Accessing high frame rate radar data via a circular buffer

By combining a circular buffer and a data manager, the problem of wasted memory and processing resources in high frame rate radar data access is solved, achieving efficient multi-application data access and improving system performance.

CN117785506BActive Publication Date: 2026-11-17GOOGLE LLC
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311664389.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2017-09-21
Filing Date
2018-08-29
Publication Date
2026-11-17
Estimated Expiration
2038-08-29

AI Technical Summary

Technical Problem

Existing technologies require additional memory and processing resources when accessing high frame rate radar data, especially in real-time data access and multi-application environments, leading to resource waste and inefficiency.

Method used

A combination of circular buffers and a data manager is adopted. The circular buffer stores radar data frames, while the data manager monitors and manages data requests from multiple applications. It ensures that the application is notified to read the data frame after it corresponds to the request, thereby reducing memory requirements and processor resource consumption.

Benefits of technology

It enables multiple applications to efficiently access high frame rate radar data, reduces memory requirements and processor resource usage, and improves data access efficiency and system performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117785506B_ABST
    Figure CN117785506B_ABST
Patent Text Reader

Abstract

This application describes accessing high frame rate radar data via a circular buffer. In some embodiments, a radar sensor collects radar data about objects detected by a radar field and stores the data in a circular buffer. A data manager monitors the circular buffer and processes data requests from multiple applications. By using the described techniques and devices, the multiple applications can efficiently access the requested radar frame data from the circular buffer, thereby reducing memory requirements and processor resource usage associated with providing the requested data.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Case Analysis

[0002] This application is a divisional application of Chinese invention patent application 201880019295.3, filed on August 29, 2018. Technical Field

[0003] This application relates to accessing high frame rate radar data via a circular buffer. Background Technology

[0004] Applications utilizing high frame rate radar data are becoming increasingly common. For example, radar sensors can be used to detect attitude, map the environment, or improve the performance of non-radar sensors. The usefulness of high frame rate radar sensors creates environments where multiple applications require more and different types of radar data (e.g., raw or minimally processed radar data, digital in-phase and quadrature data, range Doppler data, etc.). Currently, to provide radar data from a single radar sensor to multiple applications, applications use time-sharing techniques to access the data, allowing each application to access the specific data it needs at predefined times. In other cases, each application has a dedicated radar sensor to provide the requested data. In either case, the radar sensor typically collects the data upon request from an application and stores it in memory locations accessible to one or more applications as needed. These techniques therefore require additional memory and / or sensors, and use additional processing resources to manage data requests. Furthermore, in some cases, applications (such as user interfaces) may need access to real-time radar data, which, in the case of time sharing, requires even more processing resources to manage requests for real-time data. Summary of the Invention

[0005] This paper describes a technique for accessing high frame rate radar data via a circular buffer, and a system capable of doing so. The technique provides a radar sensor, a circular buffer, and a data manager. The radar sensor writes high frame rate radar data (as radar data frames) to a circular buffer, which acts as a shared memory location for multiple applications that use the radar data frames. The data manager monitors the circular buffer, manages data requests from multiple applications, and determines whether a radar data frame stored in the circular buffer corresponds to the requested data. When a data frame corresponds to a request, the data manager can, for example, send a notification to the requesting application or otherwise cause the application to read the corresponding radar data frame, the notification including the memory address of the corresponding radar data frame. The application can then read the radar data frame before it is rewritten to the circular buffer. In this way, multiple applications can access radar data frames stored in a single memory location, reducing both memory requirements and processor resource usage.

[0006] This invention is provided to introduce a simplified concept regarding accessing high frame rate radar data via a cyclic buffer, which is further described below in detail. This invention is not intended to identify essential features of the claimed subject matter, nor is it intended to define the scope of the claimed subject matter. Attached Figure Description

[0007] Embodiments of techniques and systems for accessing high frame rate radar data via a cyclic buffer are described with reference to the accompanying drawings. The same numbers are used throughout the drawings to denote the same features and components:

[0008] Figure 1 The illustration shows an example environment in which techniques can be implemented to access high frame rate radar data via a circular buffer.

[0009] Figure 2 The diagram shows Figure 1 An example implementation of a computing device that can access high frame rate radar data via a circular buffer.

[0010] Figure 3 The illustration shows an example circular buffer that stores multiple radar data frames.

[0011] Figure 4 The illustration shows a sample data manager that can access the circular buffer.

[0012] Figure 5 The illustration shows an example method for accessing high frame rate radar data via a circular buffer.

[0013] Figure 6 The illustration shows the background of another example implementation of a circular buffer. Figure 5 Additional details on the method.

[0014] Figure 7 The illustration shows another example method for accessing high frame rate radar data via a circular buffer.

[0015] Figure 8 The illustration shows the background of the example process. Figure 7 Additional details on the method.

[0016] Figure 9 An example computing system is illustrated, which can implement techniques that enable access to high frame rate radar data via a circular buffer, or can realize these techniques within the example computing system. Detailed Implementation

[0017] Overview

[0018] This paper describes a technique for accessing high frame rate radar data via a circular buffer, and a device capable of accessing high frame rate radar data via a circular buffer. The technique provides a common memory location for radar data and a data manager that can handle data requests from multiple applications and access the data requested by each application.

[0019] Consider, for example, a system comprising multiple radar sensors collecting radar data at high frame rates and multiple applications with varying needs for using that data. In this example, one application might only need the radar data for a specific radar location (e.g., a specific combination of azimuth, elevation, and range). Another application might only need data about a non-moving object with a large radar cross-section. Yet another application might require radar data that provides minimum azimuth, elevation, range, and Doppler resolution for high-accuracy measurements. Yet another application might need targets that meet a predefined minimum signal-to-noise ratio to minimize false alarms and the effects of ambient clutter and noise.

[0020] Traditional technologies typically stipulate that individual radar sensors write their data to separate memories, and applications then search those memories for data that meets their needs. Because radar sensors continuously collect data at high frame rates, memory requirements increase rapidly. Furthermore, the large amount of data operations required by current technology, such as writing data to memory, consumes processor resources that could be used for other tasks. Moreover, applications must search and filter data to find those that meet their specific needs, further utilizing processor resources and slowing down data collection.

[0021] This paper compares conventional techniques for storing and accessing radar data with the system and technique described herein, which offer improvements in several aspects. For example, the circular buffer can be implemented as page-locked memory (e.g., pinned memory), which allows the radar sensor to write data to a fixed number of physical memory addresses. This reduces the processor resources required to write data and also increases transfer speed. Furthermore, because it is a circular buffer, the memory size is constant and can be set by the user, which reduces overall memory requirements. Additionally, the data manager reduces the processor resources required for applications to determine and read application-related data.

