Target object detection method and device, computer device, storage medium and product

Abstract

The application relates to a target detection method and device, computer equipment, a storage medium and a computer program product, which comprises the following steps: determining a target grouping number of grouping a plurality of channels of a multi-channel laser radar, grouping the plurality of channels until the grouping number reaches the target grouping number, obtaining a plurality of corresponding channel grouping sets, for each channel grouping set, sequentially detecting a target according to a detection time sequence of each channel group in the channel grouping set, obtaining a corresponding echo signal set, and comparing and obtaining the distance between the multi-channel laser radar and the target detected by each channel. For each grouping except the first grouping, compared with the first grouping, the detection time sequence of the channel and the channel included in the existing channel group change. The method can accurately identify the actual echo signal on each channel, and then obtain the actual distance value, thereby improving the target detection accuracy.

Description

Technical Field

[0001] This application relates to the field of lidar technology, and in particular to a target detection method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the development of LiDAR technology, its applications are becoming increasingly widespread, with the most extensive use being in autonomous vehicles. As the "eyes" of autonomous vehicles, LiDAR boasts superior detection accuracy compared to other sensors, enabling it to perceive the distance to objects around the vehicle. However, on actual roads, when a laser beam from one channel strikes a highly reflective target, crosstalk between channels causes signals from these same targets to also appear in other channels. This crosstalk from other channels manifests as multiple highly reflective targets in the point cloud image, leading to detection errors and potentially causing problems such as accidental braking during autonomous driving. Summary of the Invention

[0003] Therefore, it is necessary to provide a target object detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of target object detection in response to the above-mentioned technical problems.

[0004] Firstly, this application provides a target detection method applied to scenarios where detection is performed using a multi-channel lidar, the method comprising:

[0005] Determine the target grouping number for grouping the corresponding multiple channels of the multi-channel lidar;

[0006] The multiple channels are grouped until the target number of groupings is reached, thereby obtaining a corresponding set of multiple channel groups.

[0007] For each channel group set, the target object is detected sequentially through the channels in the corresponding channel group according to the detection timing of each channel group in the channel group set, thereby obtaining the corresponding echo signal set of the channel group set;

[0008] The distance between the multi-channel lidar and the target detected by each channel is obtained by comparing the sets of echo signals.

[0009] Specifically, for each remaining group other than the first group, a preset condition is met. The preset condition is that, compared with the first group, the detection timing of the channel and the channels included in the remaining group have changed.

[0010] In one embodiment, the step of determining the number of groupings for grouping the corresponding multiple channels of the multi-channel lidar includes:

[0011] Based on the scenario type, determine the number of groupings for the corresponding multiple channels of the multi-channel LiDAR; the scenario type is at least divided into static detection scenarios and dynamic detection scenarios, and the number of groupings for the dynamic detection scenario is less than or equal to the number of groupings for the static detection scenario.

[0012] In one embodiment, the step of determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type includes:

[0013] In the case of a static detection scenario, the number of groupings for multiple channels is determined based on the detection repetition frequency of the multi-channel lidar.

[0014] In the case of a dynamic detection scenario, the number of times the multiple channels are grouped is determined based on the relative movement speed between the multi-channel lidar and the target object.

[0015] In one embodiment, the detection sequence of the channel group is characterized by the order of detection time periods, and the detection time periods of different channel groups in the channel group set do not overlap.

[0016] In one embodiment, the step of comparing the echo signal sets to obtain the distance between the multi-channel lidar and the target detected by each channel includes:

[0017] Compare different sets of echo signals, and obtain the corresponding target echo signal for each channel based on the comparison results;

[0018] The distance between the multi-channel lidar and the target object detected by each channel is determined based on the corresponding target echo signal and echo duration of each channel.

[0019] In one embodiment, the step of comparing different sets of echo signals and obtaining the corresponding target echo signal for each channel based on the comparison results includes:

[0020] For each channel, obtain the echo signal subset of that channel in each echo signal set;

[0021] The intersection of each subset of echo signals corresponding to the channel is taken, and the intersection echo signal is used as the target echo signal corresponding to the channel.

[0022] In one embodiment, the step of comparing the echo signal sets to obtain the distance between the multi-channel lidar and the target detected by each channel includes:

[0023] For each echo signal set, the reference distance between the multi-channel lidar and the target detected by each channel is determined based on the corresponding echo signal and echo duration of each channel in the echo signal set, thereby obtaining the reference distance set corresponding to the echo signal set;

[0024] By comparing different sets of reference distances, the actual distance between the multi-channel lidar and the target object detected by each channel is determined based on the comparison results.

[0025] Secondly, this application also provides a target detection device, the device comprising:

[0026] The determination module is used to determine the number of target groupings for grouping the corresponding multiple channels of the multi-channel lidar;

[0027] The grouping module is used to group the multiple channels until the number of groupings reaches the target number of groupings, thereby obtaining a corresponding set of multiple channel groups;

[0028] The detection module is used to detect the target object sequentially through the channels in the corresponding channel group according to the detection timing of each channel group in the channel group set, and obtain the corresponding echo signal set of the channel group set.

[0029] The comparison module is used to compare each echo signal set to obtain the distance between the multi-channel lidar and the target detected by each channel; wherein, for each remaining group except the first group, a preset condition is met, the preset condition is that the detection timing of the channel and the channels included in the remaining group have changed compared with the first group.

[0030] Thirdly, this application also provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps of any one of the first aspects.

[0031] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps of any one of the first aspects.

[0032] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the method steps of any one of the first aspects.

