Self-adaptive sensing system based on visual scene

Abstract

The utility model relates to a self-adaptive sensing system based on a visual scene, which comprises a visual sensor, a plurality of ultrasonic radars, a signal converter, a signal processing unit, a signal processing unit, a signal processing unit and an MCU (Microprogrammed Control Unit), the output end of the visual sensor is connected with the input end of the visual processor through the signal converter, and the visual processor is in interactive connection with the MCU. The output end of each ultrasonic radar is connected with the input end of the corresponding radar transceiver, the plurality of radar transceivers are interactively connected with the main radar transceiver, and the main radar transceiver is interactively connected with the MCU. According to the utility model, false alarm or missing alarm caused by different environments of the vehicle can be effectively reduced.

Description

Technical Field

[0001] The utility model relates to an adaptive sensing system based on a visual scene. Background Art

[0002] At present, with the development of intelligentization and networking in the automotive industry, especially the rise of assisted driving and autonomous driving, the automotive system has added more sensors to perceive the information outside the vehicle. The more common sensors are millimeter wave radar, camera, ultrasonic radar, etc. Different sensors have their own perception methods. For example, the camera extracts feature points through graphics or identifies different obstacles and different scenes through model training, and the ultrasonic radar measures the distance information through sound wave reflection. The perception of the camera will be affected by light, etc., and the perception of the ultrasonic radar is most affected by noise including ground noise at the same temperature. The working principle of the car's parking alarm is to distinguish between ground noise and real obstacles in the working environment. The distinction method uses a threshold to cut the signal-to-noise ratio of different obstacles. The echo intensity exceeding the threshold is released as obstacle information and the corresponding measured distance is output. The echo height below the threshold will be filtered. The noise sources that need to be filtered include environmental noise, mainly the noise generated by the ultrasonic radar transmitting to the ground. In the parking system, the user is prompted with the distance information of the vehicle from the obstacle, and a beep of different frequencies is issued according to different distance information to remind the user.

[0003] After searching, the patent: An ultrasonic adaptive threshold estimation method based on deep learning (CN202210190877.6) includes the following steps: in the model training stage, the ultrasonic radar is first installed and calibrated; secondly, the ultrasonic radar is used to collect data; the collected data is labeled again; then, an adaptive threshold prediction model based on deep learning is established; in the model reasoning stage: the installed and calibrated ultrasonic radar is used to collect data to obtain ultrasonic pulse signals, and after processing the ultrasonic pulse signals, the trained adaptive threshold prediction model based on deep learning is input to determine the scene in which the vehicle is located, thereby outputting the adaptive threshold of the ultrasonic radar in the scene.

[0004] Ultrasonic radar plays an important role in low-speed autonomous driving and assisted driving products. In low-speed autonomous driving systems, it is necessary to avoid radar detection misses and false alarms during LAEB (low-speed emergency braking). Therefore, it is extremely important to avoid radar false alarms and misses in different scenarios. There are currently two ways to adjust the sensitivity of ultrasonic radar. One is to use the parameters provided by the ultrasonic radar chip manufacturer, mainly including the signal-to-noise ratio threshold, to cut the obstacle echo heights with different signal-to-noise ratios and calibrate the detection capability of the current sensor. When the cutting threshold is relatively high, some low obstacles cannot be detected. When the calibration is more sensitive, some clutter will appear in open areas. The second is to filter some clutter through the ultrasonic sensing algorithm to reduce false alarms caused by sensitive detection. The ultrasonic sensing tracking algorithm can also be used to continuously report obstacles to avoid the temporary loss of the original echo due to insensitive detection. The two algorithms in the second method can make obstacle detection relatively stable. The robustness of the ultrasonic algorithm is based on the calibration results of the radar sensitivity of the first method. Detection performance that is too sensitive and slow beyond the algorithm range needs to be avoided.

[0005] At present, the calibration of ultrasonic radar parameters is to take a relatively reasonable intermediate threshold value after calibration in different scenarios before mass production of vehicles and write it into the parameters of the final mass production software. In order to achieve relative balance, the performance in different application scenarios is not optimal. The current threshold parameters are set higher for outdoor gravel, ecological brick and other roads to reduce false alarms caused by rough ground. However, in underground garages, the ground noise of epoxy pavement is relatively small, and there are many obstacles such as ice cream cones, stop signs, pedestrians, etc. The threshold of cutting outdoor roads will inevitably fail to detect the above obstacles with weak echo energy, resulting in the inability to have both.

[0006] In view of the above-mentioned defects, the designers have actively carried out research and innovation in order to create a new structure of adaptive sensing system based on visual scenes, making it more valuable for industrial use. Utility Model Content

[0007] In order to solve the above technical problems, the purpose of the utility model is to provide an adaptive sensing system based on visual scenes.

[0008] In order to achieve the above purpose, the utility model adopts the following technical solutions:

[0009] An adaptive sensing system based on a visual scene comprises a visual sensor, wherein the output end of the visual sensor is connected to the input end of a visual processor through a signal converter, the visual processor is interconnected with an MCU, and further comprises a plurality of ultrasonic radars, wherein the output end of each ultrasonic radar is connected to the input end of its corresponding radar transceiver, the plurality of radar transceivers are interconnected with a main radar transceiver, and the main radar transceiver is interconnected with the MCU.

[0010] Preferably, in the adaptive sensing system based on visual scenes, the visual sensor is a surround-view camera.