[0022] These are just a few examples of how the techniques and systems described herein can improve access to high frame rate radar data. Other examples and implementations of these techniques are described herein. This document now turns to an example setting, after which example apparatuses, methods, and components are described.

[0023] Example Environment

[0024] Figure 1 An example environment is illustrated where a technique capable of accessing high frame rate radar data via a circular buffer can be implemented. Example environment 100 includes a computing device 102 having an application 104 and a radar-based data collection system 106. The radar-based data collection system 106 represents the capability to wirelessly capture high frame rate radar data describing various characteristics of a target object 108. For example, the radar-based data collection system 106 can use radar signals 110 to wirelessly sense, detect, and identify the size, shape, position, velocity, and other characteristics of the target object 108. The target object 108 is a physical entity, and the radar-based data collection system 106 is collecting data about this entity. Therefore, the target object 108 can be a physical object or a posture. For example, the target object 108 can be a chair, a person, or a posture made by a person. The radar-based data collection system 106 includes a circular buffer 112 that can store high frame rate radar data as radar data frames 114. The circular buffer 112 is a memory accessible by the application 104 or other components of the computing device 102. The implementation and use of the radar-based data collection system 106, the circular buffer 112, and / or the radar data frame 114 may vary and are described throughout this document.

[0025] Application 104 can be any application that uses radar data captured by radar-based data collection system 106 to perform various operations. Radar signal 110 typically represents one or more radio frequency (RF) signals transmitted and received by radar-based data collection system 106. In some embodiments, radar-based data collection system 106 uses a single antenna pointed at target object 108 to emit a radar field or signal. In other embodiments, multiple radar signals are transmitted on respective antennas. When the transmitted signal reaches target object 108, at least a portion of the transmitted signal is reflected back to radar-based data collection system 106 and processed, as further described below. In this example environment, computing device 102 is illustrated as a mobile device; however, it should be understood that this is merely for discussion purposes, and other devices may be utilized without departing from the scope of the claimed subject matter.

[0026] Radar signal 110 may have any suitable combination of power, carrier frequency, burst periodicity, pulse width, modulation type, waveform, phase relationship, etc. Some or all of the corresponding signals transmitted in radar signal 110 may be distinguished from each other to create a specific diversity scheme. Example diversity schemes include: a time diversity scheme that transmits multiple versions of the same signal at different points in a timely manner; a frequency diversity scheme that uses several different frequency channels to transmit signals; or a spatial diversity scheme that transmits signals on different propagation paths. In some implementations, the configuration of radar signal 110 and how the reflected signals are processed by radar-based data collection system 106 can be dynamically configured, controlled, or influenced by a user of computing device 102 or by application 104.

[0027] The environments in which high frame rate radar data can be accessed via a circular buffer have been generally described; now, let's consider... Figure 2 , Figure 2 The diagram shows Figure 1 Example embodiment 200 of computing device 102. In example embodiment 200, computing device 102 includes a radar-based data collection system 106, the additional details of which are described throughout this document. In other embodiments, radar-based data collection system 106 may operate as a separate system communicatively connected to computing device 102.

[0028] The computing device 102 can be any of a variety of devices, such as a smartphone, tablet computer, laptop computer, desktop computer, or server. Specifically, the computing device 102 can be a mobile device. The computing device 102 includes one or more computer processors 202 and a computer-readable medium 204, which includes a memory medium and a storage medium. An operating system (not shown) and one or more applications 206 may be embodied as computer-readable instructions on the computer-readable medium 204, which may include references to... Figure 1 The described application 104 or reference Figure 1 Application 104 is implemented in a similar manner. Application 206 and / or the operating system can be executed by the computer processor 202 to implement various functions of the computing device 102.

[0029] Various non-restrictive examples of application 206 are provided in Figure 2 The examples shown are 206-1 to 206-4. Figure 2As shown, Example Application 206-1 is a gesture recognition application for an occluded gesture system, enabling a device, for example, placed in a handbag, to detect gestures outside the handbag. Example Application 206-2 is implemented as part of a radar-based gesture recognition system that provides a radar field (shown as a dashed cube) in which a user can interact with a computing device by making gestures. Example Application 206-3 is implemented as part of a medical diagnostic system that uses radar to measure physiological characteristics or assess abnormal body movements, such as facial spasms, which can help diagnose various medical conditions (e.g., symptoms of stroke or Parkinson's disease). The example applications also include a mapping application 206-4, which can be used to identify a three-dimensional contextual mapping of the space used for configuring and using the contextual awareness settings of computing device 102.

[0030] The computing device 102 may also include a network interface 208 and a display 210. The network interface 208 can transmit data via any of a variety of wired, wireless, or optical networks. For example, the network interface 208 can communicate via a local area network (LAN), wireless local area network (WLAN), personal area network (PAN), wide area network (WAN), intranet, internet, peer-to-peer network, point-to-point network, or mesh network. The display 210 may be integrated with or associated with the computing device 102 (e.g., as a separate monitor for a desktop computer). The display 210 may display information, data, status reports, or any of a variety of user interfaces that allow users to modify, control, or otherwise interact with the operation of the computing device 102.

[0031] In this example, the radar-based data collection system 106 of computing device 102 includes a circular buffer 112, a radar sensor 214, and a data manager 216. The circular buffer 112 can be implemented as a reference... Figure 1Alternatively, a circular buffer 112 or similar may be described herein. Components of the radar-based data collection system 106 may be integrated into a single device or operate as separate components communicatively coupled to each other. The radar-based data collection system 106 may collect and store radar data frames 114 from one or more radar data sources (such as radar sensor 214). The radar-based data collection system 106 may also enable access to the radar data frames 114 stored in the circular buffer 112 via one or more applications 206. For example, radar sensor 214 may write multiple radar data frames 114 into the circular buffer 112, which receives and stores multiple radar data frames 114 according to various embodiments. Radar sensor 214 typically detects targets wirelessly via the transmission and reception of RF or radar signals. Once stored in the circular buffer 112, data manager 216 can enable access to multiple radar data frames 114 via one or more applications 206, as described herein.

[0032] In some implementations, the circular buffer 112 is configured as a region or partition of random access memory (RAM) that can store multiple radar data frames 114. The circular buffer 112 may include radar data frames received from radar sensor 214 or multiple different radar sensors. The radar data frames may include any suitable type of radar data, such as digital in-phase and quadrature data (I / Q data) or range Doppler data. See reference... Figure 3 Additional details are described for multiple radar data frames 114.

