An autonomous driving platform based on an imaging adjustment intelligent gateway

Abstract

The present invention provides an autonomous driving platform based on an imaging adjustment intelligent gateway, comprising: an in-vehicle camera and an intelligent gateway, wherein the in-vehicle camera is connected to the intelligent gateway through an in-vehicle Ethernet bus; the original Bayer format video data collected by the in-vehicle camera is transmitted to the intelligent gateway through the IEEE 1722 AVTP protocol; the intelligent gateway at least includes: an ISP chip; the ISP chip processes the original Bayer format data and outputs an image in the RGB spatial domain for storage in a cache for external devices to call; or the ISP chip feeds back to control the lens and image sensor of the in-vehicle camera and the logic circuit unit of the ISP chip itself according to the processing result of the Bayer format data. The technical solution provided by the present invention can adjust the imaging of the in-vehicle camera in the intelligent gateway, which is beneficial for different hosts to directly obtain video data.

Description

Technical Field

[0001] The present invention relates to the field of image acquisition of an autonomous driving platform, and particularly to an autonomous driving platform based on an imaging adjustment intelligent gateway. Background Art

[0002] An intelligent vehicle is an integrated system that combines functions such as environmental perception, planning and decision-making, and multi-level assisted driving. Currently, intelligent vehicles mainly provide the safety and comfort of the vehicle, as well as an excellent human-vehicle interaction interface. Functions such as in-vehicle entertainment, autonomous driving, and active braking have become standard features of intelligent vehicles. The realization of these functions is based on visual images. Images are collected through video, analyzed in real time, and autonomous driving, in-vehicle entertainment, active braking, etc. are performed according to the results of image analysis. However, in existing image acquisition systems, such as Figure 1 As shown, first, an in-vehicle camera using a traditional LVDS interface collects images, and then forms a MIPI signal. The MIPI image signal of the Sensor is converted into a proprietary serial protocol through an FPD-link Serializer connector, and then transmitted through an FPD_link coax or stp transmission medium. Then, at the receiving end, the De-Serializer connector in the FPD-link III hub is used to convert it into a MIPI signal, and then the MIPI signal is transmitted to the host of the platform for image processing, such as being processed by the host of an autonomous driving platform or a surround-view platform. This approach is essentially just an extension of MIPI while multiplexing control signals. When transmitting the video data of each camera, it is necessary to exclusively occupy a channel. For example, in an FPD-link III hub, each camera needs to be configured with a transmission channel, and the data transmission channels cannot be combined for transmission. Moreover, it is subject to the manufacturer. The protocols of the connectors of cameras produced by different manufacturers are proprietary and not interoperable. If a different camera is replaced, due to the incompatibility of the proprietary protocol, the connector needs to be replaced again, resulting in a high degree of coupling between hardware and software. Figure 2 In [reference], in the prior art, the ISP chip and the image processor are integrated in the camera. In addition, there are also in-vehicle cameras based on the LVDS transmission interface, such as Figure 3 , the in-vehicle camera does not have an ISP chip. The ISP chip is bound to the SOC processing chip and the MIPI signal can only be directly transmitted to the ISP chip. This makes it necessary to collect data through the SOC processing chip of the corresponding platform and it is not possible to directly collect video data through other means, restricting applications in various scenarios. For example, for surround-view in a vehicle, images need to be used. Either set up its own camera or go through the host of the autonomous driving platform. However, since the ISP chip of the autonomous driving platform is for the images required for autonomous driving and cannot meet the requirements of surround-view, it needs to be re-debugged. However, after debugging, the configuration will be changed and it cannot be adapted. Summary of the Invention

[0003] Based on the defects existing in the prior art, the present invention provides an autonomous driving platform based on an imaging adjustment intelligent gateway, including: an in-vehicle camera and an intelligent gateway, and the in-vehicle camera is connected to the intelligent gateway through an in-vehicle Ethernet bus;

[0004] The original Bayer format video data collected by the in-vehicle camera is transmitted to the intelligent gateway through the IEEE 1722 AVTP protocol;

[0005] The intelligent gateway at least includes: an ISP chip; the ISP chip processes the original Bayer format data and outputs an image in the RGB spatial domain, which is stored in a cache for external devices to call; or the ISP chip feeds back to control the lens and image sensor of the in-vehicle camera and the logic circuit unit of the ISP chip itself according to the processing result of the Bayer format data.

