, the lateral false alarm detection in the Fourier transform step specifically includes the following sub-steps:

Select critical cell values by log-likelihood estimation function;

According to the critical unit value, determine whether the target is in the weak clutter region or in the strong clutter region. If it is in the weak clutter region, the SOCA-CFAR algorithm is used. If it is in the strong clutter region, the fast Fourier transform is used to detect The intermediate frequency signal of the GOCA-CFAR algorithm is selected to detect the intermediate frequency signal after the fast Fourier transform.

Further, in the step of calculating the difference frequency, the peak detection module is used to find the maximum value point P1 of the spectral line amplitude.

Further, the windowing function adopted in the windowing process is a Hanning window or a Hamming window, and the MTI algorithm is adopted for the clutter cancellation.

Further, a tracking step is included after the calculation step: the obtained speed and distance of the object are combined with the speed and acceleration of the vehicle itself through the tracking module to achieve continuous tracking of the target object in front of the vehicle.

Further, the tracking module adopts an extended Kalman filter algorithm.

The second purpose of the present invention adopts the following technical scheme to realize:

An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, when the processor executes the computer program, one of the objects described in any one of the objects of the present invention is realized. A method to improve the speed of target recognition.

The third purpose of the present invention adopts the following technical scheme to realize:

A computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements a method for improving the recognition speed of a target object according to any one of the objectives of the present invention.

Compared with the prior art, the beneficial effects of the present invention are:

The method for improving the recognition speed of the target object of the present invention processes the echo signal by adopting the fast Fourier transform and the spectrum refinement algorithm, so that the calculation amount of the signal processing is greatly reduced, and the calculation cost of the system is effectively reduced.

Description of drawings

1 is a flow chart of a method for improving target recognition speed according to Embodiment 1;

Fig. 2 is the waveform diagram of FMCW when static;

Fig. 3 is the waveform diagram of FMCW during exercise;

FIG. 4 is a structural diagram of a three-pulse canceller.

Detailed ways

The present invention will be further described below with reference to the accompanying drawings and specific embodiments. It should be noted that, on the premise of no conflict, the embodiments or technical features described below can be combined arbitrarily to form new embodiments. .

Example 1

Among the various modulation methods of vehicle-mounted millimeter wave radar, FMCW (frequency modulated continuous wave) radar modulates the frequency of the transmitted continuous wave, so as to measure the target information according to the acquired frequency difference, phase difference, etc., and its cost is relatively low. , the development is also relatively easy, and the measurement accuracy is high, so it has gradually become the first choice for the development of vehicle-mounted millimeter-wave radar, so this technology uses FMCW (frequency modulated continuous wave) as the radar modulation method.

The basic working principle of the vehicle-mounted millimeter-wave radar in FMCW mode: the general modulation signal is a triangular wave signal, the frequency changes of the transmitted signal and the received signal are shown in Figure 2 and Figure 3, and the shape of the reflected wave is the same. There is only a delay Δt in time, and the relationship between Δt and the target distance R is:

Among them: Δt: the time delay between the transmitted wave and the reflected wave; R: the target distance; c: the speed of light 3×10 ⁸ m/s.

According to the triangular relationship, we get:

Among them: Δf: the frequency difference between the transmitted signal and the reflected signal

T: Modulation signal period

B: modulation bandwidth

The target distance R is:

It can be concluded that the target distance R is proportional to the intermediate frequency Δf output by the radar front end.