[0033] The aforementioned target detection method, apparatus, computer equipment, storage medium, and computer program product predetermine the target number of groupings for the corresponding multiple channels of a multi-channel lidar. Multiple channels are grouped until the target number of groupings is reached, resulting in a set of corresponding channel groups. For each channel group set, the target object is detected sequentially through the channels of the corresponding channel group according to the detection timing sequence of each channel group. This yields a set of echo signals for the corresponding channel group set. Based on a comparison of each echo signal set, the distance between the multi-channel lidar and the target object detected by each channel is obtained. For each grouping except the first grouping, a preset condition is met: compared to the first grouping, the detection timing of the channels and the channels included in the channel groups have changed. This allows for accurate identification of the actual echo signals on each channel, thereby obtaining the actual distance value and improving the accuracy of target object detection. Attached Figure Description

[0034] Figure 1 This is a diagram illustrating the application environment of a target detection method in one embodiment;

[0035] Figure 2 This is a flowchart illustrating a target detection method in one embodiment;

[0036] Figure 3 This is a flowchart illustrating the steps for obtaining the distance to the target object in one embodiment;

[0037] Figure 4 This is a flowchart illustrating a target detection method in one embodiment;

[0038] Figure 5 This is a schematic diagram of a four-channel lidar detection system in one embodiment;

[0039] Figure 6 This is a schematic diagram of false detections in a four-channel lidar system in one embodiment;

[0040] Figure 7 This is a schematic diagram of false detections in a four-channel lidar system in one embodiment;

[0041] Figure 8 This is a structural block diagram of a target detection device in one embodiment;

[0042] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0044] The target object detection method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, the multi-channel lidar 102 communicates with the computer device 104 via a network. The multi-channel lidar 102 can be used independently to execute the target detection method of this application, or it can be used in conjunction with the computer device 104 to execute the target detection method of this application. Taking the multi-channel lidar 102 and the computer device 104 in conjunction as an example, the computer device 104 is used to determine the target number of groupings for the corresponding multiple channels of the multi-channel lidar 102, grouping the multiple channels until the target number of groupings is reached, obtaining the corresponding set of multiple channel groups. For each channel group set, the multi-channel lidar 102, according to the detection time sequence of each channel group in the channel group set, sequentially passes through the channels in the corresponding channel group to detect the target object, obtaining the corresponding echo signal set of the channel group set. The computer device 102 is also used to compare each echo signal set to obtain the distance between the multi-channel lidar and the target object detected by each channel. Specifically, for each subsequent grouping (excluding the first grouping), a preset condition is met. This preset condition is that, compared to the first grouping, the detection timing of the channels and the channels included in each subsequent grouping change. The multi-channel LiDAR 102 is a LiDAR with at least two detection channels. The computer device 104 can be a terminal, which can be, but is not limited to, various personal computers, laptops, etc.

[0045] In one embodiment, such as Figure 2 As shown, a target object detection method is provided, which is applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0046] S202: Determine the target grouping number for grouping the corresponding multiple channels of the multi-channel lidar.

[0047] In this context, the number of channels in a LiDAR refers to the number of scan lines. Each channel corresponds to one laser beam, and a multi-channel LiDAR refers to a LiDAR that contains at least two channels. In scenarios where computer equipment uses a multi-channel LiDAR for detection, the number of target groupings is determined based on the corresponding multiple channels of the multi-channel LiDAR.

[0048] Specifically, multi-channel LiDAR is used in both dynamic and static scenarios. In dynamic scenarios, the relative speed between the multi-channel LiDAR and the target is high. To ensure a complete scan of the target, the switching time between the multiple channels of the multi-channel LiDAR needs to be shorter. In static scenarios, the relative speed between the multi-channel LiDAR and the target is low, allowing for more channel switching. Therefore, the number of target groupings in static scenarios should be greater than in dynamic scenarios. In practical applications, the number of target groupings can be determined based on the scenario being detected by the multi-channel LiDAR, its detection repetition frequency, and other characteristics, combined with the practical experience of technical personnel. Generally, in static scenarios, the number of target groupings should be as high as possible.

[0049] S204: Group multiple channels until the target number of groupings is reached, and obtain the corresponding set of multiple channel groups.

[0050] The computer equipment groups multiple channels multiple times according to a pre-set target number of groupings until the target number of groupings is reached. For each grouping, a corresponding set of multiple channel groupings is obtained. For example, taking a four-channel LiDAR as an example, the four channels are labeled as channel 1, channel 2, channel 3, and channel 4. In the first grouping, channels 1 and 2 form the first channel group, and channels 3 and 4 form the second channel group. The first and second channel groups together constitute the first channel grouping set corresponding to the first grouping. In the second grouping, channels 1 and 3 form the third channel group, and channels 2 and 4 form the fourth channel group. The third and fourth channel groups together constitute the second channel grouping set corresponding to the second grouping, and so on, until the target number of groupings is reached, obtaining the corresponding set of multiple channel groupings.

[0051] In practical applications, taking a four-channel LiDAR as an example, the number of channels in each channel group can be different each time the grouping is performed. For example, in the first grouping, channels 1, 2, and 3 are channels in the first channel group, while channel 4 is a channel in the second channel group.

[0052] For each channel group set, there is a corresponding detection time sequence for the channel groups. For example, in the first channel group set, the first channel group is the group detected first, and the second channel group is the group detected later. In practical applications, in order to avoid redundant interference signals between the first channel group and the second channel group, the detection time period of the channel group detected later usually does not overlap with the detection time period of the channel group detected earlier.

