CN105446934B - A kind of moving-target and CFAR detection system based on multi-core DSP - Google Patents
A kind of moving-target and CFAR detection system based on multi-core DSP Download PDFInfo
- Publication number
- CN105446934B CN105446934B CN201410401783.4A CN201410401783A CN105446934B CN 105446934 B CN105446934 B CN 105446934B CN 201410401783 A CN201410401783 A CN 201410401783A CN 105446934 B CN105446934 B CN 105446934B
- Authority
- CN
- China
- Prior art keywords
- core
- data
- radar signal
- processing
- dsp
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 72
- 238000004891 communication Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 16
- 238000004886 process control Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 claims 1
- 230000006870 function Effects 0.000 claims 1
- 238000007689 inspection Methods 0.000 claims 1
- 235000019800 disodium phosphate Nutrition 0.000 description 20
- 238000012546 transfer Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
Description
技术领域technical field
本发明属于雷达信号处理技术领域,具体涉一种基于多核DSP的动目标及恒虚警检测系统。The invention belongs to the technical field of radar signal processing, in particular to a multi-core DSP-based moving target and constant false alarm detection system.
背景技术Background technique
伴随着雷达技术以及以FPGA和DSP为代表的数字信号处理芯片的快速发展,雷达信号处理技术也得到了飞速发展。这不仅体现在灵活、复杂的雷达信号形式与雷达信号处理算法,也体现在高性能数字信号处理器件的使用与多种信号处理架构的出现。With the rapid development of radar technology and digital signal processing chips represented by FPGA and DSP, radar signal processing technology has also been developed rapidly. This is not only reflected in the flexible and complex radar signal form and radar signal processing algorithm, but also in the use of high-performance digital signal processing devices and the emergence of various signal processing architectures.
现在典型的雷达信号处理器一般采用单DSP信号处理平台、单纯基于FPGA或者FPGA+DSP架构。在专利CN101561501A中介绍了一种基于DSP的雷达目标跟踪识别器,其优势在于且无需另外采用专用芯片,有利于降低生产成本。但是遇到底层的信号预处理算法处理数据量大,但运算结构相对简单的情况,且对处理速度要求高的情况时,单DSP的架构明显没了优势。现在最常用的的是DSP+FPGA结构,具有两种处理器的优点,兼顾速度和灵活性,而且可以应用在不同雷达信号处理系统中,具有很强的通用性在《电子科技》的《一种雷达通用信号处理系统的实现与应用》一文中,介绍了一种基于一片FPGA(EP2S60F1020)加上四片DSP(TS201)的信号处理架构,该架构具有通用性好、处理能力强、数据通信速率高等优点。但是该信号处理结构具有芯片使用数目多、芯片之间通信复杂、PCB布局布线难度大等缺点。Now a typical radar signal processor generally adopts a single DSP signal processing platform, based solely on FPGA or FPGA+DSP architecture. In the patent CN101561501A, a DSP-based radar target tracking recognizer is introduced, which has the advantage of not needing to use additional dedicated chips, which is conducive to reducing production costs. However, when the underlying signal preprocessing algorithm processes a large amount of data, but the operation structure is relatively simple, and the processing speed is high, the single DSP architecture obviously loses its advantage. Now the most commonly used structure is the DSP+FPGA structure, which has the advantages of two processors, taking into account speed and flexibility, and can be applied in different radar signal processing systems, and has strong versatility. In the article "Realization and Application of a Radar General Signal Processing System", a signal processing architecture based on one FPGA (EP2S60F1020) plus four DSPs (TS201) is introduced. This architecture has good versatility, strong processing capability, and data communication Advantages of high speed. However, this signal processing structure has disadvantages such as a large number of chips used, complex communication between chips, and difficulty in PCB layout and wiring.