[0033] Typically, a circular buffer (such as circular buffer 112) is a memory buffer of a pre-configured size (e.g., fixed size) that is written sequentially (circular buffers are also referred to as ring buffers). For example, in an example buffer with ten memory addresses, data is written sequentially starting from a first address (e.g., "1, 2, 3...8, 9, 10" or "9, 10, 1...6, 7, 8"). When all addresses have been written, the next data to be written is stored in the original first address, overwriting any data previously written at that location (in the previous example, the first addresses are "1" and "9"). Circular buffer 112 may be provided by the operating system or memory controller (not shown) of computing device 102, which manages RAM or other memory. For example, the operating system of computing device 102 may allocate a fixed area of ​​RAM as a circular buffer. Alternatively or additionally, the circular buffer may be provided by another device or service (such as a server or a cloud-based service).

[0034] The circular buffer 112 may be a fixed memory, specifically a page-locked memory, which cannot be paged out of physical memory and cannot be reclaimed / reallocated by the operating system under normal system operation. In some embodiments, the circular buffer 112 is or includes a multiport memory that allows multiple applications and / or devices to perform simultaneous read access. For example, a RAM region provided by a device or service to act as the circular buffer 112 may itself be a multiport memory. In other cases, radar data frames 114 may be transmitted to a separate multiport circular buffer for access by multiple applications and / or devices (e.g., parallel access).

[0035] Radar sensor 214 represents the function of wirelessly detecting targets via the transmission and reception of RF or radar signals. Radar sensor 214 can write multiple radar data frames 114 into memory, such as a circular buffer 112. Radar sensor 214 can be implemented as a system embedded in computing device 102 and / or a radar-enabled component, such as a system-on-a-chip (SoC) or an on-chip sensor. However, it should be noted that radar sensor 214 can be implemented in any other suitable manner. For example, radar sensor 214 can be implemented as: one or more integrated circuits (ICs), a processor with embedded processor instructions (or configured to access memory storing processor instructions), a hardware element with embedded firmware, a printed circuit board assembly with various hardware components, or any combination thereof. Here, radar sensor 214 includes a radar transmitting element 218, one or more antennas (multiple) 220, and a digital signal processor (DSP or digital signal processing unit) 222, which can be consistently used to wirelessly detect various types of targets in the environment of computing device 102.

[0036] Typically, radar transmitting element 218 is configured to provide a radar field. The radar field can be configured to at least partially reflect one or more target objects. In some cases, the target object may include the user of computing device 102 or other persons present in the environment of computing device 102. In other cases, the target object includes the user's physical attributes, such as hand movements, respiratory rate, or other physiological characteristics.

[0037] The generated radar field can be any of a variety of radiation fields, including wide field, narrow field, shaped field (e.g., hemispherical, cubic, sector, conical, or cylindrical), manipulated field, unmanipulated field, near-range field, or far-range field. Furthermore, radar transmitting element 218 can use continuous wave signals or pulsed Doppler signals and can use any of a variety of frequencies, update rates, pulse widths, pulse intervals (IPPs), transmit power, and modulations. The radar field provided by radar transmitting element 218 may be small in size (e.g., 0 or 1 mm to 1.5 m) or medium in size (e.g., 1 m to 30 m). It should be understood that these sizes are merely for discussion purposes, and any other suitable size or range of radar field can be used. For example, when the radar field has a medium size, radar sensor 214 can be configured to receive and process reflections of the radar field to provide large body posture based on reflections from human tissue caused by body, arm, or leg movements. In some aspects, the radar field can be configured to enable radar sensor 214 to detect smaller and more accurate postures, such as micro-postures.

[0038] Radar sensor 214 detects nearby targets by transmitting and receiving reflected radio waves, as described below regarding antenna 220. Radio waves are invisible and can be designed to penetrate various materials (e.g., wood, glass, plastic, textiles, or nylon) and reflect from other materials (such as human tissue and skin). Radar sensor 214 can also calculate the target's three-dimensional position and velocity, as described below regarding DSP 222.

[0039] Antennas (multiple) 220 transmit and receive RF signals from radar sensor 214. In some cases, radar transmitting element 218 is coupled to antenna 220 to transmit a radar field. As those skilled in the art will recognize, this is achieved by converting electrical signals into electromagnetic waves for transmission and converting electromagnetic waves back into electrical signals for reception. Radar sensor 214 may include one or an array of any suitable number of antennas in any suitable configuration. For example, any one of antennas 220 may be configured as a dipole antenna, parabolic antenna, helical antenna, planar array, inverted-F antenna, monopole antenna, etc. In some embodiments, antenna 220 is constructed or formed in a chip (e.g., as part of a SoC), while in other embodiments, antenna 220 is a separate component, metal, dielectric, hardware, etc., attached to or included within radar sensor 214.

[0040] In some embodiments of the radar sensor 214, the antenna 220 may be dedicated (e.g., a first antenna 220 may be pointed to transmit signals and a second antenna 220 may be pointed to receive signals). In other embodiments, the antenna 220 may be multi-purpose (e.g., a single antenna 220 may be pointed to both transmit and receive signals). Therefore, different combinations of the antenna 220 can be used, such as implementations utilizing two dedicated antennas 220 configured for transmission in combination with four dedicated antennas 220 configured for receiving, or implementations utilizing a single antenna 220 configured for both transmission and reception. The placement, size, and / or shape of the antenna 220 can be selected to enhance a particular transmission mode or diversity scheme, such as a mode or scheme designed to capture information about the environment, as further described herein.

[0041] Antennas 220 can be physically separated from each other by a distance that allows radar sensors 214 to transmit and receive signals directed at a target object simultaneously through different channels, different radio frequencies, and different distances. In some embodiments, antennas 220 can be spatially distributed to support triangulation techniques, while in other embodiments, antennas 220 can be placed side-by-side to support beamforming techniques. Although not shown, each antenna 220 can correspond to a corresponding transceiver path that physically routes and manages the output signals for transmission and the input signals for acquisition and analysis.

[0042] DSP 222 typically refers to a function used to perform operations related to digitally processing radar signals and generating radar data based on those signals. For example, DSP 222 can process radar signals using techniques such as digital beamforming, Doppler filtering, noise estimation, clutter cancellation, and target detection. Through these techniques, DSP 222 can generate radar data, including raw or minimally processed radar data, digital in-phase and quadrature data, range Doppler data, etc.