[0006] For an autonomous driving platform based on an imaging adjustment intelligent gateway, further optionally, when the number of in-vehicle camera connectors reserved in the intelligent gateway is less than the number of in-vehicle cameras, the original Bayer format data collected by the in-vehicle camera is first output to an external Ethernet switch, and then converges to the intelligent gateway through the external Ethernet switch.

[0007] For an autonomous driving platform based on an imaging adjustment intelligent gateway, further optionally, if an external device needs to call the video data of the in-vehicle camera, the external device establishes a communication connection based on the SOA service with the intelligent gateway, and the intelligent gateway processes the original Bayer format image through the ISP chip, converts it into the data format required by the corresponding external device, stores it in the cache and sends it to the corresponding external device;

[0008] The external device at least includes a host containing a SoC chip and an ARM chip.

[0009] For an autonomous driving platform based on an imaging adjustment intelligent gateway, further optionally, the ISP chip at least includes: an ISP logic circuit unit and firmware, and the firmware encapsulates an image adjustment processing algorithm in the Bayer format.

[0010] For an autonomous driving platform based on an imaging adjustment intelligent gateway, further optionally, the intelligent gateway further includes: a gateway body and a PCBA circuit board installed on the body, and the PCBA circuit board is provided with: an AVB / TSN Ethernet gateway, an ISP chip, an MCU chip, and a connector, wherein the MCU chip and the connector are respectively connected to the AVB / TSN Ethernet gateway.

[0011] An autonomous driving platform based on an imaging adjustment intelligent gateway. Further optionally, the in-vehicle Ethernet transmission bus between the in-vehicle Ethernet camera and the intelligent gateway includes shielded STP single-pair twisted pair with a transmission rate of 1G or 10G;

[0012] Or the 10G in-vehicle Ethernet transmission bus includes optical fibers, using optical fibers as the transmission medium.

[0013] An autonomous driving platform based on an imaging adjustment intelligent gateway. Further optionally, the connector includes at least one or more of an Ethernet PHY chip, a CAN chip, an RGMII chip, and a PCIE PHY chip;

[0014] The Ethernet PHY chip includes at least an electrical interface PHY chip or an optical interface PHY chip;

[0015] When using an electrical interface PHY chip, the transmission medium uses shielded twisted pair; when using an optical interface PHY chip, the transmission medium uses optical fibers as the transmission medium.

[0016] An autonomous driving platform based on an imaging adjustment intelligent gateway. Further optionally, the firmware includes at least three modules. The first module includes: an ISP control unit and ISP basic algorithms; the second module includes: AE automatic exposure, AWB automatic white balance, and AEB automatic exposure bracketing algorithms; the third module includes: image sensor algorithms;

[0017] The ISP control unit schedules the ISP basic algorithms and the second module, and at the same time calls the third module to register function callbacks with the ISP basic algorithms and the second module respectively to achieve differentiated sensor adaptation.

[0018] An autonomous driving platform based on an imaging adjustment intelligent gateway. Further optionally, the intelligent gateway further includes: an H.264 decoding chip, which is used to compress the video data to be transmitted and convert the compressed video data into an output conforming to the H.264 protocol.

[0019] An autonomous driving platform based on an imaging adjustment intelligent gateway. Further optionally, the AVB / TSN Ethernet protocol stack module or the AVB / TSN Ethernet gateway can parse data packets at the network layer; can convert data packets conforming to the AVB / TSN protocol into data packets in other standard protocol formats, or convert data packets in other protocols into the AVB / TSN protocol; or can parse and encapsulate data packets in the AVB / TSN protocol according to the format of the AVB / TSN protocol.