When the target and the radar are not relatively stationary, that is, there is relative motion, the reflected signal contains a Doppler frequency shift fd caused by the relative motion of the target. When the moving target approaches the radar, as shown in Figure 2:

A difference frequency can be obtained at the rising edge and falling edge of the triangular wave respectively, which is expressed as:

f ₊ =Δf-f _d (4)

f-=Δf+f _d (5)

Where Δf is the intermediate frequency when the target is relatively stationary, f+ represents the difference frequency of the positive frequency modulation in the first half cycle, f- represents the difference frequency obtained by the negative frequency modulation in the second half cycle, and fd is the Doppler frequency shift of the target with relative motion , according to the Doppler effect:

Thus the value of velocity vr is:

Where: vr is the radial velocity of the target and the radar, f ₀ is the center frequency of the transmitted wave, which can be obtained from Equation 4 and Equation 5:

Substituting Equation 8 into Equation 3 and Equation 7 yields the expressions for speed and distance:

The sign of the velocity v _r is related to the relative movement direction, and v _r is a positive value when the target is close to the radar. v _r is negative when the target moves away from the radar. It can be seen that after the radar detects the object, the distance and speed of the object can be obtained through the value of the positive and negative difference frequencies, so that the vehicle can perform different tasks through the obtained information.

In order to accurately obtain the positive and negative difference frequency values and to track the front target when the vehicle is running normally, a complete signal processing system is established. The whole signal processing system consists of the following parts: sampling module, clutter cancellation module, Fourier transform module, CFAR (cross false alarm detection) module, peak detection module and tracking module.

As shown in Figure 1, the present embodiment provides a method for improving the speed of target recognition, comprising the following steps:

S1: After receiving the echo signal, mix the echo signal with the local oscillator signal to obtain the intermediate frequency signal;

S2: Digitally process the intermediate frequency signal through the sampling module; the sampling module uses the A/D sampling technology to digitally process the analog intermediate frequency signal, which is convenient for subsequent Fourier transform.

S3: Perform clutter cancellation processing on the digitally processed intermediate frequency signal; MTI algorithm is used for the clutter cancellation. Clutter cancellation uses the method of MTI (Moving Target Indication), which is an effective method to filter out clutter. It is the weighted summation of the same distance unit of multiple groups of pulse echoes to obtain the result; that is, the multi-input sum One output; equivalent to a high-pass filter used to suppress stationary targets and slow clutter. In the case of a single cancel MTI filter, the echo of the first transmit pulse is subtracted from the echo of the second transmit pulse, and stationary targets and slow clutter are removed while retaining the information of moving targets. Figure 4 shows a three-pulse MTI canceller, and the transfer function is H(z)=1-2z-1+z-2, and similar clutter components can be filtered out by the three-pulse MTI canceller.

S4: Perform windowing processing on the intermediate frequency signal after the clutter cancellation processing; the windowing function used in the windowing processing is Hanning window or Hamming window; before performing Fourier transform, the echo signal should be added window, in which the window function can be Hanning window or Hamming window, and different window functions can be selected for processing according to different situations to reduce spectrum leakage and truncation error and improve target detection performance.

S5: Process the intermediate frequency signal after the windowing process through the fast Fourier transform and the spectral thinning algorithm to obtain the difference frequency frequency; in step S5, the spectral thinning algorithm is the CZT algorithm, and the step S5 specifically includes The following substeps:

S51: Perform N-point fast Fourier transform on the intermediate frequency signal after the windowing process. The Fourier transform module uses FFT (fast Fourier transform) transform. FFT is a fast algorithm for discrete Fourier transform, which is based on discrete Fourier transform. The odd, even, imaginary and real characteristics of Fourier transform are obtained by improving the algorithm of discrete Fourier transform. The amount of calculation can be greatly simplified, and the clutter-cancelled signal is transformed from time domain to frequency domain through FFT transformation. The intermediate frequency signal processed by the fast Fourier transform is detected by the horizontal false alarm detection module. The horizontal false alarm detection in the step S51 specifically includes the following sub-steps:

Select critical cell values by log-likelihood estimation function;