[0043] In some cases, the DSP 222 further processes radar data to provide radar characteristics characterizing the data. For example, the DSP 222 can determine the number of detected targets, the signal-to-noise ratio of these targets, and the characteristics of detected clutter (e.g., amplitude, Doppler frequency, range, azimuth, elevation). The DSP 222 can also describe target characteristics, position, or dynamics by measuring the target's range, azimuth, elevation, radial velocity, and / or radar cross-section. The DSP 222 can further calculate the target's three-dimensional position and velocity. The DSP 222 may also include tracking capabilities that predict the target's future position and velocity based on measurements. By using the target's predicted position and velocity, the DSP 222 can automatically determine future radiation pattern characteristics to increase the probability of target detection.

[0044] Furthermore, DSP 222 can be used to control the configuration of signals generated and transmitted by radar transmitting element 218 and / or antenna 220, such as configuring multiple signals to form a specific diversity or beamforming scheme. In some cases, DSP 222 receives input configuration parameters that control the transmission parameters of the RF signal (e.g., frequency and / or power level), such as via data manager 216. In turn, DSP 222 modifies the RF signal based on the input configuration parameters. Sometimes, the signal processing functions of DSP 222 are included in a library of signal processing functions or algorithms, which can also be accessed and / or configured via application 206 or application programming interface (API). DSP 222 can be implemented in hardware, software, firmware, or any combination thereof.

[0045] DSP 222 can write radar data to memory (such as a circular buffer 112) as multiple radar data frames 114. Radar data frames 114 are associated with time periods that begin with the transmission of a specific signal and end with the receipt of a return signal. Therefore, radar data frames 114 contain data collected on or based on a specific return signal, including raw or minimally processed data, such as I / Q and range Doppler data. DSP 222 can write radar data frames at various frame rates consistent with the rate of transmitting and receiving radar signals. For example, DSP 222 can write a new radar data frame every 100 microseconds or every 100 milliseconds. Such frame rates, from approximately 100 microseconds to 100 milliseconds, can be referred to as high frame rates for radar data frames, which may be suitable for capturing very fast movements, high levels of detail, or perfect detail in user gestures (e.g., minute gestures).

[0046] As described above, the circular buffer 112 can be fixed memory, such as a portion of RAM or other memory of the computing device 102. By using fixed memory, the DSP 222 is allowed to use the physical RAM address of the buffer used to write the radar data frame 114 instead of a virtual address. In turn, the physical address allows the DSP 222 to use Direct Memory Access (DMA) to write the radar data frame 114 to the circular buffer 112. The DMA operation of the fixed memory can be implemented by a memory controller (e.g., a DMA-enabled controller) or a memory manager that is separate from the processor of the computing device 102. Therefore, data write (or read) operations implemented via DMA consume fewer processor resources of the computing device 102 and / or the DSP 222, thereby freeing up the processor to handle other tasks and reducing the overall power consumption of the application.

[0047] In addition to radar data, DSP 222 can also write radar data frame 114, which also contains other information about the radar sensor and / or radar data. Figure 3 An example embodiment 302 of the circular buffer 112 is illustrated, which includes multiple radar data frames 304-1 to 304-N. A detailed view in 306 shows that each radar data frame 304 may include both a radar data portion 308 and a header data portion 310. The radar data portion 308 includes the radar data described herein (e.g., I / Q data, range Doppler data, or data related to target characteristics). The header data portion 310 may include any of various information about the radar data or the radar sensor that collected the data. For example, the header data portion 310 may include a timestamp, information about the radar sensor that collected the data (e.g., location, configuration), the type of radar signal (e.g., frequency, IPP, modulation, beamforming angle), one or more of the characteristics of the aforementioned radar data, the aforementioned input configuration parameters, or the type of radar data (e.g., I / Q data, range Doppler data, target characteristics).

[0048] return Figure 2 Data manager 216 represents the capability to access multiple radar data frames 114 through one or more applications. Data manager 216 can be implemented as a radar-enabled component of a system, subsystem, and / or embedded computing device 102, such as a system-on-a-chip (SoC). However, it should be noted that data manager 216 can be implemented in any other suitable manner or combination of components described herein. For example, data manager 216 can be implemented as one or more integrated circuits (ICs), a processor with embedded processor instructions (or configured to access memory storing processor instructions), a hardware element with embedded firmware, a printed circuit board assembly with various hardware components, or any combination thereof.

[0049] consider Figure 4 , Figure 4 An example implementation of a data manager 216 for a radar-based data collection system 106 is illustrated. Figure 4As shown, the radar-based data collection system 106 is separate from the computing device 102. In other embodiments, the radar-based data collection system 106 may be integrated with the computing device 102 to provide the functionality described herein in a single device. In example embodiment 400, the data manager 216 includes a processor 402, a memory 404, and a communication interface 406, which can be consistently used to enable multiple applications 206 to access radar data frames stored on the circular buffer 112. The processor 402 represents the functionality that enables the data manager 216 to receive data requests from multiple applications 206 utilizing radar data, process the data requests, and enable the applications 206 to access the requested data.

[0050] Memory 404 is a memory that the processor 402 and / or communication interface 406 can use to store information about data requests, access information about multiple applications 206, or for other purposes related to performing the functions of the data manager 216 described herein. Communication interface 406 allows communication between the data manager 216 and other components of the computing device 102 (including applications 206, network interface 208, and display 210). In some embodiments, communication interface 406 may also communicate via various wired, wireless, or optical networks 408 (in... Figure 4 The network 408 can transmit data using any of the following types (illustrated as a cloud): Local Area Network (LAN), Wireless Local Area Network (WLAN), Personal Area Network (PAN), Wide Area Network (WAN), Intranet, Internet, Peer-to-Peer Network, Point-to-Point Network, or Mesh Network. Network 408 can provide communication functionality between the radar-based data collection system 106 and the computing device 102. Network 408 can also host one or more functions of the radar-based data collection system 106 (e.g., by providing processor resources or memory allocation).

[0051] Example Method

[0052] Figure 5 An example method 500 for accessing high frame rate radar data via a circular buffer is described. Example method 500 is shown as a set of boxes specifying operations to be performed, but is not necessarily limited to the order or combination of operations shown for performing the respective boxes. Furthermore, any operation in one or more operations can be repeated, combined, rearranged, or linked to provide a variety of additional and / or alternative methods. References can be found in the following discussion sections. Figure 1 Example environment 100 and Figures 2 to 4 The entities and processes detailed herein are merely illustrative. This technology is not limited to the performance of one or more entities operating on a single device.