[0020] An autonomous driving platform based on an imaging adjustment intelligent gateway. Further optionally, the second external device calls video data through the intelligent gateway, including:

[0021] When the intelligent gateway receives a video signal from a second external device, obtain the priority of the second external device and the priority of the application scenario; obtain the priority of the first device and the priority of the application scenario;

[0022] Compare the priorities of the first device and the second external device, and select the imaging adjustment parameters of the ISP chip corresponding to the device with the higher priority and apply them to the imaging of the in-vehicle camera;

[0023] If the priorities of the first device and the second external device are the same, select the imaging adjustment of the ISP parameters corresponding to the device with the higher application scenario priority and apply it to the imaging of the in-vehicle camera;

[0024] Convert the data parsed by the ISP chip into the format required by the corresponding first device or second external device and then output it to the corresponding first device or second external device.

[0025] Beneficial effects:

[0026] Through the above technical solutions provided by the present invention, multiple hosts can directly call video data from the image processing gateway in a timely manner for decision-making and planning such as active braking, target recognition, and surround view imaging, and then take execution measures. Compared with traditional solutions, for example, after the surround view imaging host obtains an image, it needs to be obtained through the autonomous driving host. After adopting the technical solution of this application, it can be directly obtained from the image processing gateway. When the autonomous driving host is not required, the technical solution can still provide video images. And it can be easily switched, and at the same time, the image data is sent to multiple hosts.

[0027] In the technical solution provided by the present invention, it is possible to solve the problem of adapting the imaging adjustment parameters of the ISP chip in the in-vehicle camera for multiple different hosts.

[0028] In the technical solution provided by the present invention, it is possible to solve the problem of channel exclusivity. Description of the Drawings

[0029] The following drawings only illustrate and explain the present invention and do not limit the scope of the present invention.

[0030] Figure 1 It is a schematic structural diagram of a video signal acquisition scheme in the prior art;

[0031] Figure 2 It is a schematic structural diagram of the hardware of an in-vehicle camera in the prior art.

[0032] Figure 3 It is a schematic structural diagram of the hardware of the in-vehicle camera of the present invention.

[0033] Figure 4Schematic diagram of the automatic driving platform of the imaging adjustment intelligent gateway of the present invention.

[0034] Figure 5 Schematic diagram of the structure of the automatic driving platform of the imaging adjustment intelligent gateway with an external switch of the present invention.

[0035] Figure 6 Schematic diagram of the video stream processing structure of the ISP chip of the present invention.

[0036] Figure 7 Schematic diagram of the video acquisition method of the external device of the present invention. Detailed implementation manners

[0037] For a clearer understanding of the technical features, objectives, and effects of this article, the detailed implementation manners of the present invention are now described with reference to the accompanying drawings. The same reference numerals in the figures represent the same parts. To make the drawings concise, the relevant parts of the present invention are schematically shown in each figure, rather than representing their actual structures as products. Additionally, for the sake of simplicity and ease of understanding in some figures, for components with the same structure or function, only one of them is schematically illustrated, or only one of them is labeled.

[0038] Regarding the control system, functional modules, and application programs (APP), those skilled in the art know that they can adopt any appropriate form, which can be either hardware or software, and can be either discrete multiple functional modules or multiple functional units integrated onto one piece of hardware. In the simplest form, the control system can be a controller, such as a combinational logic controller, a microprogram controller, etc., as long as it can implement the operations described in this application. Of course, the control system can also be integrated as different modules onto one physical device, and these do not deviate from the basic principles and protection scope of the present invention.

[0039] In the present invention, "connection" can include direct connection, indirect connection, communication connection, and electrical connection, unless otherwise specifically stated.

[0040] The terms used in this article are only for the purpose of describing specific embodiments and are not intended to limit this disclosure. As used herein, the singular forms "a", "an", and "the" are also intended to include the plural forms, unless the context clearly dictates otherwise. It will also be understood that when used in the specification, the terms "include" and / or "comprise" mean the presence of the stated features, values, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, values, steps, operations, elements, components, and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the listed related items.