[0053] S206: For each channel group set, the target object is detected sequentially through the channels in the corresponding channel group according to the detection timing of each channel group in the channel group set, so as to obtain the corresponding echo signal set of the channel group set.

[0054] Specifically, for each channel group set, the multi-channel LiDAR detects the target object sequentially through the channels of the corresponding channel group according to the detection timing sequence of each channel group. For example, for the first channel group set, the multi-channel LiDAR first detects the target object through channels 1 and 2 of the first channel group according to the detection timing sequence, obtaining the first echo signal group. Then, it detects the target object through channels 3 and 4 of the second channel group, obtaining the second echo signal group. The first echo signal group and the second echo signal group together constitute the first echo signal set corresponding to the first channel group set. And so on, for each channel group set, the multi-channel LiDAR obtains the echo signal set corresponding to the channel group set.

[0055] In some cases, because there are highly reflective targets, when a laser from one channel hits a highly reflective target, other channels will also receive the light signal. This will result in many signals on the current channel, making it impossible to distinguish the actual target. In this case, the multi-channel lidar will save all the echo signals received by the current channel.

[0056] S208: Based on the comparison of each echo signal set, the distance between the multi-channel lidar and the target detected by each channel is obtained.

[0057] The computer equipment compares various echo signal sets to obtain the distance between the multi-channel lidar and the target detected by each channel. Specifically, the computer equipment can directly compare the echo signals. For all echo signals corresponding to the same channel in the echo signal set, the computer equipment determines the actual echo signal corresponding to the current channel. In practical applications, the reception duration of the echo signals corresponding to the current channel is similar. For an echo signal set corresponding to multiple received echo signals, all the echo signals obtained this time are compared with the echo signals corresponding to the current channel in other echo signal sets to determine the echo signals with the same reception duration, which are the actual echo signals. Based on the actual echo signals, the distance between the multi-channel lidar and the target detected by the current channel is determined. In addition, for each echo signal set, the computer equipment can calculate the distance between the multi-channel lidar and the target for each echo signal, obtaining a corresponding distance set. Based on the comparison of each distance set, the actual distance value corresponding to each channel is determined, and finally, the distance between the multi-channel lidar and the target detected by each channel is obtained.

[0058] Specifically, during each grouping process, for each remaining group (excluding the first grouping), preset conditions must be met. These preset conditions are that the detection timing of existing channels and the channels included in each remaining grouping change compared to the first grouping. For example, in the first grouping, the detection timing of the first channel grouping comes first, and the first channel grouping includes channels 1 and 2; the detection timing of the second channel grouping comes later, and the second channel grouping includes channels 3 and 4. Therefore, in the second grouping, the detection timing of the third channel grouping could come first, and the third channel grouping includes channels 1 and 4; the detection timing of the fourth channel grouping could come later, and the fourth channel grouping includes channels 2 and 3.

[0059] In the above target detection method, the target grouping number for grouping multiple channels of the multi-channel lidar is predetermined. Multiple channels are grouped until the target grouping number is reached, resulting in a set of multiple channel groups. For each channel group set, the target is detected sequentially through the channels in the corresponding channel group according to the detection time sequence of each channel group, obtaining the corresponding echo signal set of the channel group set. Based on the comparison of each echo signal set, the distance between the multi-channel lidar and the target detected by each channel is obtained. In this method, each grouping except the first grouping meets a preset condition. The preset condition is that the detection time sequence of the channels and the channels contained in the channel group have changed compared to the first grouping. This allows for accurate identification of the actual echo signal on each channel, thereby obtaining the actual distance value and improving the accuracy of target detection.

[0060] In one embodiment, the step of determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR includes: determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR according to the scene type; the scene type is at least divided into static detection scene and dynamic detection scene, and the number of groupings for the dynamic detection scene is less than or equal to the number of groupings for the static detection scene.

[0061] The computer equipment determines the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type being detected by the multi-channel LiDAR. Specifically, the scene type is at least divided into static detection scene and dynamic detection scene. In dynamic scene, the relative movement speed between the multi-channel LiDAR and the target object is large, while in static scene, the relative movement speed between the multi-channel LiDAR and the target object is small. In order to scan the target object completely, the switching time of the multiple channels in the multi-channel LiDAR is required to be shorter in dynamic scene. Therefore, the number of groupings for dynamic detection scene is less than or equal to the number of groupings for static detection scene.

[0062] In this embodiment, the number of groupings for the corresponding multiple channels of the multi-channel LiDAR is determined according to the scene type. The scene type is at least divided into static detection scene and dynamic detection scene. The number of groupings for the dynamic detection scene is less than or equal to the number of groupings for the static detection scene, which can make the number of groupings approach the maximum value, thereby ensuring the integrity of the detected echo signal set and improving the accuracy of target detection.

[0063] In one embodiment, the step of determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type includes: in the case of a static detection scene, determining the number of groupings for the multiple channels based on the detection repetition frequency of the multi-channel LiDAR; in the case of a dynamic detection scene, determining the number of groupings for the multiple channels based on the relative movement speed between the multi-channel LiDAR and the target object.

[0064] In static detection scenarios, the computer equipment determines the number of groupings for multiple channels based on the detection repetition frequency and other characteristics of the multi-channel LiDAR, combined with the practical experience of technicians. The detection repetition frequency of the LiDAR refers to the pulse repetition frequency, i.e., the number of pulses sent per second by the LiDAR. The pulse repetition frequency affects the maximum unambiguous range of the LiDAR, i.e., the maximum detection range. In dynamic detection scenarios, the computer equipment determines the number of groupings for multiple channels based on the relative movement speed between the multi-channel LiDAR and the target object. Generally, the number of groupings for dynamic detection scenarios is less than or equal to the number of groupings for static detection scenarios.