[0053] In step 502, the request to read radar data frames from the application is analyzed. This analysis can be performed by any of various devices (such as the data manager 216 described above). The request may include specific requirements for the requested radar data frame. For example, the request may include characteristics of the radar data frame. These characteristics may relate to various aspects of the data, including how the radar data frame was collected, such as the type of radar or the sampling rate. In other cases, the characteristics may be related to references... Figure 3 The request describes information in the header data portion 310 of the requested radar data frame or various attributes of the data itself (such as target range, target Doppler, or signal-to-noise ratio). The request may also include a request for the most recent radar data frame written to the circular buffer. Therefore, the request can be for any data frame with certain characteristics, or for the most recent radar data frame already written, or for the most recent radar data frame including characteristics, etc.

[0054] An analysis request may include any of the following steps, such as determining a time window for radar data frames, determining the radar data frame interval, or determining a set of consecutive radar data frames. A time window is the time interval during which an application needs radar data frames (e.g., an application may request radar data frames during a time window that begins at a specific time and lasts for 100 microseconds, 200 microseconds, or 300 milliseconds). Determining the time window allows the data manager 216 to determine which radar data frames are associated with the application's requests. A radar data frame interval is the time interval between radar data frames requested by the application. For example, even if new radar data frames may be available every millisecond (or faster), the application may request radar data frames every minute, every hour, or every 30 milliseconds.

[0055] In step 504, it is determined that the current radar data frame stored in the circular buffer corresponds to the radar data frame requested by the application to be read (this step may be referred to as "determining the correspondence"). This determination can be performed by any of a variety of devices (such as the data manager 216 described above). In some embodiments, determining the correspondence between the current radar data frame stored in the circular buffer and the radar data frame is performed after receiving an interrupt that indicates that the current radar data frame has been written to the circular buffer (e.g., circular buffer 112). For example, as part of the DMA write process, the radar sensor 214 may send an interrupt signal to the data manager 216 to notify the data manager 216 that a specific radar data frame has been written.

[0056] Determining the correspondence may include determining that all aspects of the current radar data frame correspond to the requested radar data frame, such as determining that the characteristics of the current radar data frame correspond to the characteristics of the requested radar data frame (as described above) or determining that the current radar data frame is the most recently written radar data frame to the circular buffer. Other aspects of determining the correspondence may include determining that the time of the current radar data frame is within the time window of the requested radar data frame, determining that the current radar data frame occurs within a radar data frame interval, or determining that the current radar data frame is one of a set of consecutive radar data frames.

[0057] Figure 6 Another example implementation 602 of the circular buffer 112 is illustrated, which includes current radar data frames 604-1 to 604-N and receives example application requests 606-1 to 606-5. In the example circular buffer 602, each current radar data frame 604 includes a reference... Figure 3 The radar data portion and header data portion are described. Further, the current radar data frame 604-1 is the oldest radar data frame, and the current radar data frame 604-N is the newest. Assume request 606-1 includes characteristics of the radar data frame. Data manager 216 can determine (e.g., based on information in the header data portion of radar data frame 604) that the current radar data frame 604-1 includes characteristics and thus determine that the current radar data frame 604-1 corresponds to radar data frame application request 606-1. Similarly, assuming request 606-2 includes a request for the latest radar data frame to be written to example circular buffer 602, data manager 216 can use information in the header data portion of radar data frame 604 to determine that the current radar data frame 604-N is the newest radar data frame and thus determine that the current radar data frame 604-N corresponds to the radar data frame requested in request 606-2.

[0058] continue Figure 6 For example, assuming Data Manager 216 has already analyzed the reference Figure 5 The example requests described are 606-3, 606-4, and 606-5. It is further assumed that the analysis of request 606-3 determined the time window of the requested radar data frames, the analysis of request 606-4 determined the radar data frame interval of the requested radar data frames, and the analysis of request 606-5 determined a set of consecutive radar data frames requested.

[0059] Data manager 216 can use information from the radar data portion and / or header data portion of radar data frame 604 to determine that the current radar data frame 604-6 is within a defined time window. For example, suppose the defined time window is an interval 608 extending from time T1 to time T2, and the current radar data frame 604-6 is simply the current radar data frame 604 within the window. Using this information, data manager 216 can determine that the current radar data frame 604-6 is within the time window and therefore corresponds to the radar data frame requested in request 606-3.

[0060] In a similar manner, data manager 216 can determine that the current radar data frames 604-1, 604-3, and 604-5 occur within a defined radar frame interval. For example, suppose the defined radar frame interval determined for request 606-4 is one minute and the current radar data frames 604-1 to 604-5 are written every 30 seconds. Using this information, data manager 216 can determine that the current radar data frames 604-1, 604-3, and 604-5 occur within a radar data interval (i.e., one minute apart) and therefore correspond to the radar data frames requested in request 606-4.

[0061] Data Manager 216 can also determine that the current radar data frame 604 is one of a set of consecutive radar data frames. For example, by using information in the radar data portion and / or header data portion of the current radar data frame 604, Data Manager 216 can determine that the current radar data frames 604-3, 604-4, and 604-5 are a set of consecutive radar data frames. Data Manager 216 can then use the determination of the consecutive group to determine that any one of the current radar data frames 604-3, 604-4, and 604-5 is a radar data frame in a determined consecutive group and therefore corresponds to the radar data frame requested in request 606-5.

[0062] Return now Figure 5In step 506, the application is made to read the current radar data frame stored in the circular buffer before the current radar data frame is rewritten. The application can read the current radar data frame using any of a variety of devices (such as the data manager 216 described above). For example, the data manager 216 can read the current radar data frame by providing the address of the current radar data frame to the application. The application can then read the radar data frame during normal operation. As mentioned above, however, the circular buffer (e.g., circular buffer 112) has a fixed size, and when data has been written to all addresses in the circular buffer, the next data element will be written to the address with the oldest data. In some implementations, the data manager 216 can therefore make the application read the current radar data frame by sending a hardware interrupt to the application, which forces the application to read the radar data frame. Instead of sending the address of the current radar data frame, a hardware interrupt can be sent as described herein.

[0063] Using the aforementioned technology, the radar-based data collection system 106 can receive requests from one or more applications to read radar data frames from a circular buffer memory. The radar-based data collection system 106 can determine which radar data frames in the stored radar data frames correspond to the radar data frames requested by the applications and cause the applications to read the requested radar data frames. In this way, the radar-based data collection system 106 can achieve synchronous real-time access to the radar data of applications that use radar data in their operations.