[0041] It should be understood that the term "vehicle" or "vehicular" or other similar terms used herein generally include motor vehicles, such as passenger cars including sport utility vehicles (SUVs), buses, trucks, various commercial vehicles, boats including various boats and ships, aircraft, etc., and include hybrid vehicles, electric vehicles, plug-in hybrid electric vehicles, hydrogen-powered vehicles, and other alternative fuel vehicles (e.g., fuels derived from non-petroleum energy sources). As mentioned herein, a hybrid vehicle is a vehicle having two or more power sources, such as a vehicle having both gasoline power and electric power.

[0042] The first embodiment of the present invention provides an autonomous driving platform based on an imaging adjustment intelligent gateway. Refer to Figures 3 to 7 , specifically including: an in-vehicle camera and an intelligent gateway. The in-vehicle camera is connected to the intelligent gateway through an in-vehicle Ethernet bus;

[0043] The original bayer format video data collected by the in-vehicle camera is transmitted to the intelligent gateway through the IEEE 1722 AVTP protocol;

[0044] The intelligent gateway at least includes: an ISP chip; the ISP chip processes the original bayer format data and outputs an image in the RGB spatial domain for storage in a cache for external devices to call; or the ISP chip feeds back to control the lens and image sensor of the in-vehicle camera and the logic circuit unit of the ISP chip itself according to the processing result of the bayer format data.

[0045] In the autonomous driving platform provided in this embodiment, the intelligent gateway includes an ISP chip that can adjust the imaging quality of the in-vehicle camera. Through the intelligent gateway, the original imaging quality of the in-vehicle camera can be controlled, that is, the imaging quality adjustment of the original Raw bayer format, rather than the image processing of the output three-channel primary colors after imaging adjustment. It enables the host of various platforms to conveniently call images and at the same time reduces hardware costs.

[0046] Specifically, as mentioned in the background art, in the image transmission process of the prior art autonomous driving platform, channels are exclusive and cannot be shared. When the number of cameras increases, corresponding hardware channels need to be added for transmission. To solve this problem, the following solutions are provided in this embodiment, specifically as follows:

[0047] When the number of in-vehicle camera connectors reserved in the intelligent gateway is less than the number of in-vehicle cameras, the original bayer format data collected by the in-vehicle cameras is first output to an external Ethernet switch, and then converges to the intelligent gateway through the external Ethernet switch;

[0048] The Ethernet switch uses the IEEE 1722 AVTP protocol for data transmission.

[0049] If an external device needs to call the video data of the in-vehicle camera, the external device establishes a communication connection based on SOA services with the intelligent gateway. The intelligent gateway processes the original Bayer format image through the ISP chip, converts it into the data format required by the corresponding external device, stores it in the cache, and sends it to the corresponding external device;

[0050] The external device at least includes a host containing a SoC chip and an ARM chip.

[0051] The ISP chip at least includes: an ISP logic circuit unit and firmware, and the firmware encapsulates an image adjustment processing algorithm in Bayer format.

[0052] See Figure 6 , after the lens of the in-vehicle camera projects the optical signal onto the photosensitive area of the image sensor, the sensor undergoes photoelectric conversion and sends the original image in Bayer format to the ISP chip. The ISP chip processes it through algorithms and outputs images in formats such as RGB, YUV, and YcrCb that match the target to the external device;

[0053] The ISP chip controls the ISP logic circuit unit through the firmware, thereby performing corresponding control on the lens and the sensor, and further completing functions such as automatic aperture, automatic exposure, and automatic white balance;

[0054] In addition to completing part of the algorithm processing, the ISP logic circuit unit can also count the real-time information of the current image. The firmware recalculates by obtaining the image statistical information of the ISP logic unit and feeds back to control the lens, the sensor, and the ISP logic circuit unit to achieve the purpose of automatically adjusting the image quality.

[0055] The firmware includes three modules,

[0056] The first module includes: an ISP control unit and ISP basic algorithms;

[0057] The second module includes: AE automatic exposure, AWB automatic white balance, and AEB automatic bracketing exposure algorithms;

[0058] The third module includes: image sensor algorithms.

[0059] The ISP control unit schedules the basic algorithms and the second module, and at the same time calls the third module to register function callbacks to the ISP basic algorithms and the second module respectively to achieve differentiated sensor adaptation.