发明内容Contents of the invention
本发明的目的在于提供一种基于多核DSP的动目标及恒虚警检测系统,解决了单芯片架构以及多片DSP联合处理时存在的计算复杂度高、运算耗时、数据通信困难等问题,具有实时性好、结构简单、通信效率高、处理能力强等优点。The purpose of the present invention is to provide a multi-core DSP-based moving target and constant false alarm detection system, which solves the problems of high computational complexity, time-consuming calculation, and difficult data communication that exist in single-chip architecture and multi-chip DSP joint processing. It has the advantages of good real-time performance, simple structure, high communication efficiency, and strong processing ability.
为了解决上述技术问题,本发明提供一种基于多核DSP的动目标及恒虚警检测系统,所述多核DSP中包括一个主核和两个以上的从核,其中:In order to solve the above technical problems, the present invention provides a multi-core DSP-based moving target and constant false alarm detection system, wherein the multi-core DSP includes a master core and more than two slave cores, wherein:
主核负责系统处理雷达信号的过程控制、信号传递、数据搬移以及跟踪目标的信息生成;The main core is responsible for the process control of the system processing radar signals, signal transmission, data transfer and information generation of tracking targets;
在两个以上的从核中,单独开辟一个从核作为数据接收从核,数据接收从核用于响应外部中断并通过高速接口从FPGA接收雷达信号数据;其它从核作为数据处理从核,数据处理从核用于雷达信号数据的处理;Among more than two slave cores, one slave core is separately opened as a data receiving slave core, and the data receiving slave core is used to respond to external interrupts and receive radar signal data from the FPGA through a high-speed interface; other slave cores are used as data processing slave cores, data Processing slave cores for the processing of radar signal data;
数据接收从核在外部DDR中开辟两个存储区域用于存放接收的雷达信号数据,每个数据处理从核在自己核内开辟两个存储区域用于存放接收的雷达信号数据。The data receiving slave core opens up two storage areas in the external DDR for storing the received radar signal data, and each data processing slave core opens up two storage areas in its own core for storing the received radar signal data.
本发明与现有技术相比,其显著优点在于:(1)单独开辟一个核响应频繁的GPIO中断并从外部接收数据,从而提高CPU的执行效率;(2)避免多个核长时间对DDR总线访问,减少DDR总线访问冲突所带来的额外开销;(3)核间通信同时采用标志位、IPC中断、DMA数据搬移等技术,保证多核之间通信的可靠性以及快速性;(4)从核数据存储采用乒乓结构,减少了数据等待时间。Compared with the prior art, the present invention has significant advantages in that: (1) separately open up a core to respond to frequent GPIO interrupts and receive data from the outside, thereby improving the execution efficiency of the CPU; Bus access, reducing the additional overhead caused by DDR bus access conflicts; (3) Inter-core communication uses technologies such as flag bits, IPC interrupts, and DMA data transfer at the same time to ensure the reliability and speed of multi-core communication; (4) The slave core data storage adopts a ping-pong structure, which reduces the data waiting time.
附图说明Description of drawings
图1是本发明中主核的工作流程图。Fig. 1 is a working flow diagram of the main core in the present invention.
图2是本发明中数据接收从核的工作流程图。Fig. 2 is a working flow diagram of data receiving slave core in the present invention.
图3是本发明中信号处理从核的工作流程图。Fig. 3 is a working flowchart of the signal processing slave core in the present invention.