[0064] Figure 7 Another example method 700 for accessing high frame rate radar data via a circular buffer is illustrated. Example method 700 is shown as a set of boxes specifying operations to be performed, but is not necessarily limited to the order or combination of operations shown for performing the respective boxes. Furthermore, any operation in one or more operations can be repeated, combined, rearranged, or linked to provide a variety of additional and / or alternative methods. References can be found in the following discussion sections. Figure 1 Example environment 100 and Figures 2 to 6 The entities and processes detailed herein are merely illustrative. This technology is not limited to the performance of one or more entities operating on a single device.

[0065] In 702, multiple radar data frames stored in a circular buffer are monitored. These multiple radar data frames can be stored in a circular buffer (such as circular buffer 112) or in another memory. Monitoring can be performed by any of a variety of devices (such as data manager 216 described herein). For example, data manager 216 can monitor various aspects of the radar data frames, including those stored... Figure 3Information in either or both of the radar data section 308 and header data section 310 of the example circular buffer 112 described herein.

[0066] In step 704, a request to read radar data frames from the circular buffer is received from any one or more of the multiple applications. Continuing the example from step 702, data manager 216 receives a request from... Figure 2 The example application described in 206 is a read request from any of the applications.

[0067] In step 706, one of the multiple radar data frames stored in the circular buffer is determined to correspond to the read request. This determination can be performed by various devices (such as data manager 216). Additional details regarding the determination of the correspondence are provided in [reference needed]. Figure 8 To describe it.

[0068] In step 708, the requesting application is instructed to read a radar data frame, which is determined to correspond to the read request. The application reads the corresponding radar data frame before it is rewritten to the circular buffer. Steps 710 and 712 describe an example of how data manager 216 can enable the requesting application to read the corresponding radar data frame.

[0069] In 710, the data manager 216 sends a notification that the corresponding radar data frame can be read to the requesting application. The notification includes the address in the circular buffer of the corresponding radar data frame, which allows the requesting application to read the corresponding radar data frame during normal operation and thus enables the requesting application to read the corresponding radar data frame during normal operation.

[0070] In step 712, or alternatively as an alternative to step 710, data manager 216 sends an interrupt signal to the requesting application. The interrupt signal forces the application to suspend its current operation and read the corresponding radar frame before resuming other operations. (Regarding...) Figure 8 Describe additional details about the interrupt signal.

[0071] Figure 8 Additional details of method 700 are illustrated within the context of example process 800, which can be implemented to enable multiple applications to access multiple radar data frames. In example process 800, radar sensor 214 writes multiple radar data frames 114-1 to 114-N into circular buffer 112. Data manager 216 monitors the multiple radar data frames 114 stored in circular buffer 112. Data manager 216 can monitor the radar data portion and header data portion of radar data frames 114 (e.g., Figure 3Both radar data section 308 and header data section 310 are described herein. As described herein, radar sensor 214 can write radar data frame 114 to a circular buffer via DMA. Optionally, as part of the DMA write process, radar sensor 214 can send an interrupt signal to data manager 216 to warn data manager 216 that a specific radar data frame has been written.

[0072] Data manager 216 also receives requests to read radar data frames from any of the multiple applications 206. Data manager 216 then determines which of the multiple radar data frames 114 stored in circular buffer 112 corresponds to the request to read the radar data frame. Determining that a radar data frame in the stored radar data frames 114 corresponds to the requested radar data frame can be achieved using various methods, such as comparing the radar data frame request with the radar data portion 308 and / or header data portion 310 of radar data frame 114. In some cases, the data manager may receive the request before the radar data frame corresponding to the request is written. In these cases, the data manager may store the request (e.g., in reference...). Figure 4 The correspondence is determined after the requested radar data frame 114 is written (as described in memory 404).

[0073] Before the corresponding radar data frame 114 is rewritten by the radar sensor, the data manager 216 then prompts the requesting application 206 to read the corresponding radar data frame 114 stored in the circular buffer. The data manager 216 can also prompt the application 206 to read the corresponding radar data frame 114 by sending a notification that the requested radar data frame is in the circular buffer 112 at a specific address, allowing the application 206 to read the radar data frame 114 during normal operation. Alternatively, the data manager 216 can send an interrupt signal that forces the application 206 to read the radar data frame 114. The interrupt signal can replace or be used in conjunction with a notification. For example, the data manager 216 can send a notification and, if the application 206 does not read the radar data frame 114 within a threshold time, send a hardware interrupt to ensure that the application 206 reads the requested radar data frame 114 before it is rewritten into the circular buffer 112.

[0074] As described herein, the circular buffer 112 can be a multi-port memory that allows multiple applications and / or devices to access it simultaneously. This is because the DMA process can provide interrupts (in...). Figure 8 (shown as dashed lines) to warn data manager 216 that radar data frame 114 has been written, so data manager 216 can provide a real-time or near real-time response to data requests, even in the case of a synchronization request for a specific radar data frame 114.

[0075] In some implementations, data manager 216 may also receive another request from another application 206 to read another radar data frame 114. This other application 206 may process the radar data frame 114 in a different manner than the original application. For example, data manager 216 may receive a request from application 206-1 that can be used to detect an occluded pose, and then receive another request from application 206-4 that can be used to identify a three-dimensional context map of the space. By using a technique similar to that described above, data manager 216 may then determine that another radar data frame among the multiple radar data frames 114 stored in the circular buffer corresponds to another request (from application 206-4) and allow another application (application 206-4) to read the other radar data frame 114 stored in the circular buffer before the other radar data frame is overwritten. In some implementations, individual radar data frames 114 may be used by different applications and processed differently depending on the purpose of that application.

[0076] Example Application

[0077] The described technologies and devices can be paired with machine learning techniques to predict the orientation, motion, and position of a target object detected by a radar sensor using radar and location data. For example, a radar-based data collection system 106 can be used in conjunction with machine learning techniques to determine and predict the two-dimensional (2D) or three-dimensional (3D) position of a user's hand. Knowing the 3D (x,y,z) position of a user's hand is fundamental to many user interaction systems, such as touchscreens, computer mice, gesture recognition systems, and handwriting recognition systems. Radar-based techniques for determining the (x,y,z) position allow the user to provide input, such as handwriting gestures, anywhere within the sensor's range. The (x,y,z) coordinates determined by the radar sensor can be used by existing handwriting recognition systems, just as a user presses their finger or stylus onto a touchscreen.