[0060] Different sensors register control functions with the ISP algorithm library in the form of callback functions;

[0061] When the ISP control unit schedules the basic algorithm and the second module, it will obtain the initialization parameters through the callback function and control the sensor, such as adjusting the exposure time, analog gain, digital gain, controlling the lens to focus step by step or rotating the aperture, etc.

[0062] If an external device needs to call the video data of the vehicle-mounted camera, the external device establishes a communication connection based on the SOA service with the intelligent gateway. The intelligent gateway processes the original bayer format image through the ISP chip, converts it into the data format required by the corresponding external device, stores it in the cache, and sends it to the corresponding external device.

[0063] The external device at least includes a host containing an SoC chip and an ARM chip.

[0064] Specifically, the process of establishing a connection between the external device that needs to obtain video data and the intelligent gateway includes:

[0065] The client sends a request for obtaining a service to the server. After receiving the service request, the server determines whether to provide a service to the client according to the content of the service request. If the service is authorized, the server responds to the client and establishes a connection.

[0066] The client sends a request message, and the server processes the response after receiving the request.

[0067] When the event subscribed by the client to the server occurs or is updated, the server sends the updated content to the client.

[0068] The intelligent gateway further includes: a gateway body, a PCBA circuit board installed on the body. The PCBA circuit board is provided with: an AVB / TSN Ethernet gateway, an ISP chip, an MCU chip, an H.264 decoding chip, an MCU chip, and a connector. Among them, the H.264 decoding chip, the MCU chip, and the connector are respectively connected to the AVB / TSN Ethernet gateway.

[0069] The in-vehicle Ethernet transmission bus between the in-vehicle Ethernet camera and the intelligent gateway includes a shielded STP single-pair twisted pair with a transmission rate of 1G or 10G.

[0070] Or the 10G in-vehicle Ethernet transmission bus includes optical fibers, using optical fibers as the transmission medium.

[0071] The connector at least includes one or more of an Ethernet PHY chip, a CAN chip, an RGMII chip, and a PCIE PHY chip.

[0072] The PHY chip of the Ethernet at least includes an electrical interface PHY chip or an optical interface PHY chip.

[0073] When using a PHY chip with an electrical interface, the transmission medium is shielded twisted pair; when using a PHY chip with an optical interface, the transmission medium is optical fiber.

[0074] An H.264 decoding chip is used to compress the video data to be transmitted and convert the compressed video data into an output that conforms to the H.264 protocol.

[0075] The AVB / TSN Ethernet protocol stack module or the AVB / TSN Ethernet gateway can parse data packets at the network layer; can convert data packets that conform to the AVB / TSN protocol into data packets of other standard protocol formats, or convert data packets of other protocols into the AVB / TSN protocol; or can parse and encapsulate data packets of the AVB / TSN protocol in accordance with the format of the AVB / TSN protocol.

[0076] The AVB / TSN protocol at least includes: the IEEE1722 AVTP audio and video transmission protocol.

[0077] Or according to the use of the video data, such as in scenarios like ADAS assisted driving and autonomous driving, the following can be added to the AVB / TSN protocol stack: IEEE 802.1AS, Precision Clock Synchronization Protocol (gPTP); IEEE 802.1Qat: Stream Reservation Protocol (SRP); IEEE 802.1Qav: Forwarding and Queuing of Time-Sensitive Streams Protocol (FQTSS); IEEE 802.1BA: Audio Video Bridging System, used to define network profiles.

[0078] Through the above technical solutions provided by the present invention, multiple hosts can directly call video data from the image processing gateway in a timely manner for decision-making and planning such as active braking, target recognition, and surround view imaging, and thus take execution measures. Compared with traditional solutions, such as the surround view imaging host needing to obtain images through the autonomous driving host after obtaining the images. After adopting the technical solution of this application, it can directly obtain from the image processing gateway. When the autonomous driving host is not required, this technical solution can still provide video images. And it can be easily switched, and at the same time send image data to multiple hosts, reducing latency.