具体实施方式Detailed ways
本发明基于多核DSP的动目标检测(MTD)以及恒虚警检测(CFAR)系统,所述多核DSP中包括一个主核和两个以上的从核,其中:The present invention is based on the moving target detection (MTD) of multi-core DSP and the constant false alarm detection (CFAR) system, comprises a master core and more than two slave cores in the described multi-core DSP, wherein:
主核负责系统处理雷达信号的过程控制、信号传递、数据搬移以及跟踪目标的信息生成,跟踪目标的信息包括距离、速度等信息;The main core is responsible for the process control, signal transmission, data transfer and tracking target information generation of the system processing radar signals. The tracking target information includes distance, speed and other information;
在两个以上的从核中,单独开辟一个从核专门用于响应外部中断并通过高速接口(SRIO)从FPGA接收雷达信号数据,即单独开辟一个从核作为数据接收从核;其它从核用于雷达信号数据的处理,即在雷达信号数据中对跟踪目标进行动目标检测以及恒虚警检测,即其他从核作为信号处理从核;Among more than two slave cores, one slave core is dedicated to respond to external interrupts and receive radar signal data from the FPGA through the high-speed interface (SRIO), that is, a separate slave core is opened as a data receiving slave core; other slave cores use For the processing of radar signal data, that is, to perform moving target detection and constant false alarm detection on tracking targets in radar signal data, that is, other slave cores are used as signal processing slave cores;
数据接收从核在外部DDR(双倍速率同步动态随机存储器)中开辟了两个存储区域,全部信号处理从核在自己核内开辟两个存储区域,即包括第一存储区域和第二存储区域,以实现乒乓结构存储。The data receiving slave core has opened up two storage areas in the external DDR (Double Rate Synchronous Dynamic Random Access Memory), and all the signal processing slave cores have opened up two storage areas in its own core, including the first storage area and the second storage area , to realize ping-pong structure storage.
实施例Example
在多核DSP中选用七个核构建本发明基于多核DSP的动目标及恒虚警检测系统,其中确定核0为主核,核1至核5作为处理雷达信号数据的信号处理从核,单独开辟核6作为响应外部中断并接收雷达信号数据的数据接收从核。Select seven cores in the multi-core DSP to build the multi-core DSP-based moving target and constant false alarm detection system of the present invention, wherein it is determined that core 0 is the main core, and cores 1 to 5 are used as signal processing slave cores for processing radar signal data, which are developed separately Core 6 acts as a data receiving slave core in response to an external interrupt and receives radar signal data.
结合图1,使用本发明在雷达信号数据中对跟踪目标进行动目标检测以及恒虚警检测的过程如下:In conjunction with Fig. 1, the process of using the present invention to carry out moving target detection and constant false alarm detection to tracking targets in radar signal data is as follows:
第一步,对主核和从核进行初始化。主核核0的初始化包括DSP系统时钟、DDR(双倍速率同步动态随机存储器)、IPC(核间通信)中断等配置;核1至核5的初始化包括核间通信标志位赋初值;核6的初始化包括SRIO初始化配置、GPIO(通用I/O端口)中断配置。核1至核6各个从核初始化完成之后将相应标志位拉高,核0检测到核1至核6各个从核初始化完成的标志位拉高之后进入到正常工作模式。The first step is to initialize the master core and slave core. The initialization of the main core core 0 includes configurations such as DSP system clock, DDR (Double Rate Synchronous Dynamic Random Access Memory), IPC (inter-core communication) interruption; the initialization of core 1 to core 5 includes initial value assignment of the inter-core communication flag bits; 6 initialization includes SRIO initialization configuration, GPIO (general purpose I/O port) interrupt configuration. After the initialization of each slave core of core 1 to core 6 is completed, the corresponding flag bit is pulled high, and the core 0 detects that the flag bit of each slave core initialization of core 1 to core 6 is pulled high and then enters the normal working mode.
第二步,FPGA每完成一波雷达信号数据接收后,均给数据接收从核核6发送一个GPIO上升沿中断信号,核6每收到一个中断信号后就在中断服务函数中进行一次SRIO读操作,读取雷达信号数据并存储在外部DDR中。In the second step, each time the FPGA completes a wave of radar signal data reception, it sends a GPIO rising edge interrupt signal to the data reception from core 6, and every time the core 6 receives an interrupt signal, it performs an SRIO read in the interrupt service function Operation, read radar signal data and store in external DDR.