[0065] In this embodiment, when the scene type is static detection, the number of groupings for multiple channels is determined based on the detection repetition frequency of the multi-channel LiDAR. When the scene type is dynamic detection, the number of groupings for multiple channels is determined based on the relative movement speed between the multi-channel LiDAR and the target. This allows for the determination of the corresponding number of groupings based on the scene being detected by the multi-channel LiDAR, thereby ensuring the integrity of the detected echo signal set and improving the accuracy of target detection.

[0066] In one embodiment, the detection timing of the corresponding channel group is characterized by the order of detection time periods, and the detection time periods of different channel groups in the channel group set do not overlap.

[0067] The detection timing of the channel group is characterized by the sequence of detection periods. The detection periods of different channel groups in the channel group set do not overlap. Taking the first channel group set as an example, assuming that the detection period of the first channel group in the first channel group set is from T0 to T4, the detection period of the second channel group is from T5 to T9, where T5 is longer than T4, to ensure that the detection periods of the first channel group and the second channel group do not overlap and to avoid generating more interference signals.

[0068] In this embodiment, the detection sequence of the channel group is characterized by the order of the detection time periods. The detection time periods of different channel groups in the channel group set do not overlap, which can avoid unnecessary interference between different channel groups in the channel group set, so as to ensure the actuality of the echo signal set obtained in each detection as much as possible, thereby improving the accuracy of target object detection.

[0069] In one embodiment, the step of obtaining the distance between the multi-channel lidar and the target object detected by each channel by comparing different echo signal sets includes: comparing different echo signal sets, obtaining the corresponding target echo signal of each channel according to the comparison results; and determining the distance between the multi-channel lidar and the target object detected by each channel according to the corresponding target echo signal and echo duration of each channel.

[0070] The computer equipment compares different echo signal sets and obtains the corresponding target echo signal for each channel based on the comparison results. For example, in the first echo signal set, the echo signal corresponding to channel 1 is echo signal 1; in the second echo signal set, the echo signals corresponding to channel 1 are echo signal 2 and echo signal 3. Then, echo signal 1, echo signal 2, and echo signal 3 together serve as the target echo signal for channel 1. Assuming the echo duration of echo signal 1 is S1 seconds, the echo duration of echo signal 2 is S0 seconds, and the echo duration of echo signal 3 is S1 seconds, then based on the comparison results of the first and second echo signal sets, echo signal 2 is determined to be an intermittent signal. This indicates that echo signal 2 is a signal detected by channel 1 due to crosstalk from other channels. Therefore, for the first detection, the computer equipment can determine the distance between the multi-channel lidar and the target object detected by channel 1 based on the echo duration and speed of light corresponding to echo signal 1, thus obtaining the distance between the multi-channel lidar and the target objects detected by each channel.

[0071] In this embodiment, by comparing different sets of echo signals, the corresponding target echo signal of each channel is obtained according to the comparison results. Based on the corresponding target echo signal and echo duration of each channel, the distance between the multi-channel lidar and the target object detected by each channel is determined, which can ensure that the target echo signal is the actual echo signal, thereby improving the accuracy of target object detection.

[0072] In one embodiment, the step of comparing different echo signal sets and obtaining the corresponding target echo signal for each channel based on the comparison results includes: for each channel, obtaining the echo signal subset of the channel in each echo signal set; taking the intersection of each echo signal subset corresponding to the channel, and using the intersection echo signal as the corresponding target echo signal for the channel.

[0073] For each channel, the computer device acquires the echo signal subsets of the current channel in each echo signal set. Taking the first echo signal subset of channel 1 in the first echo signal set as including echo signal 1, and the second echo signal subset of channel 1 in the second echo signal set as including echo signal 2 and echo signal 3 as an example, where echo signal 3 is a signal with the same reception duration as echo signal 1, the computer device takes the intersection of the first echo signal subset and the second echo signal subset based on the reception duration of the echo signal. The resulting intersection echo signals are echo signal 1 and echo signal 3. Therefore, in the first detection, echo signal 1 is the target echo signal corresponding to channel 1.

[0074] In this embodiment, by obtaining the echo signal subset of each channel in each echo signal set, taking the intersection of each echo signal subset of the corresponding channel, and using the intersection echo signal as the target echo signal of the corresponding channel, the actual echo signal of each channel can be determined, thereby improving the accuracy of target object detection.

[0075] In one embodiment, such as Figure 3 As shown, the steps for obtaining the distance between the multi-channel lidar and the target detected by each channel by comparing the sets of echo signals include:

[0076] S302: For each echo signal set, based on the corresponding echo signal and echo duration of each channel in the echo signal set, determine the reference distance between the multi-channel lidar and the target detected by each channel, and obtain the reference distance set corresponding to the echo signal set.

[0077] Specifically, for each echo signal set, the computer device can determine the reference distance between the multi-channel lidar and the target detected by each channel based on the corresponding echo signal and echo duration of each channel in the echo signal set. Specifically, the reference distance is equal to the product of the echo signal and the speed of light. For each echo signal, the computer device calculates the corresponding reference distance to obtain the reference distance set for each echo signal set.

[0078] It should be noted that even if multiple echo signals are received on a single channel, since the multi-channel lidar cannot determine which is the actual correct echo signal, a reference distance is calculated for each echo signal. By comparing different sets of reference distances, the actual distance between the multi-channel lidar and the target detected by each channel is determined from the reference distances corresponding to the multiple echo signals.