[0079] Specifically, since on-vehicle cameras are applicable to many scenarios, such as ADAS assisted driving, 360-degree surround view, and in-vehicle entertainment, the imaging quality requirements for on-vehicle cameras are different. In the prior art, cameras are usually added to the vehicle for specific application scenarios, and camera sharing cannot be achieved. In the technical solution provided in this embodiment, since multiple different hosts call on-vehicle cameras, but the application scenarios of each host may be the same or different, different application scenarios may lead to different imaging parameter adjustments of the ISP chip for the on-vehicle camera. Therefore, it is necessary to solve the technical problem of how to adapt the imaging parameters of the on-vehicle camera to external devices and application scenarios without affecting the use.

[0080] The specific solution is as follows:

[0081] Step S1: Call the corresponding ISP chip according to the application scenario to call the internal processing method to adjust the imaging parameters of the corresponding ID camera and store them;

[0082] Step S2: Set the priorities of external devices and application scenarios;

[0083] Specifically, the priority of external devices can be set by the user when calling. If not set, the system will automatically set the priority of external devices. For example, the priority of the autonomous driving host is default greater than the priority of the surround view system host. However, if the user is reversing at this time and sets the priority when obtaining the video, the priority can be increased, and after use, it will return to the default setting;

[0084] Therefore, when reversing, obviously the user does not turn on the autonomous driving mode, so it will not affect driving safety.

[0085] The second external device includes the device that is about to call the video data, but does not include the device that is currently calling the video data; the first device definition includes the device that is currently using the video data;

[0086] Step S3: When the intelligent gateway receives a video signal from the second external device, obtain the priority of the second external device and the priority of the application scenario;

[0087] Obtain the priority of the first device and the priority of the application scenario;

[0088] Step S4: First, judge the priorities of the first device and the second device

[0089] If the priority of the first device is greater than the priority of the second external device, then judge whether the required image formats of the second external device are the same. If the same, directly transmit the image data to the second external device;

[0090] If the priority of the first device is lower than that of the second external device, the first device that is currently calling the video data will be interrupted; the ISP chip will call the imaging parameters corresponding to the second external device to adjust the imaging of the camera and obtain an adapted image; and at the same time, the adapted image will be output to the second external device and the first device. Specifically, it should be noted that since the priority of the second device is high at this time, the imaging debugging parameters of the ISP chip will adopt those required by the second device, that is, the imaging parameters required by the second device will be given priority, and the image obtained by the first device at this time is adjusted with the imaging parameters required by the second device, but does not include image formats, such as RGB, YUV, YcrCb and other formats. Therefore, external devices may require different formats, such as the RGB format image required by the screen, but the surround view may require the YUV format image. At this time, the image format needs to be converted into the format required by the corresponding device before transmission.

[0091] Step S4: if the priority of the first device is equal to the priority of the second external device, the priority of the application scenario is determined. If the priorities are the same, the current imaging parameters are kept unchanged. Then, it is determined whether the image format required by the second external device is the same. If they are the same, the image data is directly transmitted to the second external device. Otherwise, the formats are converted and then transmitted. The video data is shared with the first device and the second external device at the same time.

[0092] If the application scenario priority of the first device is lower than that of the second external device, the first device currently calling the video data will be interrupted; the ISP chip will call the imaging parameters corresponding to the second external device to adjust the camera imaging and obtain an adapted image. At the same time, the adapted image will be output to the second external device and the first device.

[0093] The above is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment. It is clear to those skilled in the art that the form in the embodiment is not limited thereto, and the adjustable manner is not limited thereto. It is understood that other improvements and changes directly derived or associated with those skilled in the art without departing from the basic concept of the present invention should be considered to be included in the protection scope of the present invention.