核6读取并存储雷达信号数据的方法具体为:开始时核6一直在判断是否接收到来自FPGA的外部中断信号,当核6接收到第一个中断信号后,响应来自FPGA的外部中断,并通过SRIO接口从外部读取数据。核6通过当前接收数据的次数的奇偶来判断将读取的数据存储在第一存储区域或者第二存储区域。比如将读取的第一波雷达信号数据存储在外部DDR中的第一存储区域,当判断该波雷达信号数据存储完毕后将其标志位拉高,但此时核6不停止接收中断数据,继续读取下一波雷达信号数据并存储到外部DDR中的第二存储区域。如此循环实现乒乓结构存储。核6每波读取的雷达信号数据量的大小需要根据读取速率以及FPGA端存储资源来协定。数据接收从核核6的工作流程如图2所示。The method for core 6 to read and store radar signal data is as follows: at the beginning, core 6 has been judging whether to receive an external interrupt signal from FPGA, and when core 6 receives the first interrupt signal, it responds to the external interrupt from FPGA, And read data from the outside through the SRIO interface. The core 6 judges whether to store the read data in the first storage area or the second storage area according to the parity of the times of receiving data currently. For example, the first wave of radar signal data read is stored in the first storage area of the external DDR. When it is judged that the wave of radar signal data is stored, its flag is pulled high, but at this time the core 6 does not stop receiving interrupt data. Continue to read the next wave of radar signal data and store it in the second storage area in the external DDR. Such a cycle realizes the storage of the ping-pong structure. The amount of radar signal data read by core 6 for each wave needs to be negotiated according to the reading rate and the storage resources on the FPGA side. The workflow of receiving data from the core 6 is shown in FIG. 2 .
第三步,在进行步骤二的过程中,当主核核0检测到核6的标志位拉高之后,开始进行DMA(直接数据存储)数据搬移,即核0将核6存储在外部DDR中的雷达信号数据依次搬移到核1至核5每个数据处理从核的核内存储空间。具体过程为:核0先给核1至核5的核内存储空间的第一存储区域DMA雷达信号数据,然后再给每个数据处理从核的核内存储空间的第二存储区域DMA雷达信号数据,实现乒乓结构操作,主核核0在开始搬移雷达信号数据之后就一直等待核1至核5各个核在数据处理完成之后产生的IPC中断。当主核核0收到IPC中断后,判断IPC中断来自于核1至核5中哪一个核,并将下一波数据DMA给该核进行雷达数据处理。当主核核0检测到所有数据均被信号处理从核完成之后,根据各个信号处理从核返回的结果进行目标距离、速度等信息的确定。主核核0的工作流程图如图1所示。The third step, in the process of step two, when the main core core 0 detects that the flag bit of core 6 is pulled high, it starts to perform DMA (direct data storage) data transfer, that is, core 0 stores core 6 in the external DDR The radar signal data is sequentially moved to the core storage space of each data processing slave core from core 1 to core 5. The specific process is: core 0 first gives DMA radar signal data to the first storage area in the core storage space of core 1 to core 5, and then processes each data from the second storage area DMA radar signal in the core storage space of the core The data realizes the ping-pong structure operation. After the main core core 0 starts to move the radar signal data, it has been waiting for the IPC interrupt generated by each core from core 1 to core 5 after the data processing is completed. When the main core core 0 receives the IPC interrupt, it determines which core the IPC interrupt comes from from core 1 to core 5, and DMAs the next wave of data to the core for radar data processing. When the master core 0 detects that all the data has been processed by the slave core, it determines the target distance, speed and other information according to the results returned by each signal processing slave core. The working flow chart of the main core core 0 is shown in Figure 1.