[0079] S304: Compare different sets of reference distances and determine the actual distance between the multi-channel lidar and the target detected by each channel based on the comparison results.

[0080] The computer equipment compares different reference distance sets. Taking the first reference distance set corresponding to the first echo signal set of channel 1 as including D1 and D2, and the second reference distance set corresponding to the second echo signal set as including D3 as an example, where the values ​​of D1 and D3 are the same, the computer equipment compares the first reference distance set and the second reference distance set to determine the actual distance in the first reference distance set as D1. Based on the comparison results, the actual distance between the multi-channel lidar and the target object detected by each channel is determined.

[0081] In this embodiment, for each echo signal set, the reference distance between the multi-channel lidar and the target object detected by each channel is determined based on the corresponding echo signal and echo duration of each channel in the echo signal set. The reference distance set corresponding to the echo signal set is obtained. The different reference distance sets are compared, and the actual distance between the multi-channel lidar and the target object detected by each channel is determined based on the comparison results. The actual distance value can be accurately obtained, thereby improving the accuracy of target object detection.

[0082] In one embodiment, such as Figure 4 As shown, a target detection method is provided, applicable to scenarios where detection is performed using a multi-channel lidar. The method includes the following steps:

[0083] S402: In the case of a static detection scenario, determine the number of groupings for multiple channels based on the detection repetition frequency of the multi-channel LiDAR; in the case of a dynamic detection scenario, determine the number of groupings for multiple channels based on the relative movement speed between the multi-channel LiDAR and the target object; the scenario type is at least divided into static detection scenarios and dynamic detection scenarios, and the number of groupings for dynamic detection scenarios is less than or equal to the number of groupings for static detection scenarios.

[0084] S404: Group multiple channels until the target number of groupings is reached, and obtain the corresponding set of multiple channel groups.

[0085] S406: For each channel group set, the target object is detected sequentially through the channels in the corresponding channel group according to the detection time sequence of each channel group in the channel group set, and the corresponding echo signal set of the channel group set is obtained; the detection time sequence of the channel group is characterized by the order of detection time periods, and the detection time periods of different channel groups in the channel group set do not overlap.

[0086] S408: For each channel, obtain the echo signal subset of the channel in each echo signal set; take the intersection of each echo signal subset of the channel, and use the intersection echo signal as the target echo signal of the channel; determine the distance between the multi-channel lidar and the target object detected by each channel according to the target echo signal and echo duration of each channel; wherein, for each remaining group except the first group, a preset condition is met, the preset condition is that the detection timing of the channel and the channels included in the group of the remaining group have changed compared with the first group.

[0087] S410: For each echo signal set, determine the reference distance between the multi-channel lidar and the target object detected by each channel based on the corresponding echo signal and echo duration of each channel in the echo signal set, and obtain the reference distance set corresponding to the echo signal set; compare the different reference distance sets, and determine the actual distance between the multi-channel lidar and the target object detected by each channel based on the comparison results.

[0088] Taking a four-channel lidar as an example, such as... Figure 5As shown, channels 1, 2, 3, and 4 are four detection channels distributed along the vertical direction of the four-channel lidar. Each detection channel emits light at a different angle to detect targets, and each channel has the same detection range. Channels 1 and 2 form the first channel group, and channels 3 and 4 form the second channel group. Specifically, 11 represents the actual target at the detection angle of channel 1, with distance D1 calculated based on the echo signal reception time; 12 represents the actual target at the detection angle of channel 2, with distance D2 calculated based on the echo signal reception time; 13 represents the actual target at the detection angle of channel 3, with distance D3 calculated based on the echo signal reception time; and 14 represents the actual target at the detection angle of channel 4, with distance D4 calculated based on the echo signal reception time.

[0089] Assuming target 11 is a highly reflective object, such as a road sign on a real road, there are two scenarios: If the distance to target 11 is within the detection range of channel 1, such as... Figure 6 As shown, since channels 1 and 2 perform emission detection simultaneously, the laser emitted by channel 1 is received by channel 2, resulting in crosstalk signals from channel 1 appearing on channel 2. Figure 6 The second channel falsely detected an echo signal of 112, meaning that two distance values, D1 and D2, existed on channel 2. For a two-channel system, it's difficult to determine which signal is actually present, leading to false detections. The resulting distance set after false detections is: {D1, D1 / D2, D3, D4}. In the second grouping, channels 1 and 3 are grouped as the first channel in a new round, and channels 2 and 4 are grouped as the second channel in a new round. Target detection is performed again, and the resulting distance set is: {D1, D2, D1 / D3, D4}. For each channel, the computer compares the two distance sets and takes the intersection to obtain the distance set {D1, D2, D3, D4}, which represents the actual distance between the multi-channel lidar and the target detected by each channel.

[0090] When the distance to 11 is outside the detection range of channel 1, such as Figure 7 As shown, since 11 exceeds the detection range of channel 1, channel 1 cannot detect the object, and the output value is X. 12 is the actual target object at the detection angle of channel 2, and the distance is calculated as D2 based on the reception time of the echo signal. 13 is the actual target object at the detection angle of channel 3, and the distance is calculated as D3 based on the reception time of the echo signal. 14 is the actual target object at the detection angle of channel 4, and the distance is calculated as D4 based on the reception time of the echo signal.