[0078] In this example embodiment of the radar-based data collection system 106, the application requests radar data frames associated with a specific target object from the data manager 216. The application also requests data representing the physical location of the target object from a position sensor. The position sensor can be any one or a combination of various sensors, such as capacitive or photoelectric proximity sensors, or ultrasonic sensors.

[0079] The example application takes a sequence of paired data (S,P) as input, where S is radar data (from cyclic buffer 112) and P is data from a position sensor. The example application uses a machine learning model that can be trained on the (S,P) paired data to learn how a new input S can be transformed into the corresponding position P. Any of the various machine learning models used for sequence learning can be used, such as Hidden Markov Models or Recurrent Neural Networks.

[0080] In some implementations, S can be raw data from radar sensor 214. In others, S can be any of various processed data, such as early radar data (e.g., amplitude and phase information from radar-returned images) or minimally processed radar data (e.g., range Doppler data, micro Doppler data, or I / Q data). In some cases, P represents the absolute position of the target object in (x, y, z) coordinates. In others, P represents the relative position (x, y, z) corresponding to the movement between the current point and subsequent points.

[0081] Sequences (S, P) can be synchronized so that there is a direct mapping between each sensor output S and position P. In other cases, sequences (S, P) can only be partially synchronized. For example, when the sampling frequencies of S and P are different, the sequences may have different lengths, in which case multiple samples from one sequence correspond to one sample from another sequence. Furthermore, it may sometimes be necessary to predict gestures in a specific 2D (x, y) plane along the z-axis or excluded from a specific 2D (x, y) plane along the z-axis. Therefore, separate models can be trained for both (x, y) and (z) coordinates.

[0082] The described implementation can be used to train applications to use radar-based gesture recognition to calculate the (x,y) or (x,y,z) position of a user's hand. In this way, a user can interact with the computing device from a distance. For example, a user's handwriting can be recognized from a distance, allowing data (e.g., animations or signatures) to be entered without contact with the touchscreen. In another scenario, the technology can enable the user's hand to be recognized as a cursor, allowing the user to unlock additional functions using the cursor without having to use touch input.

[0083] Example computing system

[0084] Figure 9 The illustration shows the various components of an example computing system 900, which can be implemented with reference to previous examples. Figures 1 to 8Any type of client, server, and / or computing device described to implement access to high frame rate radar data via a circular buffer.

[0085] The computing system 900 includes a communication device 902 that enables wired and / or wireless communication of device data 904 (e.g., radar data, received data, data being received, data scheduled for broadcast, data packets, etc.). Device data 904 or other device content may include device configuration settings, media content stored on the device, and / or information associated with the device's user (e.g., the identity of a person within the radar field). Media content stored on the computing system 900 may include any type of audio, video, and / or image data. The computing system 900 includes one or more data inputs 906 through which any type of data, media content, and / or input can be received, such as human speech, interaction with the radar field, user-selectable input (explicit or implicit), messages, music, television media content, recorded video content, and any other type of audio, video, or image data received from any content or data source.

[0086] The computing system 900 also includes a communication interface 908, which can be implemented as any one or more of a serial and / or parallel interface, a wireless interface, a network interface of any type, or a modem, and can also be implemented as any other type of communication interface. The communication interface 908 provides a connection and / or communication link between the computing system 900 and a communication network through which other electronic, computing, and communication devices communicate data with the computing system 900.

[0087] The computing system 900 includes one or more processors 910 (e.g., any of a microprocessor, controller, etc.) capable of processing various computer-executable instructions to control the operation of the computing system 900 and implement techniques for accessing high frame rate radar data via a circular buffer or embodying such techniques. Alternatively or additionally, the computing system 900 may be implemented using any or a combination of hardware, firmware, or a fixed logic circuitry system implemented in conjunction with the processing and control circuitry typically identified in 912. Although not shown, the computing system 900 may include a system bus or data transmission system coupling the various components within the device. The system bus may include any or a combination of different bus architectures, such as a memory bus or memory controller, a peripheral device bus, a universal serial bus, and / or a processor or local bus utilizing any of these bus architectures.

[0088] The computing system 900 also includes a computer-readable medium 914, such as one or more memory devices supporting permanent and / or non-transitory data storage (i.e., only in contrast to signal transmission). Examples of such memory devices include random access memory (RAM), non-volatile memory (e.g., any one or more of read-only memory (ROM), flash memory, EPROM, EEPROM, etc.), and disk storage devices. The disk storage device can be implemented as any type of magnetic or optical storage device, such as a hard disk drive, a recordable and / or rewritable optical disc (CD), any type of digital versatile optical disc (DVD), etc. The computing system 900 may also include a mass storage media device (storage medium) 916.

[0089] Computer-readable medium 914 provides a data storage mechanism to store device data 904, as well as various device applications 918 and any other types of information and / or data relating to the operation of computing system 900. For example, operating system 920 may be maintained as a computer application having computer-readable medium 914 and executed on processor 910. Device application 918 may include device managers, such as any form of control application, software application, signal processing and control module, device-specific code, abstraction module, or gesture recognition module, etc. Device application 918 also includes system components, engines, or managers for accessing high frame rate radar data via a circular buffer, such as radar-based data collection system 106, including circular buffer 112, radar sensor 214, and data manager 216. Computing system 900 may also include one or more machine learning systems or have access to one or more machine learning systems.

[0090] in conclusion

[0091] While embodiments of techniques and apparatus for accessing high frame rate radar data via a cyclic buffer have been described with reference to specific features and / or methods, it is to be understood that the subject matter of the appended claims is not necessarily limited to the specific features or methods described. Rather, specific features and methods are disclosed as exemplary embodiments capable of accessing high frame rate radar data via a cyclic buffer.

Claims

1. An apparatus for accessing radar data, the apparatus comprising: A radar sensor configured to generate multiple radar data frames with corresponding times; A memory including a circular buffer configured to store the radar data frames; as well as A data manager, which is at least partially implemented in hardware and configured to: Monitor the radar data frames stored in the cyclic buffer; Receive requests from the application for radar data frames between the first and second times; The radar data frames stored in the circular buffer are determined to have a corresponding time between the first time and the second time; as well as Before the determined radar data frame is rewritten, the application is instructed to read the determined radar data frame from the circular buffer.

2. The apparatus according to claim 1, wherein, The radar sensor is further configured to write the radar data frame to the circular buffer at write intervals between 100 microseconds and 100 milliseconds.

3. The apparatus according to claim 1, wherein, The radar sensor is further configured to send an interrupt to the data manager in response to each radar data frame being written to the circular buffer.