考虑到核1至核5的核内存储空间资源有限,而且划分为两个存储区域做乒乓结构存储,因此当一波数据很大时,不可能将每波数据一次性全部DMA到每个数据处理从核;同时,考虑到核1至核5在做动目标检测和恒虚警检测时,各个距离单元之间是独立的,因此,核0在给数据处理从核DMA数据时,以距离单元为单位进行数据搬移。在本实施例中,核0每次只DMA给数据处理从核3个距离单元的数据,数据处理从核在对该3个距离单元的数据进行动目标检测和恒虚警检测处理后,给主核核0一个IPC(核间通信)中断,要求核0从DDR中继续DMA另外3个距离单元的数据。如此循环直至所有的数据从外部DDR中DMA到核1至核5。Considering that the core storage space resources of core 1 to core 5 are limited, and are divided into two storage areas for ping-pong structure storage, when a wave of data is large, it is impossible to DMA each wave of data to each data at one time Processing slave cores; at the same time, considering that core 1 to core 5 are doing target detection and constant false alarm detection, each distance unit is independent, therefore, when core 0 processes slave core DMA data for data, it uses distance Data is moved in units of units. In this embodiment, core 0 only DMAs the data of 3 distance units from the data processing slave core each time, and the data processing slave core performs moving target detection and constant false alarm detection processing on the data of the 3 distance units. The main core core 0 is interrupted by an IPC (inter-core communication), requiring core 0 to continue DMA data of another 3 distance units from the DDR. This loops until all the data is DMAed from the external DDR to core 1 to core 5.
第四步,数据处理从核的工作流程如图3所示。核1至核5每个数据处理从核收到主核核0DMA过来的数据之后,进行动目标检测和恒虚警检测处理。恒虚警检测处理采用单元平均恒虚警,在待检测点左右两侧各取一个保护单元,再在所取的左侧的保护单元的左测以及在所取的右侧的保护单元的右测取若干点作积累(所取点数与选择的虚警概率有关),生成检测门限后与信号比较,超过门限的值保留,小于门限的点数置为0,核1至核5每个信号处理从核将检测出的目标幅度最大值以及相应的位置信息返回到约定的共享存储空间。如果知道上次的雷达目标的速度信息,由于是做速度维的恒虚警,可以根据上一次的速度信息适当缩小速度单元恒虚警检测检测范围。In the fourth step, the workflow of the data processing slave core is shown in Figure 3. After each data processing of core 1 to core 5 receives the data from the main core core 0DMA from the core, it performs moving target detection and constant false alarm detection processing. The constant false alarm detection process adopts unit average constant false alarm, and one protection unit is taken on the left and right sides of the point to be detected, and then the left side of the taken protection unit on the left side and the right side of the taken right side protection unit are taken. Measure a number of points for accumulation (the number of points taken is related to the selected false alarm probability), generate a detection threshold and compare it with the signal, keep the value exceeding the threshold, set the points less than the threshold to 0, and process each signal from core 1 to core 5 The slave core returns the detected maximum value of the target amplitude and the corresponding position information to the agreed shared storage space. If you know the velocity information of the radar target last time, since the constant false alarm of the velocity dimension is used, the detection range of the velocity unit constant false alarm can be appropriately reduced according to the last velocity information.
第五步,主核核0将数据以距离单元为单位进行划分,则可以获得总的距离单元数目,然后将核1到核5每个从核需要处理的数据的距离单元数目分配给核1到核5每个从核,则可进一步获知核1到核5每个从核在处理出具过程中需要完成的DMA次数。当主核核0DMA数据给5个信号处理从核的次数都达到每个核各自对应的DMA次数之后,此时主核核0的数据搬移工作已经完成,等待5个从核处理完成后标志拉高。In the fifth step, the main core core 0 divides the data in units of distance units, then the total number of distance units can be obtained, and then the number of distance units of the data that each slave core needs to process from core 1 to core 5 is allocated to core 1 From core 5 to each slave core, you can further know the number of DMA times that each slave core from core 1 to core 5 needs to complete during the issuance process. When the number of DMA data from the main core core 0 to the 5 signal processing slave cores reaches the corresponding DMA times of each core, the data transfer work of the main core core 0 has been completed at this time, and the flag is pulled high after the processing of the 5 slave cores is completed. .