Claims

1. An autonomous driving platform based on an imaging adjustment intelligent gateway, characterized in that, Including: A vehicle-mounted camera and an intelligent gateway, where the vehicle-mounted camera is connected to the intelligent gateway through a vehicle-mounted Ethernet bus; The original Bayer format video data collected by the vehicle-mounted camera is transmitted to the intelligent gateway through the IEEE 1722 AVTP protocol; The intelligent gateway at least includes: an ISP chip; the ISP chip processes the original Bayer format data and outputs an image in the RGB spatial domain, which is stored in a cache for external devices to call; or the ISP chip feeds back and controls the lens and image sensor of the vehicle-mounted camera and the logic circuit unit of the ISP chip itself according to the processing result of the Bayer format data; The feedback control of the ISP chip includes adjusting the imaging parameters of the vehicle-mounted camera by the ISP chip according to the application scenario; When the number of vehicle-mounted camera connectors reserved in the intelligent gateway is less than the number of vehicle-mounted cameras, the original Bayer format data collected by the vehicle-mounted camera is first output to an external Ethernet switch, and then aggregated to the intelligent gateway through the external Ethernet switch.

2. The autonomous driving platform based on an imaging adjustment intelligent gateway according to claim 1, wherein If an external device needs to call the video data of the vehicle-mounted camera, the external device establishes a communication connection based on the SOA service with the intelligent gateway. The intelligent gateway processes the original Bayer format image through the ISP chip, converts it into the data format required by the corresponding external device, stores it in the cache, and sends it to the corresponding external device; The external device at least includes a host containing a SoC chip and an ARM chip.

3. An autonomous driving platform based on an imaging adjustment intelligent gateway according to claim 1, characterized in that, The ISP chip at least includes: an ISP logic circuit unit and firmware, and the firmware encapsulates an image adjustment processing algorithm in the Bayer format.

4. An autonomous driving platform based on an imaging adjustment intelligent gateway according to claim 1, characterized in that The intelligent gateway further includes: a gateway body and a PCBA circuit board installed on the body. The PCBA circuit board is provided with: an AVB / TSN Ethernet gateway, an ISP chip, an MCU chip, and a connector. Among them, the MCU chip and the connector are respectively connected to the AVB / TSN Ethernet gateway.

5. An autonomous driving platform based on an imaging adjustment intelligent gateway as claimed in claim 1, characterized in that, The vehicle-mounted Ethernet transmission bus connecting the vehicle-mounted camera and the intelligent gateway includes a shielded STP single-pair twisted pair with a transmission rate of 1G or 10G; Or the 10G vehicle-mounted Ethernet transmission bus includes optical fibers, using optical fibers as the transmission medium.

6. The autonomous driving platform based on an imaging adjustment intelligent gateway according to claim 4, wherein The connector at least includes one or more of an Ethernet PHY chip, a CAN chip, an RGMII chip, and a PCIE PHY chip; The Ethernet PHY chip at least includes an electrical interface PHY chip or an optical interface PHY chip; When using an electrical interface PHY chip, the transmission medium uses shielded twisted pair; when using an optical interface PHY chip, the transmission medium uses optical fibers as the transmission medium.

7. The autonomous driving platform based on an imaging adjustment intelligent gateway according to claim 3, characterized in that The firmware at least includes three modules. The first module includes: an ISP control unit and an ISP basic algorithm; the second module includes: AE (Automatic Exposure), AWB (Automatic White Balance), and AEB (Automatic Exposure Bracketing) algorithms; the third module includes: an image sensor algorithm; The ISP control unit schedules the ISP basic algorithm and the second module, and at the same time calls the third module to register function callbacks to the ISP basic algorithm and the second module respectively to achieve differentiated sensor adaptation.

8. An autonomous driving platform based on an imaging adjustment intelligent gateway according to claim 1, characterized in that, The intelligent gateway further includes: an H.264 decoding chip, which is used to compress the video data to be transmitted, and convert the compressed video data into a format compliant with the H.264 protocol for output.

9. The autonomous driving platform based on an imaging adjustment intelligent gateway according to claim 4, characterized in that The AVB / TSN Ethernet protocol stack module or the AVB / TSN Ethernet gateway can parse data packets at the network layer; can convert data packets compliant with the AVB / TSN protocol into data packets in other standard protocol formats, or convert data packets in other protocols into the AVB / TSN protocol; or can parse and encapsulate data packets in the AVB / TSN protocol according to the format of the AVB / TSN protocol.

Images