According to the critical unit value, determine whether the target is in the weak clutter region or in the strong clutter region. If it is in the weak clutter region, the SOCA-CFAR algorithm is used. If it is in the strong clutter region, the fast Fourier transform is used to detect The intermediate frequency signal of the GOCA-CFAR algorithm is selected to detect the intermediate frequency signal after the fast Fourier transform. The CFAR (horizontal false alarm detection) module adopts an improved adaptive CFAR algorithm to estimate the statistical characteristics of the unit data to determine the relative relationship between the target and the clutter, so as to adaptively select different processing algorithms. A window consisting of N reference units, including the unit to be inspected, and the window spans two differently distributed clutter regions. The clutter edge is assumed to occur between samples M and M+1, let Represents the average of samples 1 to M forming the first clutter region the estimated value of , is the mean value of the M+1 th sample to the N th sample forming the second clutter region. The algorithm starts from M=1 Just the sample mean of unit 1, while calculating the sample mean of N-1 units When M=2,...,N-1 is taken, the above process is repeated. Therefore, for N-1 possible critical units, a pair of sample mean sequences are calculated respectively and

Next, select the most probable critical unit Mt value, and the maximum likelihood estimate of this critical point is the M value that maximizes the following log-likelihood estimation function:

Once the Mt value is found, it is also established whether the unit to be inspected is located in the weak clutter area or the strong clutter area. When the unit to be inspected is located in the weak clutter area, the SOCA-CFAR algorithm is used. If the detection unit is located in the strong clutter area, the GOCA-CFAR (unit average selection) algorithm is selected.

S52: Calculate the frequency values f1 and f2 of the two points (P-1) and (P+1);

S53: Perform M-point CZT transformation operation in the interval from f1 to f2, find the maximum point P1 of the spectral line amplitude through the peak detection module, and calculate the frequency value of this point, which is the difference frequency frequency. By searching for the spectral peak of the echo signal transformed to the frequency domain, after the work of the above-mentioned modules, the clutter is basically eliminated, the target information is retained, and then the frequency corresponding to the maximum peak point is found, which is what we need The frequency of the upper and lower difference frequencies of the target.

In the embodiment, in order to improve the accuracy and calculation speed of the signal processing system, the technique of spectral thinning is adopted in the Fourier transform, and the spectral thinning adopts the CZT algorithm, which operates together with the FFT. Perform N-point FFT operation on the difference frequency signal to find the peak point P with the largest spectrum, then calculate the frequencies of (P-1) and (P+1) two points, and then perform M-point CZT transformation on the spectrum between these two points. The operation refines the spectrum, and the frequency value corresponding to the peak point of the spectrum obtained after the local refinement of the spectrum is the difference frequency. The key to the FFT/CZT joint algorithm lies in the selection of the spectrum range, and the correctness of the frequency estimation can be ensured only when the appropriate selection is made. The FFT/CZT joint algorithm reflects a wavelet processing idea of partial amplification, which can not only improve the speed, but also obtain the accuracy.

For the N*M point sequence, the FFT operation is directly used, and the calculation amount is: (N*M)lg2(N*M). If the FFT/CZT joint algorithm is used, in order to achieve the same resolution, it is necessary to perform the N-point FFT operation and then the M-point CZT transform calculation. The total calculation amount is: Nlg2N+2(N+M)+(N+ M) lg2(N+M). For the same resolution, the computational complexity of using the FFT/CZT joint algorithm is much smaller than that of directly calculating the FFT, so the joint algorithm can improve the precision without increasing the computation time.

S6: Calculate the speed and distance of the corresponding target according to the target calculation formula; the target calculation formula is:

Among them, Vf is the speed of the target object, c is the speed of light, f0 is the center frequency of the transmitted wave, f+ is the positive difference frequency value, f- is the negative difference frequency value, T is the modulation signal period, B is the modulation bandwidth, and R is the target distance of things.

S7: The speed and distance of the object obtained by the tracking module are combined with the speed and acceleration of the vehicle itself to achieve continuous tracking of the target in front of the vehicle. The tracking module adopts the extended Kalman filter algorithm.

The tracking module adopts the method of extended Kalman filtering, which is a Kalman filtering algorithm suitable for nonlinear systems. The system equations of the linear system model are replaced by nonlinear system model equations in the extended Kalman filter algorithm. The nonlinear system is linearized by introducing the Jacobian matrix, and then Kalman filtering is used for correlation processing.