[0091] Since channels 1 and 2 perform emission detection simultaneously, the crosstalk from channel 11 to channel 2 is also outside the range of channel 2. Because channels 3 and 4 perform simultaneous detection with a delay compared to channels 1 and 2, channel 11 reflects the laser emitted from channel 1 into channels 3 and 4, causing crosstalk. Figure 7 The third channel falsely detected echo signal 113, and the fourth channel falsely detected echo signal 114. The resulting distance set after these false detections was {X, D2, D5 / D3, D5 / D4}. The signals were then regrouped. The grouping process is described in the case where the distance to signal 11 is within the detection range of the first channel, and will not be repeated here. The second grouping resulted in the distance set {X, D5 / D2, D3, D5 / D4}, and the third grouping resulted in the distance set {X, D5 / D2, D5 / D3, D4}. The computer compared these different distance sets and took the intersection to obtain the distance set {X1, D2, D3, D4}, which represents the actual distance between the multi-channel lidar and the target detected by each channel.

[0092] In this embodiment, a target number of groupings is predetermined for the corresponding multiple channels of the multi-channel LiDAR. Multiple channels are grouped until the target number of groupings is reached, resulting in a set of multiple channel groups. For each channel group set, the target object is detected sequentially through the channels in the corresponding channel group according to the detection timing sequence of each channel group. This yields a set of echo signals for each channel group set. Based on a comparison of these echo signal sets, the distance between the multi-channel LiDAR and the target object detected by each channel is obtained. For each grouping except the first grouping, a preset condition is met: compared to the first grouping, the detection timing of the channels and the channels included in the channel groups have changed. This allows for accurate identification of the actual echo signals on each channel, thereby obtaining the actual distance value and improving the accuracy of target object detection.

[0093] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0094] Based on the same inventive concept, this application also provides a target object detection device for implementing the target object detection method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more target object detection device embodiments provided below can be found in the limitations of the target object detection method described above, and will not be repeated here.

[0095] In one embodiment, such as Figure 8 As shown, a target object detection device is provided, comprising: a determination module 10, a grouping module 20, a detection module 30, and a comparison module 40, wherein:

[0096] The determination module 10 is used to determine the number of target groupings for grouping the corresponding multiple channels of the multi-channel lidar.

[0097] Grouping module 20 is used to group multiple channels until the target number of groupings is reached, thereby obtaining the corresponding set of multiple channel groups.

[0098] The detection module 30 is used to detect the target object sequentially through the channels in the corresponding channel group according to the detection timing of each channel group in the channel group set, and obtain the corresponding echo signal set of the channel group set.

[0099] The comparison module 40 is used to compare the echo signal sets to obtain the distance between the multi-channel lidar and the target detected by each channel; wherein, for each remaining group except the first group, a preset condition is met. The preset condition is that the detection timing of the existing channels and the channels included in the existing channel group have changed compared with the first group.

[0100] In one embodiment, the determining module 10 is further configured to determine the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type of the scene; the scene type is at least divided into static detection scene and dynamic detection scene, and the number of groupings for the dynamic detection scene is less than or equal to the number of groupings for the static detection scene.

[0101] In one embodiment, the determining module 10 is further configured to determine the number of times multiple channels are grouped based on the detection repetition frequency of the multi-channel LiDAR when the scene type is a static detection scene; and to determine the number of times multiple channels are grouped based on the relative movement speed between the multi-channel LiDAR and the target object when the scene type is a dynamic detection scene.

[0102] In one embodiment, the detection timing of the corresponding channel group is characterized by the order of detection time periods, and the detection time periods of different channel groups in the channel group set do not overlap.

[0103] In one embodiment, the comparison module 40 includes: a set comparison unit and a distance determination unit, wherein:

[0104] The ensemble comparison unit is used to compare different echo signal sets and obtain the corresponding target echo signal for each channel based on the comparison results.

[0105] The distance determination unit is used to determine the distance between the multi-channel lidar and the target object detected by each channel based on the corresponding target echo signal and echo duration of each channel.

[0106] In one embodiment, the set comparison unit includes: a subset acquisition subunit and a target signal determination subunit, wherein:

[0107] The subset acquisition sub-unit is used to acquire the echo signal subset of each channel in each echo signal set.

[0108] The target signal determination subunit is used to take the intersection of each echo signal subset corresponding to the channel, and use the intersection echo signal as the target echo signal corresponding to the channel.

[0109] In one embodiment, the comparison module 40 includes:

[0110] For each echo signal set, the reference distance between the multi-channel lidar and the target detected by each channel is determined based on the corresponding echo signal and echo duration of each channel in the echo signal set, thus obtaining the reference distance set corresponding to the echo signal set.

[0111] By comparing different sets of reference distances, the actual distance between the multi-channel lidar and the target detected by each channel is determined based on the comparison results.

[0112] Each module in the aforementioned target detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0113] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a target detection method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0114] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0115] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: determining a target number of groupings for multiple channels of a multi-channel lidar; grouping the multiple channels until the target number of groupings is reached, obtaining a set of multiple channel groups; for each channel group set, detecting a target object by sequentially passing through the channels in the corresponding channel group according to the detection timing sequence of each channel group in the channel group set, obtaining a set of echo signals corresponding to the channel group set; comparing each set of echo signals to obtain the distance between the multi-channel lidar and the target object detected by each channel; wherein, for each remaining grouping except for the first grouping, a preset condition is met, the preset condition being that the detection timing sequence of the channels and the channels contained in the channel groups have changed compared to the first grouping.

[0116] In one embodiment, the determination of the number of groupings for the corresponding multiple channels of the multi-channel LiDAR when the processor executes the computer program includes: determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR according to the scene type of the scene; the scene type is at least divided into static detection scene and dynamic detection scene, and the number of groupings for the dynamic detection scene is less than or equal to the number of groupings for the static detection scene.