4. The apparatus according to claim 1, wherein, Instructing the application to read the determined radar data frame includes: transferring the memory address corresponding to the determined radar data frame to the application.

5. The apparatus according to claim 1, wherein, The device includes a mobile device.

6. The apparatus according to claim 1, wherein, The determined radar data frame is the latest radar data frame written into the circular buffer, which allows the application to access the radar data frame in real time.

7. The apparatus according to claim 1, wherein, The radar sensor is further configured to use direct memory access to write the radar data frame into the circular buffer.

8. An apparatus for accessing radar data, comprising: A radar sensor configured to generate multiple radar data frames; A memory including a circular buffer configured to store the radar data frames; as well as A data manager, which is at least partially implemented in hardware and configured to: Monitor the radar data frames stored in the cyclic buffer; Receive requests from the application for one or more radar data frames; Determine that the radar data frame stored in the circular buffer corresponds to the requested radar data frame; as well as An interrupt is sent to the application to instruct it to read the determined radar data frame from the circular buffer before the determined radar data frame is rewritten.

9. The apparatus according to claim 8, wherein: The request includes the characteristics of the request; as well as Determining that the radar data frame stored in the circular buffer corresponds to the requested radar data frame includes: determining that the determined radar data frame contains the requested characteristics.

10. The apparatus according to claim 9, wherein, The requested characteristics include one or more of the sampling rate or the type of radar used.

11. The apparatus according to claim 9, wherein, The requested characteristics include one or more of the following: target range, target Doppler, or signal-to-noise ratio.

12. The apparatus according to claim 9, wherein, The requested feature is the latest radar data frame.

13. The apparatus according to claim 8, wherein, The data manager is further configured to transfer the memory address corresponding to the determined radar data frame to the application in conjunction with the interrupt.

14. An apparatus for accessing radar data, comprising: A radar sensor configured to generate multiple radar data frames with corresponding times; A memory including a circular buffer configured to store the radar data frames; as well as A data manager, which is at least partially implemented in hardware and configured to: Monitor the radar data frames stored in the cyclic buffer; Receive requests for radar data frames from the application at time intervals; Determine that the radar data frames stored in the cyclic buffer have a time corresponding to the time interval; as well as Before the determined radar data frame is rewritten, the application is instructed to read the determined radar data frame from the circular buffer.

15. The apparatus according to claim 14, wherein, The time interval is greater than the write interval of the radar sensor.

16. The apparatus according to claim 15, wherein: The write interval is between 100 microseconds and 100 milliseconds; and The time interval is greater than 1 second.

17. The apparatus according to claim 14, wherein, The device includes a mobile device.

18. The apparatus according to claim 14, wherein, Instructing the application to read the determined radar data frame includes: transferring the memory address corresponding to the determined radar data frame to the application.

19. The apparatus according to claim 14, wherein, The radar sensor is further configured to use direct memory access to write the radar data frame into the circular buffer.

20. The apparatus of claim 19, further comprising a memory controller configured to facilitate the direct memory access of the radar sensor.

21. A method performed by a computing device, the method comprising: The computing device receives multiple radar data frames with corresponding times. The computing device writes the radar data frame into a circular buffer; The computing device monitors the radar data frames in the circular buffer; The computing device receives a request from the application for radar data frames between the first and second times. The computing device determines that the radar data frames stored in the circular buffer have a corresponding time between the first time and the second time; as well as Before the determined radar data frame is rewritten, the computing device instructs the application to read the determined radar data frame from the circular buffer.

22. The method according to claim 21, wherein, The radar data frames are written to the circular buffer at write intervals between 100 microseconds and 100 milliseconds.

23. The method of claim 21, further comprising: The computing device receives an interrupt in response to each radar data frame in the radar data frames being written to the circular buffer.

24. The method according to claim 21, wherein, Instructing the application to read the determined radar data frame includes: transferring the memory address corresponding to the determined radar data frame to the application.

25. The method according to claim 21, wherein, The computing device is a mobile device.

26. The method according to claim 21, wherein, The determined radar data frame is the latest radar data frame that is written into the circular buffer, allowing the application to access the radar data frame in real time.

27. The method according to claim 21, wherein, The radar data frames are written to the circular buffer using direct memory access.

28. A method performed by a computing device, the method comprising: The computing device receives multiple radar data frames; The computing device writes the radar data frame into a circular buffer; The computing device monitors the radar data frames in the circular buffer; The computing device receives from the application a request for one or more radar data frames; The computing device determines that the radar data frame in the radar data frame in the circular buffer corresponds to the requested radar data frame; as well as The computing device sends an interrupt to the application, instructing the application to read the determined radar data frame from the circular buffer before the determined radar data frame is rewritten.

29. The method according to claim 28, wherein: The request includes the characteristics of the request; as well as Determining that the radar data frame stored in the circular buffer corresponds to the requested radar data frame includes: determining that the determined radar data frame contains the requested characteristics.

30. The method according to claim 29, wherein, The requested characteristics include one or more of the sampling rate or the type of radar used.

31. The method according to claim 29, wherein, The requested characteristics include one or more of the following: target range, target Doppler, or signal-to-noise ratio.

32. The method according to claim 29, wherein, The requested feature is the latest radar data frame.

33. The method of claim 28, further comprising: The interrupt will then transfer the memory address corresponding to the determined radar data frame to the application.

34. A method implemented by a computing device, the method comprising: The computing device receives multiple radar data frames with corresponding times. The computing device writes the radar data frame into a circular buffer; The computing device monitors the radar data frames in the circular buffer; The computing device receives requests for radar data frames from the application at time intervals; The computing device determines that the radar data frames in the cyclic buffer have a time corresponding to the time interval; as well as Before the determined radar data frame is rewritten, the computing device instructs the application to read the determined radar data frame from the circular buffer.

35. The method according to claim 34, wherein, The time interval is greater than the write interval for writing the radar data frame into the circular buffer.

36. The method of claim 35, wherein: The write interval is between 100 microseconds and 100 milliseconds; and The time interval is greater than 1 second.

37. The method of claim 34, wherein, The computing device is a mobile device.

38. The method according to claim 34, wherein, Instructing the application to read the determined radar data frame includes: transferring the memory address corresponding to the determined radar data frame to the application.

39. The method according to claim 34, wherein, The radar data frames are written to the circular buffer by the radar sensor of the computing device using direct memory access.

40. The method according to claim 39, wherein, The direct memory access is facilitated by the memory controller of the computing device.

Citation Information

Patent Citations

  • Memory management method and device

    CN103761194A

  • Vehicular radar data processing algorithm verification system

    CN106443607A