First, a system of discrete control process is introduced by combining the obtained speed and distance of the object with the equivalent value of the vehicle's own speed and acceleration. The system model can choose constant speed, constant acceleration or current statistical model, the system can be described by linear stochastic differential equation, and the system state equation is introduced:

X(k)=AX(k-1)+BU(k)+W(k)

Plus the measurement equation of the system: Z(k)=HX(k)+V(k)

The Kalman filter equation is as follows:

Current state prediction result: X(k|k-1)=AX(k-1|k-1)+B U(k)......(11)

The corresponding covariance of the current state prediction: P(k|k-1)=AP(k-1|k-1)A’+Q…………(12)

The optimal result in the current state: X(k|k)=X(k|k-1)+Kg(k)(Z(k)-H X(k|k-1))......(13)

Gain: Kg(k)=P(k|k-1)H'/(H P(k|k-1)H'+R)......(14)

The current state optimal corresponding covariance P(k|k)=(I-Kg(k)H)P(k|k-1)......(15)

By continuously updating the above formula, the object in front of the vehicle can be continuously tracked.

After processing by the above signal processing module, the obtained data can be connected to the vehicle system through CAN communication. After the vehicle receives the relevant information, it will perform braking or alarm processing, so that the vehicle can implement AEB (active emergency braking system), ACC (Adaptive Cruise), BSD (Blind Spot Monitoring) and other functions.

The process of the signal processing system is: after the radar receives the echo signal, it mixes with the local oscillator signal to obtain the intermediate frequency signal. The intermediate frequency signal is sampled by the sampling module and sent to the clutter canceller for clutter cancellation. The finished signal is transformed from the time domain to the frequency domain after passing through the Fourier transform module. In order to further filter out interference such as clutter noise, the signal transformed into the frequency domain needs to be processed by CFAR (transverse false alarm detection). After processing, interference such as clutter noise is basically filtered out, leaving only the target information, and then the required difference frequency frequency can be obtained through peak detection. Combined with Equation 9, the speed and distance of the detected object can be obtained. , by combining the obtained speed and distance of the object with the vehicle's own speed and acceleration, the object in front can be continuously tracked through the tracking module.

The present invention has the following advantages:

1. The FFT-CZT algorithm is adopted, which greatly reduces the calculation amount of signal processing and effectively reduces the calculation cost of the system.

2. The self-adaptive CFAR algorithm can adapt to various complex environments, so that the entire signal processing system has high accuracy and greatly improves the probability of missed alarms and false alarms during target detection.

3. Using the extended Kalman filter algorithm, the whole system can track the target accurately and has high stability.

4. The whole system has fast calculation speed, less resource consumption, and high accuracy of target recognition and tracking.

Embodiment 2

Embodiment 2 discloses an electronic device, the electronic device includes a processor, a memory, and a program, wherein one or more of the processors and the memory can be used, and the program is stored in the memory and configured to be executed by the processor, When the processor executes the program, the method for improving the recognition speed of the target object of the first embodiment is realized. The electronic device may be a series of electronic devices such as a mobile phone, a computer, a tablet computer, and the like.

Embodiment 3

The third embodiment discloses a computer-readable storage medium, the storage medium is used for storing a program, and when the program is executed by a processor, the method for improving the recognition speed of a target object according to the first embodiment is implemented.

Of course, a storage medium containing computer-executable instructions provided by an embodiment of the present invention, the computer-executable instructions of which are not limited to the above-mentioned method operations, and can also perform related operations in the methods provided by any embodiment of the present invention .

From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be realized by software and necessary general-purpose hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment . Based on such understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in a computer-readable storage medium, such as a floppy disk of a computer , read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), flash memory (FLASH), hard disk or CD, etc., including several instructions to make an electronic device (which can be a personal computer, A server, or a network device, etc.) executes the methods described in the various embodiments of the present invention.

It is worth noting that, in the above-mentioned embodiment based on the content update notification device, the included units and modules are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; , the specific names of the functional units are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present invention.