[0117] In one embodiment, when the processor executes the computer program, determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type includes: in the case of a static detection scene, determining the number of groupings for the multiple channels based on the detection repetition frequency of the multi-channel LiDAR; and in the case of a dynamic detection scene, determining the number of groupings for the multiple channels based on the relative movement speed between the multi-channel LiDAR and the target object.

[0118] In one embodiment, the detection timing of the channel groups involved when the processor executes the computer program is characterized by the sequence of detection time periods, and the detection time periods of different channel groups in the channel group set do not overlap.

[0119] In one embodiment, the process of the processor executing a computer program to obtain the distance between the multi-channel lidar and the target object detected by each channel by comparing different sets of echo signals includes: comparing different sets of echo signals, obtaining the corresponding target echo signal for each channel based on the comparison results; and determining the distance between the multi-channel lidar and the target object detected by each channel based on the corresponding target echo signal and echo duration for each channel.

[0120] In one embodiment, when the processor executes a computer program, it compares different sets of echo signals and obtains the target echo signal for each channel based on the comparison results. This includes: for each channel, obtaining a subset of echo signals for that channel in each set of echo signals; taking the intersection of the subsets of echo signals for each channel, and using the intersection echo signal as the target echo signal for that channel.

[0121] In one embodiment, the process of the processor executing a computer program to obtain the distance between the multi-channel lidar and the target detected by each channel by comparing each set of echo signals includes: for each set of echo signals, determining the reference distance between the multi-channel lidar and the target detected by each channel based on the corresponding echo signal and echo duration of each channel in the set of echo signals, and obtaining a reference distance set corresponding to the set of echo signals; comparing different reference distance sets, and determining the actual distance between the multi-channel lidar and the target detected by each channel based on the comparison results.

[0122] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: determining a target number of groupings for the corresponding multiple channels of a multi-channel LiDAR; grouping the multiple channels until the number of groupings reaches the target number of groupings, thereby obtaining a set of corresponding multiple channel groups; for each channel group set, detecting a target object by sequentially passing through the channels in the corresponding channel group according to the detection timing sequence of each channel group in the channel group set, thereby obtaining a set of echo signals corresponding to the channel group set; comparing each set of echo signals to obtain the distance between the multi-channel LiDAR and the target object detected by each channel; wherein, for each remaining grouping except for the first grouping, a preset condition is met, the preset condition being that the detection timing sequence of the channels and the channels contained in the channel groups have changed compared to the first grouping.

[0123] In one embodiment, when the computer program is executed by the processor, the determination of the number of groupings for the corresponding multiple channels of the multi-channel LiDAR includes: determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR according to the scene type of the scene; the scene type is at least divided into static detection scene and dynamic detection scene, and the number of groupings for the dynamic detection scene is less than or equal to the number of groupings for the static detection scene.

[0124] In one embodiment, when the computer program is executed by the processor, determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type includes: in the case of a static detection scene, determining the number of groupings for the multiple channels based on the detection repetition frequency of the multi-channel LiDAR; and in the case of a dynamic detection scene, determining the number of groupings for the multiple channels based on the relative movement speed between the multi-channel LiDAR and the target object.

[0125] In one embodiment, the detection timing of the channel groups involved when the computer program is executed by the processor is characterized by the sequence of detection time periods, and the detection time periods of different channel groups in the channel group set do not overlap.

[0126] In one embodiment, when the computer program is executed by the processor, the process of comparing different sets of echo signals to obtain the distance between the multi-channel lidar and the target detected by each channel includes: comparing different sets of echo signals, obtaining the corresponding target echo signal for each channel based on the comparison results, and determining the distance between the multi-channel lidar and the target detected by each channel based on the corresponding target echo signal and echo duration for each channel.

[0127] In one embodiment, when the computer program is executed by the processor, it involves comparing different sets of echo signals and obtaining the target echo signal for each channel based on the comparison results. This includes: for each channel, obtaining a subset of echo signals for the channel in each set of echo signals; taking the intersection of the corresponding subsets of echo signals for the channel, and using the intersection echo signal as the target echo signal for the channel.

[0128] In one embodiment, when the computer program is executed by the processor, the comparison based on each echo signal set to obtain the distance between the multi-channel lidar and the target detected by each channel includes: for each echo signal set, determining the reference distance between the multi-channel lidar and the target detected by each channel according to the corresponding echo signal and echo duration of each channel in the echo signal set, and obtaining the reference distance set corresponding to the echo signal set; comparing different reference distance sets, and determining the actual distance between the multi-channel lidar and the target detected by each channel according to the comparison result.

[0129] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: determining a target number of groupings for multiple channels of a multi-channel LiDAR; grouping the multiple channels until the target number of groupings is reached, obtaining a corresponding set of multiple channel groups; for each channel group set, detecting a target object sequentially through the channels in the corresponding channel group according to the detection timing sequence of each channel group in the channel group set, obtaining a set of echo signals corresponding to the channel group set; comparing each set of echo signals to obtain the distance between the multi-channel LiDAR and the target object detected by each channel; wherein, for each remaining grouping except for the first grouping, a preset condition is met, the preset condition being that, compared with the first grouping, the detection timing sequence of the channels and the channels contained in the channel groups have changed in each remaining grouping.

[0130] In one embodiment, when the computer program is executed by the processor, the determination of the number of groupings for the corresponding multiple channels of the multi-channel LiDAR includes: determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR according to the scene type of the scene; the scene type is at least divided into static detection scene and dynamic detection scene, and the number of groupings for the dynamic detection scene is less than or equal to the number of groupings for the static detection scene.