当数据处理从核处理完所有的数据之后,将各自的处理结果按核1到核5的排列顺序存储在指定的共享存储空间中,并将各自雷达信号处理完成的标志位拉高,主核核0检测到5个数据处理从核的标志位都拉高之后,从共享存储空间中读取每个核的处理结果,并进行跟踪目标的信息生成,包括目标的距离、速度等信息。After the data processing slave core has processed all the data, the respective processing results are stored in the designated shared storage space in the order of core 1 to core 5, and the respective radar signal processing completion flags are pulled high, the main core After core 0 detects that the flag bits of the five data processing slave cores are all pulled high, it reads the processing results of each core from the shared storage space, and generates tracking target information, including target distance, speed and other information.
为了说明本发明在计算速度上的优势,使用本发明方法,DSP选用TI公司型号为TMS320C6678的高性能8核DSP,数据由XILINX公司的型号为XC7K325T的FPGA通过SRIO传给DSP,距离单元取59个,每次中断接收59*32*2*4=15014个数据,256次中断组成一个CPI数据包进行处理,总数据量为59*8192*8。按59个距离单元分配到核1至核5,则核1至核4每个核分配得到12个距离单元数据,核5得到11个距离单元数据,按每次DMA 3个距离单元,则核1至核5均需要DMA 4次数据。在使用本发明方法进行处理,从TI的CCS软件中的CLOCK计时工具中可以看出只需要大约5.45ms。本发明还在上述实验环境下仅用一个核进行单核处理,通过CLOCK可以看出处理时间大约为28.67ms。通过比较,本发明相对于单核运算时间提高了5倍多,节约的时间主要来自于频繁中断数据的读取以及多核算法的实现。In order to illustrate the present invention's advantage in computing speed, use the inventive method, DSP selects the high-performance 8 core DSP of TMS320C6678 that the model of TI Company is selected for use by DSP, the data is passed to DSP by the FPGA of XC7K325T model of XILINX Company through SRIO, and distance unit gets 59 Each interrupt receives 59*32*2*4=15014 data, 256 interrupts form a CPI data packet for processing, and the total data volume is 59*8192*8. If 59 distance units are allocated to core 1 to core 5, each core from core 1 to core 4 will get 12 distance unit data, and core 5 will get 11 distance unit data. If DMA is 3 distance units each time, the core 1 to core 5 all need DMA data 4 times. When using the method of the present invention to process, it can be seen from the CLOCK timing tool in TI's CCS software that only about 5.45ms is needed. The present invention also uses only one core for single-core processing under the above-mentioned experimental environment, and it can be seen from the CLOCK that the processing time is about 28.67ms. By comparison, the present invention improves the computing time by more than 5 times compared with that of single-core, and the saved time mainly comes from the reading of frequently interrupted data and the realization of multi-core algorithms.
Claims (6)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410401783.4A CN105446934B (en) | 2014-08-14 | 2014-08-14 | A kind of moving-target and CFAR detection system based on multi-core DSP |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410401783.4A CN105446934B (en) | 2014-08-14 | 2014-08-14 | A kind of moving-target and CFAR detection system based on multi-core DSP |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105446934A CN105446934A (en) | 2016-03-30 |
CN105446934B true CN105446934B (en) | 2018-07-31 |
Family
ID=55557152
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410401783.4A Active CN105446934B (en) | 2014-08-14 | 2014-08-14 | A kind of moving-target and CFAR detection system based on multi-core DSP |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105446934B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107885585A (en) * | 2016-09-30 | 2018-04-06 | 罗伯特·博世有限公司 | A kind of dynamic task scheduling device in multinuclear electronic control unit |
CN107193230A (en) * | 2017-05-10 | 2017-09-22 | 合肥晟泰克汽车电子股份有限公司 | Car radar signal processing system and method |
CN109587484B (en) * | 2017-09-28 | 2021-04-27 | 北京航空航天大学 | Design method of multi-mode HEVC video encoder based on dual-chip DSP |
CN108717187A (en) * | 2018-05-23 | 2018-10-30 | 桂林电子科技大学 | Based on multinuclear digital signal processor through-wall radar motion target tracking imaging method |
CN109324995A (en) * | 2018-08-24 | 2019-02-12 | 江西洪都航空工业集团有限责任公司 | A method of configuration DSP initialization |