The above-mentioned embodiments are only preferred embodiments of the present invention, and cannot be used to limit the scope of protection of the present invention. Any insubstantial changes and substitutions made by those skilled in the art on the basis of the present invention belong to the scope of the present invention. Scope of protection claimed.

Claims (10)

1. a kind of method for improving object recognition speed, which comprises the following steps:

Frequency mixing stages: after receiving echo-signal, echo-signal is mixed with local oscillation signal to obtain intermediate-freuqncy signal；

Sampling step: digitized processing is carried out to intermediate-freuqncy signal by sampling module；

Clutter cancellation step: clutter cancellation processing is carried out to the intermediate-freuqncy signal for being digitized processing；

Adding window step: windowing process is carried out to the intermediate-freuqncy signal by clutter cancellation processing；

Difference frequency obtaining step: the intermediate-freuqncy signal after windowing process is carried out by Fast Fourier Transform (FFT) and frequency spectrum refinement algorithm Processing is to obtain beat frequency；

It calculates step: the speed and distance of corresponding object being calculated according to object calculation formula；The object calculates Formula are as follows:

Wherein, V_fFor object speed, c is the light velocity, f₀For the centre frequency of transmitted wave, f₊Be positive difference frequency value, f_-Be negative difference frequency value, T is the modulated signal period, and B is modulation bandwidth, and R is the distance to object.

2. a kind of method for improving object recognition speed as described in claim 1, which is characterized in that obtained in the difference frequency Among step, the frequency spectrum refinement algorithm is CZT algorithm, and the difference frequency obtaining step specifically includes following sub-step:

Fourier transformation step: the transformation of N point quick Fourier is done to the intermediate-freuqncy signal after windowing process, and searches spectral line amplitude most Big value point P；

Frequency calculates step: calculating the frequency values f1 and f2 of (P-1) and (P+1) two o'clock；

Difference frequency calculates step: doing M point CZT transform operation in f1 to the section f2, searches spectral line amplitude maximum of points P1, and calculate The frequency values of the point, the frequency values are beat frequency.

3. a kind of method for improving object recognition speed as claimed in claim 2, which is characterized in that walked in Fourier transformation In rapid: detected by horizontal false-alarm detection module through Fast Fourier Transform (FFT) treated intermediate-freuqncy signal.

4. a kind of method for improving object recognition speed as claimed in claim 3, which is characterized in that the Fourier transformation Horizontal false-alarm detection in step specifically includes following sub-step:

The critical element value is chosen by log-likelihood estimation function；

Judge that object is to be in strong clutter area in weak clutter area according to the critical element value, if it is in weak clutter Area then selects SOCA-CFAR algorithm, detects the intermediate-freuqncy signal through Fast Fourier Transform (FFT) if it is strong clutter area is in, then GOCA-CFAR algorithm is selected to detect the intermediate-freuqncy signal through Fast Fourier Transform (FFT).

5. a kind of method of raising object recognition speed as described in any one of claim 1-4, which is characterized in that The difference frequency calculates in step, and spectral line amplitude maximum of points P1 is searched by peak detection module.

6. a kind of method for improving object recognition speed as claimed in claim 5, which is characterized in that in the windowing process For the windowed function used for Hanning window or hamming window, the clutter cancellation uses MTI algorithm.

7. a kind of method for improving object recognition speed as claimed in claim 5, which is characterized in that after calculating step It further include tracking step: by tracking module by the speed of obtained object and distance and in conjunction with the speed and acceleration of vehicle itself Degree is to realize the lasting tracking to vehicle forward target.

8. a kind of method for improving object recognition speed as claimed in claim 7, which is characterized in that in the tracking module Track algorithm use expanded Kalman filtration algorithm.

9. a kind of electronic equipment including memory, processor and stores the meter that can be run on a memory and on a processor Calculation machine program, which is characterized in that the processor realizes any one of claim 1-8 institute when executing the computer program A kind of method for the raising object recognition speed stated.

10. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the computer program A kind of method of raising object recognition speed as described in claim 1-8 any one is realized when being executed by processor.