[0011] Preferably, in the adaptive sensing system based on visual scenes, the radar transceiver adopts an E524.17 USS chip, and the master radar transceiver adopts an E521.42Master chip.

[0012] Preferably, in the adaptive sensing system based on visual scenes, the visual processor adopts a chip with model number TDA4 A72.

[0013] Preferably, in the adaptive sensing system based on visual scenes, the MCU adopts a chip model TDA4R5F.

[0014] By means of the above solution, the utility model has at least the following advantages:

[0015] The utility model can effectively reduce false alarms or missed alarms caused by different environments in which vehicles are located, reduce the probability of collisions, especially in low-speed unmanned vehicles, and the frequent braking caused by false alarms, improve user experience, and reduce customer complaints caused by radar problems.

[0016] The above description is only an overview of the technical solution of the utility model. In order to more clearly understand the technical means of the utility model and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the utility model in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the utility model, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the utility model and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a structural block diagram of the utility model;

[0019] Figure 2 It is a circuit diagram of the radar transceiver of the utility model;

[0020] Figure 3 It is a circuit diagram of the main radar transceiver of the utility model;

[0021] Figure 4 It is a circuit diagram of the MCU of the utility model;

[0022] Figure 5 It is a circuit diagram of the visual processor of the utility model. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0024] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0025] The visual processor can identify or memorize the current environmental information based on the SLAM information through the visual sensor, including whether it is an underground garage, outdoor asphalt road and other different scenes, and output it to the main radar transceiver through SPI / ETH.

[0026] At the same time, ultrasonic radars are preset with different sensitivity parameters according to different scenarios before mass production, which has been mentioned in the background technology and will not be repeated here. For example, radar threshold parameter calibration is performed on smooth surfaces such as epoxy pavement and cement pavement, and low obstacles are tested to obtain ultrasonic radar parameters with high sensitivity. Radar threshold parameter calibration is performed on rough pavement such as gravel pavement and floor tile pavement. To ensure that low types are tested under the condition of removing clutter such as ground noise, as much as possible, these obstacles are covered, so as to obtain ultrasonic radar parameters with standard sensitivity.

[0027] Example

[0028] like Figures 1 to 5 As shown, an adaptive sensing system based on a visual scene includes a visual sensor 1, the output end of the visual sensor 1 is connected to the input end of a visual processor 3 through a signal converter 2, the visual processor 3 is interconnected with an MCU 4, and also includes a plurality of ultrasonic radars 5, the output end of each ultrasonic radar 5 is connected to the input end of its corresponding radar transceiver 6, the plurality of radar transceivers 6 are interconnected with a main radar transceiver 7, and the main radar transceiver 7 is interconnected with an MCU 4.

[0029] The visual sensor 1 described in the present invention is a surround view camera.

[0030] The radar transceiver 6 in the present invention adopts the E524.17 USS chip, and the master radar transceiver 7 adopts the E521.42Master chip.

[0031] The visual processor 3 in the present invention adopts a chip of model TDA4 A72, and the MCU4 adopts a chip of model TDA4 R5F.

[0032] The signal converter of the utility model adopts a chip of model MAX96712.

[0033] The ultrasonic radar in the utility model is provided with 12, namely radar transceiver 6 (see Figure 2 ) also need to use 12, the corresponding main radar transceiver (see Figure 3 ) Only two are needed to connect to the radar transceiver respectively.

[0034] The working principle of the utility model is as follows:

[0035] During specific operation, the ultrasonic radar is in a standard sensitivity state. After the image is transmitted to the visual processor through the visual sensor, the visual processor processes the image to obtain the corresponding scene information, updates the new scene information and retains it in the MCU. The new scene information in the MCU is transmitted to the main radar transceiver, and the main radar transceiver controls the radar transceiver to enable the ultrasonic radar to work in a new scene, thereby improving the applicability of the ultrasonic radar.

[0036] When the vehicle is in P gear or the speed is less than 15kph, the ultrasonic radar will update the corresponding scene to adapt each time the scene changes.

[0037] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0038] In the description of this application, it should be noted that the terms "vertical", "horizontal", "inside", "outside", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the product of the application is usually placed when in use. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0039] In addition, the terms "horizontal", "vertical" and the like do not mean that the components are required to be absolutely horizontal or vertical, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0040] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0041] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the technical principle of the present invention, and these improvements and modifications should also be regarded as within the protection scope of the present invention.

Claims

1. An adaptive sensing system based on a visual scene, comprising a visual sensor (1), characterized in that: The output end of the visual sensor (1) is connected to the input end of the visual processor (3) through a signal converter (2), and the visual processor (3) is interconnected with the MCU (4). The system also includes a plurality of ultrasonic radars (5), wherein the output end of each ultrasonic radar (5) is connected to the input end of its corresponding radar transceiver (6), and the plurality of radar transceivers (6) are interconnected with a main radar transceiver (7), and the main radar transceiver (7) is interconnected with the MCU (4).

2. The adaptive sensing system based on visual scene according to claim 1, characterized in that: The visual sensor (1) is a surround-view camera.

3. The adaptive sensing system based on visual scene according to claim 1, characterized in that: The radar transceiver (6) adopts an E524.17 USS chip, and the master radar transceiver (7) adopts an E521.42Master chip.

4. The adaptive sensing system based on visual scene according to claim 1, characterized in that: The visual processor (3) uses a chip of model TDA4 A72.

5. The adaptive sensing system based on visual scene according to claim 1, characterized in that: The MCU (4) uses a chip of model TDA4 R5F.

Images