[0131] In one embodiment, when the computer program is executed by the processor, determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type includes: in the case of a static detection scene, determining the number of groupings for the multiple channels based on the detection repetition frequency of the multi-channel LiDAR; and in the case of a dynamic detection scene, determining the number of groupings for the multiple channels based on the relative movement speed between the multi-channel LiDAR and the target object.

[0132] In one embodiment, the detection timing of the channel groups involved when the computer program is executed by the processor is characterized by the sequence of detection time periods, and the detection time periods of different channel groups in the channel group set do not overlap.

[0133] In one embodiment, when the computer program is executed by the processor, the process of comparing different sets of echo signals to obtain the distance between the multi-channel lidar and the target detected by each channel includes: comparing different sets of echo signals, obtaining the corresponding target echo signal for each channel based on the comparison results, and determining the distance between the multi-channel lidar and the target detected by each channel based on the corresponding target echo signal and echo duration for each channel.

[0134] In one embodiment, when the computer program is executed by the processor, it involves comparing different sets of echo signals and obtaining the target echo signal for each channel based on the comparison results. This includes: for each channel, obtaining a subset of echo signals for the channel in each set of echo signals; taking the intersection of the corresponding subsets of echo signals for the channel, and using the intersection echo signal as the target echo signal for the channel.

[0135] In one embodiment, when the computer program is executed by the processor, the comparison based on each echo signal set to obtain the distance between the multi-channel lidar and the target detected by each channel includes: for each echo signal set, determining the reference distance between the multi-channel lidar and the target detected by each channel according to the corresponding echo signal and echo duration of each channel in the echo signal set, and obtaining the reference distance set corresponding to the echo signal set; comparing different reference distance sets, and determining the actual distance between the multi-channel lidar and the target detected by each channel according to the comparison result.

[0136] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0137] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for detecting a target object, characterized in that, The method is applicable to scenarios where detection is performed using a multi-channel lidar; the method includes: Based on the scenario type, determine the number of groupings for the corresponding multiple channels of the multi-channel LiDAR; the scenario type is at least divided into static detection scenarios and dynamic detection scenarios, and the number of groupings for the dynamic detection scenario is less than or equal to the number of groupings for the static detection scenario; The multiple channels are grouped until the target number of groupings is reached, thereby obtaining a corresponding set of multiple channel groups. For each channel group set, the target object is detected sequentially through the channels in the corresponding channel group according to the detection timing of each channel group in the channel group set, thereby obtaining the corresponding echo signal set of the channel group set; The distance between the multi-channel lidar and the target detected by each channel is obtained by comparing the sets of echo signals. Specifically, for each remaining group other than the first group, a preset condition is met. The preset condition is that, compared with the first group, the detection timing of the channel and the channels included in the remaining group have changed.

2. The method according to claim 1, characterized in that, The step of determining the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type includes: In the case of a static detection scenario, the number of groupings for multiple channels is determined based on the detection repetition frequency of the multi-channel lidar. In the case of a dynamic detection scenario, the number of times the multiple channels are grouped is determined based on the relative movement speed between the multi-channel lidar and the target object.

3. The method according to claim 1, characterized in that, The detection sequence of the channel group is characterized by the order of detection time periods, and the detection time periods of different channel groups in the channel group set do not overlap.

4. The method according to claim 1, characterized in that, The step of comparing the echo signal sets to obtain the distance between the multi-channel lidar and the target detected by each channel includes: Compare different sets of echo signals, and obtain the corresponding target echo signal for each channel based on the comparison results; The distance between the multi-channel lidar and the target object detected by each channel is determined based on the corresponding target echo signal and echo duration of each channel.

5. The method according to claim 4, characterized in that, The step of comparing different echo signal sets and obtaining the corresponding target echo signal for each channel based on the comparison results includes: For each channel, obtain the echo signal subset of that channel in each echo signal set; The intersection of each subset of echo signals corresponding to the channel is taken, and the intersection echo signal is used as the target echo signal corresponding to the channel.

6. The method according to claim 1, characterized in that, The step of comparing the echo signal sets to obtain the distance between the multi-channel lidar and the target detected by each channel includes: For each echo signal set, the reference distance between the multi-channel lidar and the target detected by each channel is determined based on the corresponding echo signal and echo duration of each channel in the echo signal set, thereby obtaining the reference distance set corresponding to the echo signal set; By comparing different sets of reference distances, the actual distance between the multi-channel lidar and the target object detected by each channel is determined based on the comparison results.

7. A target object detection device, characterized in that, The device is applicable to scenarios requiring detection using a multi-channel lidar; the device includes: The determining module is used to determine the number of groupings for the corresponding multiple channels of the multi-channel LiDAR based on the scene type of the scene; the scene type is at least divided into static detection scene and dynamic detection scene, and the number of groupings for the dynamic detection scene is less than or equal to the number of groupings for the static detection scene; The grouping module is used to group the multiple channels until the target number of groupings is reached, thereby obtaining a corresponding set of multiple channel groups. The detection module is used to detect the target object sequentially through the channels in the corresponding channel group according to the detection timing of each channel group in the channel group set, and obtain the corresponding echo signal set of the channel group set. The comparison module is used to compare each echo signal set to obtain the distance between the multi-channel lidar and the target detected by each channel; wherein, for each remaining group except the first group, a preset condition is met, the preset condition is that the detection timing of the channel and the channels included in the remaining group have changed compared with the first group.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images