CN111830478B (en) * | 2020-07-08 | 2022-06-17 | 哈尔滨工程大学 | A FPGA Implementation Method of LFMCW Radar MTD Processing |
CN111858457B (en) * | 2020-07-15 | 2023-01-10 | 苏州浪潮智能科技有限公司 | Data processing method, device and system and FPGA |
CN113281709B (en) * | 2021-04-21 | 2022-08-02 | 中国海洋大学 | Radar performance evaluation method based on regional coupled forecast system |
CN113325398B (en) * | 2021-05-13 | 2024-08-23 | 英博超算(南京)科技有限公司 | Application method of multi-core communication system of ultrasonic radar |
CN114660548A (en) * | 2022-02-15 | 2022-06-24 | 西安电子科技大学 | Unmanned aerial vehicle carries radar signal processor and processing system |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101561501A (en) * | 2009-05-13 | 2009-10-21 | 天津理工大学 | Radar target tracking recognizer based on DSP |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8330650B2 (en) * | 2010-05-07 | 2012-12-11 | The United States Of America, As Represented By The Secretary Of The Army | Radar system and antenna with delay lines and method thereof |
-
2014
- 2014-08-14 CN CN201410401783.4A patent/CN105446934B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101561501A (en) * | 2009-05-13 | 2009-10-21 | 天津理工大学 | Radar target tracking recognizer based on DSP |
Non-Patent Citations (1)
Title |
---|
基于6678多核DSP的相位编码雷达信号处理;曹阳;《中国优秀硕士学位论文全文数据库信息科技辑》;20140715(第07期);第I136-591页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105446934A (en) | 2016-03-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105446934B (en) | A kind of moving-target and CFAR detection system based on multi-core DSP | |
US11656675B2 (en) | Application processor performing a dynamic voltage and frequency scaling operation, computing system including the same, and operation method thereof | |
CN104237852B (en) | For processing the methods, devices and systems of radar signal | |
CN110647803B (en) | A gesture recognition method, system and storage medium | |
JP2018534675A (en) | Task subgraph acceleration by remapping synchronization | |
CN111190735B (en) | On-chip CPU/GPU pipelining calculation method based on Linux and computer system | |
KR20220103931A (en) | Data transfer between memory and distributed compute arrays | |
CN102262608A (en) | Method and device for controlling read-write operation of processor core-based coprocessor | |
CN116893912A (en) | Inter-core communication method, system, device, equipment and medium for vehicle-mounted software | |
CN102253916B (en) | Double-end double-channel first in first out (FIFO) for synchronous-to-asynchronous conversion | |
CN111666254A (en) | Novel heterogeneous multiprocessor circuit system | |
CN105573947B (en) | A kind of SD/MMC card control methods based on APB buses | |
TWI594125B (en) | Cross-die interface snoop or global observation message ordering | |
CN106776390A (en) | Method for realizing memory access of multiple devices | |
US6647450B1 (en) | Multiprocessor computer systems with command FIFO buffer at each target device | |
CN109801207A (en) | The image feature high speed detection and matching system of CPU-FPGA collaboration | |
CN106484640A (en) | A kind of high speed serialization user interface circuit based on FPGA and DSP | |
CN109710562A (en) | A configurable and high-speed FPGA configuration circuit and implementation method based on SELECTMAP | |
CN112035056B (en) | Parallel RAM access equipment and access method based on multiple computing units | |
CN113869494A (en) | High-level synthesis based neural network convolution FPGA embedded hardware accelerator | |
CN201465098U (en) | Multi-channel crossed DMA | |
JP2017182533A (en) | Synchronous processing unit, device, system and method | |
CN206892323U (en) | Sonar array signal processing platform | |
CN116660899B (en) | Near-field target ISAR imaging system and device based on FPGA+DSP | |
CN118094090B (en) | Mobile identification method, mobile identification device, beauty instrument and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |