TW202311781A - Obstacle detection method utilizing an obstacle recognition model to recognize obstacle category corresponding to each obstacle - Google Patents

Abstract

An obstacle detection method comprises steps of: (A) for each point cloud data, obtaining an image to be fused from the images according to the point cloud data after receiving a plurality of point cloud data and a plurality of images; (B) for each image to be fused, obtaining a previous Nth image to be synthesized photographed earlier than the image to be fused; (C) for each point cloud data, obtaining an integrated image according to the corresponding image to be fused and the previous Nth image to be synthesized; (D) for each point cloud data, aligning and projecting the point cloud data on the corresponding integrated image; and (E) for each point cloud data, utilizing an obstacle recognition model to recognize an obstacle category corresponding to each obstacle located in the front direction according to the aligned and projected point cloud data and the integrated image.

Description

Obstacle Detection Method

The present invention relates to an obstacle detection method, in particular to an obstacle detection method that integrates different sensors.

Mobile vehicles introduce more and more sensors and intelligent algorithms to continuously enhance their environmental perception and flexible movement capabilities. In various fields, including factories using AMR (Autonomous Mobile Robot) industry for storage and handling and self-driving cars running on the road Obstacle detection, stop or dodge requires the use of multi-sensors, such as radar, lidar, and cameras for detection and obstacle avoidance. When the mobile vehicle is driving on any path, the most important requirements are to avoid obstacles and identify the types of obstacles.

Each sensing element has its own advantages, and now it is mostly used on various vehicle platforms with heterogeneous sensing fusion. However, the sensing data and sampling time of each sensor are different. For example, the radar system obtains a radar data every 50ms, the lidar system obtains a point cloud data every 100ms, and the camera system takes an image every 33ms. When there are large differences in sensors, there will be a problem that time and space cannot be synchronized, and it is impossible to know what the obstacle is. It is necessary to propose a solution.

Therefore, the object of the present invention is to provide an obstacle detection method for synchronizing space and time and identifying obstacle types when multi-sensors are fused.

Therefore, the obstacle detection method of the present invention is implemented by a computing device, and the computing device is electrically connected with an image capturing device installed on a mobile vehicle and a LiDAR module, and the image capturing device is used to capture A series of images of a plurality of obstacles located in front of the mobile vehicle, the lidar module is used to obtain a series of point cloud data located in front of the mobile vehicle and including the obstacles, the obstacle detection method includes the following step:

(A) After receiving the point cloud data of the LiDAR module and the images of the image capture device, for each point cloud data, according to the point cloud data, the image captured by the image capture device Obtain a pair of images to be fused corresponding to the point cloud data in the image;

(B) For each image to be fused, obtain the Nth image to be synthesized earlier than the image to be fused, where N≧3;

(C) For each point cloud data, according to the corresponding image to be fused and the previous Nth image to be synthesized, obtain a pair of integrated images corresponding to the point cloud data;

(D) For each point cloud data, align and project the point cloud data to the corresponding integrated image; and

(E) For each point cloud data, according to the point cloud data and the integrated image after the aligned projection in step (D), use an obstacle recognition model to identify the correspondence of each obstacle located in front of the mobile vehicle obstacle category.

The effect of the present invention lies in: the image to be fused corresponding to the point cloud data is obtained from the images captured by the image shooting device by the computing device, and the image to be fused is synthesized according to the corresponding image to be fused and the previous Nth image Image obtains the integrated image, and aligns and projects the point cloud data to the corresponding integrated image to achieve spatial and temporal synchronization when fusing the sensing data of the lidar module and the image capture device. In addition, by According to the integrated image and point cloud data after alignment and projection, the obstacle identification model is used to identify the obstacle category corresponding to each obstacle, so as to achieve the purpose of identifying obstacles.

Referring to FIG. 1 , an embodiment of the obstacle detection method of the present invention is implemented by an obstacle detection system installed on a mobile vehicle. The obstacle detection system includes an image capture device 11, a lidar module 12, a radar module 13 and an electrical connection between the image capture device 11, the lidar module 12 and the mobile vehicle. The computing device 14 of the radar module 13 .

The image capture device 11 is used to continuously capture a series of images of obstacles located in front of the mobile vehicle. In this embodiment, the image capture device 11 is, for example, a video camera, and captures an image every 33 ms.

The lidar module 12 is used to continuously obtain a series of point cloud data located in front of the mobile vehicle and including the obstacles. In this embodiment, the LiDAR module 12 is, for example, a LiDAR sensor, and obtains a piece of point cloud data every 100 ms. The point cloud data obtained every 100 ms is the point cloud data scanned from right to left by the lidar module 12 during a preset period from a first scanning time point to an Nth scanning time point.

The radar module 13 is used to continuously obtain a series of radar data located in front of the mobile vehicle and including the obstacles. In this embodiment, the radar module 13 is, for example, a radar sensor, and obtains a piece of radar data every 50 ms.

The computing device 14 is, for example, a processor or a microprocessor and other chips capable of performing computing functions.

The action of each component in the obstacle detection system will be described below by using an embodiment of the obstacle detection method of the present invention. The embodiment includes a radar fusion program and an image fusion program.

Referring to FIG. 1 and FIG. 2 , the radar fusion procedure of the embodiment of the obstacle detection method of the present invention includes the following steps.

In step 21, after the computing device 14 receives the point cloud data of the lidar module 12 and the radar data of the radar module 13, for each point cloud data, according to the point cloud data, automatically Among the radar data obtained by the radar module 13, a pair of radar data to be fused corresponding to the point cloud data is obtained.

It is worth mentioning that step 21 also includes the following sub-steps (refer to FIG. 3 ).

In sub-step 211, after the computing device 14 receives the point cloud data of the lidar module 12 and the radar data of the radar module 13, for each point cloud data, according to the point cloud data, Extract a first candidate radar data and a second candidate radar data from the radar data obtained by the radar module 13, the acquisition time of the first candidate radar data is earlier than the acquisition time of the point cloud data, and The point cloud data is acquired at the shortest time interval, and the second candidate radar data is the previous radar data of the first candidate radar data.

In sub-step 212, for each point cloud data, the calculation device 14 obtains the corresponding one of the obstacles located in front of the mobile vehicle according to the first candidate radar data corresponding to the point cloud data. a first specific obstacle parameter. In this embodiment, the first specific obstacle parameter is a first specific obstacle distance between the mobile vehicle and the specific obstacle, however, in other embodiments, the first specific obstacle parameter can also be A first specific obstacle position of the specific obstacle, or a first specific obstacle speed of the specific obstacle are not limited thereto.

In sub-step 213 , for each point cloud data, the computing device 14 obtains a second specific obstacle parameter corresponding to the specific obstacle according to the second candidate radar data corresponding to the point cloud data. In this embodiment, the second specific obstacle parameter is a second specific obstacle distance between the mobile vehicle and the specific obstacle, however, in other embodiments, the second specific obstacle parameter can also be A second specific obstacle position of the specific obstacle, or a second specific obstacle speed of the specific obstacle are not limited thereto.

、該點雲資料所對應之第一候選雷達資料的獲得時間

及第二候選雷達資料的獲得時間

、該第一特定障礙物參數

以及該第二特定障礙物參數

，利用以下公式(1)計算該特定障礙物在該點雲資料之獲得時間t的一推測障礙物參數

。在本實施方式中，該推測障礙物參數為該移動載具與該特定障礙物的一推測障礙物距離，然而，在其他實施方式中，該推測障礙物參數亦可為該特定障礙物的一推測障礙物位置，或是該特定障礙物的一推測障礙物速度，並不以此為限。

…(1) In sub-step 214, for each point cloud data, the computing device 14

, The acquisition time of the first candidate radar data corresponding to the point cloud data

and the acquisition time of the second candidate radar data

, the first specific obstacle parameter

and the second specific obstacle parameter

, use the following formula (1) to calculate an estimated obstacle parameter of the specific obstacle at the acquisition time t of the point cloud data

. In this embodiment, the estimated obstacle parameter is an estimated obstacle distance between the mobile vehicle and the specific obstacle. However, in other embodiments, the estimated obstacle parameter can also be an estimated obstacle distance of the specific obstacle. The estimated obstacle position, or an estimated obstacle velocity of the specific obstacle is not limited thereto.

…(1)

為一誤差值。 in,

is an error value.

In sub-step 215, for each point cloud data, the calculation device 14 converts the estimated obstacle parameter into an estimated obtained obstacle parameter according to the estimated obstacle parameter and an obstacle parameter such as the first conversion rule of the distance to the obtained interval. interval. It is worth noting that the first conversion rule is to first calculate an estimated acquisition time corresponding to the estimated obstacle parameter by using a first conversion function of the estimated obstacle parameter to time according to the estimated obstacle parameter, and then, According to the estimated acquisition time and the plurality of radar sampling intervals, the radar sampling interval in which the estimated acquisition time falls is used as the estimated acquisition interval. Wherein, the first conversion function is obtained according to the acquisition time of each piece of radar data and the indicated obstacle parameters of the specific obstacle, from the time point of each piece of radar data acquisition to the time point of the next radar data , but not including the time interval defined by the acquisition time point of the next radar data constitutes a radar sampling interval. FIG. 4 illustrates the first conversion function 41 and the radar sampling intervals 42 .

In sub-step 216, for each point cloud data, the calculation device 14 obtains the radar data corresponding to the estimated interval from the radar data obtained by the radar module 13 according to the estimated interval, as the to-be-fused Radar data. The radar data corresponding to the estimated acquisition interval is the radar information corresponding to the starting time point of the estimated acquisition interval.

It is worth noting that since the radar module 13 obtains a piece of radar data every 50 ms, the lidar module 12 obtains a piece of point cloud data every 100 ms, plus the radar module 13 and the lidar module 12 start There may also be errors in the starting time of obtaining data, so the time of obtaining data by the radar module 13 and the lidar module 12 may not be synchronized. The present invention uses the execution of sub-steps 211 to 216 to obtain data from the lidar module 12 The acquisition time of the point cloud data is taken as the basis to obtain the corresponding radar data to be fused, and then the obtained radar data to be fused can be synchronized with the corresponding point cloud data as far as possible.

In step 22, for each point cloud data, the computing device 14 uses a directional bounding box algorithm to locate the obstacles in the point cloud data. In this embodiment, the bounding box algorithm locates the obstacles based on principal component analysis.

In step 23, the computing device 14 uses a Kalman filter to track the obstacles located in each point cloud data to obtain the correspondence between the mobile vehicle and each obstacle located in front of the mobile vehicle. obstacle distance.

In step 24, for each radar data to be fused, the computing device 14 utilizes the bounding box algorithm to locate the obstacles in the radar data to be fused.

In step 25, the calculation device 14 uses the Kalman filter to track the obstacles located in each radar data to be fused to obtain the obstacle velocity corresponding to each obstacle in front of the mobile vehicle .

Referring to FIG. 1 and FIG. 5 , the image fusion procedure of the embodiment of the obstacle detection method of the present invention includes the following steps.

In step 51, after the computing device 14 receives the point cloud data of the lidar module 12 and the images of the image capture device 11, for each point cloud data, according to the point cloud data, from the A pair of images to be fused corresponding to the point cloud data is obtained from the images captured by the image capturing device 11 .

It is worth mentioning that step 51 includes the following sub-steps (refer to FIG. 6 ).

In sub-step 511, after the computing device 14 receives the point cloud data of the lidar module 12 and the images of the image capture device 11, for each point cloud data, according to the point cloud data, automatically A first candidate image and a second candidate image are extracted from the images captured by the image capture device 11, the first candidate image was captured earlier than the point cloud data acquisition time, and is consistent with the point cloud data The time interval of obtaining time is the shortest, and the second candidate image is a previous image of the first candidate image.

In sub-step 512, for each point cloud data, the computing device 14 obtains a corresponding one of the obstacles located in front of the mobile vehicle according to the first candidate image corresponding to the point cloud data. The third specific obstacle parameter. In this embodiment, the third specific obstacle parameter is a third specific obstacle distance between the mobile vehicle and the specific obstacle, however, in other embodiments, the third specific obstacle parameter can also be A third specific obstacle position of the specific obstacle, or a third specific obstacle speed of the specific obstacle are not limited thereto. Wherein, when the third specific obstacle parameter is the third specific obstacle distance or the third specific obstacle speed, the computing device 14 also needs to obtain the third specific obstacle distance according to the focal length of the image capture device 11 or third specific obstacle speed.

In sub-step 513 , for each point cloud data, the computing device 14 obtains a fourth specific obstacle parameter corresponding to the specific obstacle according to the second candidate image corresponding to the point cloud data. In this embodiment, the fourth specific obstacle parameter is a fourth specific obstacle distance between the mobile vehicle and the specific obstacle, however, in other embodiments, the fourth specific obstacle parameter can also be A fourth specific obstacle position of the specific obstacle, or a fourth specific obstacle speed of the specific obstacle are not limited thereto. Wherein, when the fourth specific obstacle parameter is the fourth specific obstacle distance or the fourth specific obstacle speed, the computing device 14 also needs to obtain the fourth specific obstacle distance according to the focal length of the image capture device 11 or the fourth specific obstacle speed.

、該點雲資料所對應之第一候選影像的拍攝時間

及第二候選影像的拍攝時間

、該第三特定障礙物參數

以及該第四特定障礙物參數

，利用以下公式(2)計算該特定障礙物在點雲資料之獲得時間t的另一推測障礙物參數

。在本實施方式中，該另一推測障礙物參數為該移動載具與該特定障礙物的另一推測障礙物距離，然而，在其他實施方式中，該另一推測障礙物參數亦可為該特定障礙物的另一推測障礙物位置，或是該特定障礙物的另一推測障礙物速度，並不以此為限。

…(2) In sub-step 514, for each point cloud data, the computing device 14

, The shooting time of the first candidate image corresponding to the point cloud data

and the shooting time of the second candidate image

, the third specific obstacle parameter

and the fourth specific obstacle parameter

, use the following formula (2) to calculate another estimated obstacle parameter of the specific obstacle at the acquisition time t of the point cloud data

. In this embodiment, the other estimated obstacle parameter is another estimated obstacle distance between the mobile vehicle and the specific obstacle, however, in other embodiments, the another estimated obstacle parameter can also be the Another estimated obstacle position of the specific obstacle, or another estimated obstacle speed of the specific obstacle, are not limited thereto.

…(2)

為一誤差值。 in,

is an error value.

In sub-step 515, for each point cloud data, the calculation device 14 converts the other estimated obstacle parameter according to the other estimated obstacle parameter and an obstacle parameter such as the second conversion rule of distance to shooting interval To a presumed shooting interval. It is worth noting that the second conversion rule is to calculate an estimated shot corresponding to the other estimated obstacle parameter by using a second conversion function of an obstacle parameter versus time based on the other estimated obstacle parameter. time, and then, according to the estimated shooting time and a plurality of image sampling intervals, the image sampling interval in which the estimated shooting time falls is used as the estimated shooting interval. Wherein, the second conversion function is obtained according to the shooting time of each image and the indicated obstacle parameter of the specific obstacle, from the shooting time of each image to the shooting time of the next image , but not including the time interval defined by the shooting time point of the next image constitutes an image sampling interval. FIG. 7 illustrates the second conversion function 71 and the image sampling intervals 72 .

In sub-step 516, for each point cloud data, the computing device 14 obtains an image corresponding to the estimated shooting interval from the images captured by the image capturing device 11 according to the estimated shooting interval as the image to be fused. The image corresponding to the estimated shooting interval is the image corresponding to the starting time point of the estimated shooting interval.

It is worth noting that since the image capture device 11 captures an image every 33ms, the lidar module 12 obtains a piece of point cloud data every 100ms, and the image capture device 11 and the lidar module 12 start to There may also be errors in the starting time of data acquisition, so the time of obtaining data by the image capture device 11 and the LiDAR module 12 may not be synchronized. The present invention uses the LiDAR module 12 through the execution of sub-steps 511-516 The acquisition time of the point cloud data is used as the basis to obtain the corresponding image to be fused, and then the obtained image to be fused can be synchronized with the corresponding point cloud data as much as possible in time.

In step 52 , for each image to be fused, the computing device 14 obtains the Nth image to be synthesized earlier than the image to be fused, where N≧3. In this embodiment, N is 3.

In step 53, for each point cloud data, the computing device 14 obtains a pair of integrated images corresponding to the point cloud data according to the corresponding image to be fused and the previous N-th image to be synthesized. In this embodiment, for each point cloud data, the computing device 14 combines a part of the corresponding image to be fused (that is, the left half) with a part of the previous Nth image to be synthesized (that is, the right half) to perform image synthesis to obtain the integrated image corresponding to the point cloud data. Since the lidar module 12 scans from right to left each time to obtain each piece of point cloud data, the obtained point There is a scanning delay between the right half of the scene in front of the mobile vehicle in the cloud data and the left half of the scene in front of the mobile vehicle (that is, the part of the obtained point cloud data corresponding to the left half of the scene is newer, the part corresponding to the right half of the scene in the obtained point cloud data is relatively old), so by integrating the left half of the corresponding image to be fused with the right half of the previous Nth image to be synthesized, the synthesis The resulting integrated image is closer to the scanning condition of the lidar module 12, thereby achieving spatial synchronization.

In step 54, for each point cloud data, the computing device 14 aligns and projects the point cloud data to the corresponding integrated image.

It is worth mentioning that step 54 includes the following sub-steps (refer to FIG. 8 ).

In sub-step 541, for each point cloud data, the computing device 14 converts the point cloud coordinate system according to the coordinate conversion parameter set between the point cloud coordinate system of the point cloud data and the pixel coordinate system of the integrated image. The cloud data is converted into a 2D point cloud data. It is worth mentioning that the coordinate conversion parameter set includes an external parameter matrix and an internal parameter matrix, and the external parameter matrix is obtained according to the installation position of the lidar module 12 and the installation position of the image capture device 11 . The internal parameter matrix is obtained according to the focal distance in pixels of the image capture device 11 and the image center coordinates. Since the focus of the present invention is not how to convert the point cloud data into two-dimensional point cloud data, its calculation details can refer to http://www.vision.caltech.edu/bouguetj/calib_doc/htmls/parameters.html Description, no more repeat and details here.

In sub-step 542, for each 2D point cloud data, the computing device 14 obtains edge features of each object in the 2D point cloud data.

In sub-step 543, for the integrated image corresponding to each point cloud data, the computing device 14 obtains the edge features of each object in the integrated image.

In sub-step 544, for each point cloud data, the computing device 14 calculates the corresponding The 2D point cloud data is aligned with the corresponding integrated image.

In step 55, for each point cloud data, the computing device 14 uses an obstacle recognition model to identify each object located in front of the mobile vehicle according to the aligned and projected point cloud data and the integrated image in step 54. An obstacle category corresponding to an obstacle. It is worth mentioning that the obstacle recognition model is trained using a machine learning algorithm based on multiple training data marked with obstacle positions and obstacle types. Each training data contains an aligned and projected training point cloud data and training images, and the aligned and projected training point cloud data and training images are marked with obstacle positions and obstacle categories.

To sum up, in the obstacle detection method of the present invention, the computing device 14 obtains the image to be fused corresponding to the point cloud data from the images captured by the image capturing device 11, and obtains the image to be fused from the radar module The radar data to be fused corresponding to the point cloud data is obtained from the radar data obtained in 13, so as to synchronize the data obtained by different sensors. The integrated image is obtained from the Nth image to be synthesized, and the point cloud data is aligned and projected to the corresponding integrated image, so that the point cloud data and the integrated image are spatially fused, and furthermore, by aligning and projecting The integrated image and point cloud data, using the obstacle identification model to identify the obstacle category corresponding to each obstacle, so as to achieve the effect of identifying obstacles, so the purpose of the present invention can indeed be achieved.

But the above-mentioned ones are only embodiments of the present invention, and should not limit the scope of the present invention. All simple equivalent changes and modifications made according to the patent scope of the present invention and the content of the patent specification are still within the scope of the present invention. Within the scope covered by the patent of the present invention.

11: Image shooting device 12:Lidar module 13:Radar module 14: Computing device 41: The first conversion function 42: Radar sampling interval 71: The second conversion function 72: Image sampling interval 21~25: Steps 51~55: Steps 211~216: sub-steps 511~516: sub-steps 541~544: sub-steps

Other features and effects of the present invention will be clearly presented in the implementation manner with reference to the drawings, wherein: FIG. 1 is a block diagram illustrating an obstacle detection system implementing an embodiment of the obstacle detection method of the present invention; FIG. 2 is a flowchart illustrating a radar fusion procedure of an embodiment of the obstacle detection method of the present invention; Fig. 3 is a flow chart illustrating how an computing device obtains radar data to be fused corresponding to a point cloud data; 4 is a schematic diagram illustrating a first transfer function and a plurality of radar sampling intervals; FIG. 5 is a flowchart illustrating an image fusion procedure of an embodiment of the obstacle detection method of the present invention; Fig. 6 is a flowchart illustrating how the computing device obtains an image to be fused corresponding to the point cloud data; FIG. 7 is a schematic diagram illustrating a second conversion function and a plurality of image sampling intervals; and FIG. 8 is a flowchart illustrating how the computing device aligns and projects the point cloud data to the corresponding integrated image.

51~55: Steps

Claims (9)

An obstacle detection method is implemented by a computing device, the computing device is electrically connected with an image capturing device installed on a mobile vehicle and a LiDAR module, and the image capturing device is used to continuously capture images located on the A series of images of multiple obstacles in front of the mobile vehicle, the lidar module is used to continuously obtain a series of point cloud data located in front of the mobile vehicle and including the obstacles, the obstacle detection method includes the following steps : (A) After receiving the point cloud data of the LiDAR module and the images of the image capture device, for each point cloud data, according to the point cloud data, the image captured by the image capture device Obtain a pair of images to be fused corresponding to the point cloud data in the image; (B) For each image to be fused, obtain the Nth image to be synthesized earlier than the image to be fused, where N≧3; (C) For each point cloud data, according to the corresponding image to be fused and the previous Nth image to be synthesized, obtain a pair of integrated images corresponding to the point cloud data; (D) For each point cloud data, align and project the point cloud data to the corresponding integrated image; and (E) For each point cloud data, according to the point cloud data and the integrated image after the aligned projection in step (D), use an obstacle recognition model to identify the correspondence of each obstacle located in front of the mobile vehicle obstacle category. The obstacle detection method as described in claim 1, wherein step (A) includes the following sub-steps: (A-1) After receiving the point cloud data of the lidar module and the images of the image capture device, for each point cloud data, according to the point cloud data, from the image captured by the image capture device A first candidate image and a second candidate image are extracted from the images, the shooting time of the first candidate image is earlier than the acquisition time of the point cloud data, and the time interval with the acquisition time of the point cloud data is the shortest, the the second candidate image is a previous image of the first candidate image; (A-2) For each point cloud data, according to the first candidate image corresponding to the point cloud data, obtain a first specific obstacle corresponding to one of the specific obstacles located in front of the mobile vehicle parameter; (A-3) For each point cloud data, obtain a second specific obstacle parameter corresponding to the specific obstacle according to the second candidate image corresponding to the point cloud data; (A-4) For each point cloud data, according to the acquisition time of the point cloud data, the shooting time of the first candidate image and the second candidate image corresponding to the point cloud data, the first specific obstacle parameter and the first 2 specific obstacle parameters, calculating an estimated obstacle parameter for the specific obstacle at the time when the point cloud data is obtained; (A-5) For each point cloud data, convert the estimated obstacle parameter to an estimated shooting interval according to the estimated obstacle parameter and an obstacle parameter conversion rule for the shooting interval; and (A-6) For each point cloud data, according to the estimated shooting interval, an image corresponding to the estimated shooting interval is obtained from the images captured by the image capturing device as the image to be fused. The obstacle detection method as described in claim 2, wherein, in sub-step (A-4), the estimated obstacle parameter is also calculated according to the following formula

:

, in,

is the time when the point cloud data was obtained,

is the shooting time of the first candidate image corresponding to the point cloud data,

is the shooting time of the second candidate image corresponding to the point cloud data,

is the first specific obstacle parameter,

is the second specific obstacle parameter, and

is an error. The obstacle detection method as described in claim 1, wherein, in step (C), for each point cloud data, a part of the corresponding image to be fused and a part of the previous Nth image to be synthesized are combined Image synthesis is performed to obtain the integrated image corresponding to the point cloud data. The obstacle detection method as described in claim 1, wherein step (D) includes the following sub-steps: (D-1) For each point cloud data, convert the point cloud data into two dimensional point cloud data; (D-2) For each two-dimensional point cloud data, obtain the edge features of each object in the two-dimensional point cloud data; (D-3) For the integrated image corresponding to each point cloud data, obtain the edge features of each object in the integrated image; and (D-4) For each point cloud data, according to the edge features of each object in the corresponding two-dimensional point cloud data and the edge features of each object in the corresponding integrated image, the corresponding two-dimensional point cloud The data is aligned with the corresponding integrated image. The obstacle detection method as described in claim 1, further comprising the following steps: (F) After receiving the point cloud data of the lidar module, for each point cloud data, use a bounding box algorithm to locate the obstacles in the point cloud data; and (G) Using a Kalman filter to track the obstacles located in each point cloud data to obtain an obstacle distance corresponding to the mobile vehicle and each obstacle located in front of the mobile vehicle. According to the obstacle detection method described in claim 1, the computing device is also electrically connected to a radar module arranged on the mobile vehicle, and the radar module is used to continuously obtain the radar module located in front of the mobile vehicle and including A series of radar data of the obstacles, the obstacle detection method also includes the following steps: (H) After receiving the point cloud data of the lidar module and the radar data of the radar module, for each point cloud data, according to the point cloud data, the Obtain a pair of radar data to be fused corresponding to the point cloud data from the radar data; (1) For each radar data to be fused, use a bounding box algorithm to locate the obstacles in the radar data to be fused; and (J) Using a Kalman filter to track the obstacles located in each of the radar data to be fused to obtain an obstacle velocity corresponding to each obstacle in front of the mobile vehicle. The obstacle detection method as described in claim item 7, wherein, step (H) comprises the following sub-steps: (H-1) After receiving the point cloud data of the lidar module and the radar data of the radar module, for each point cloud data, according to the point cloud data, obtained from the radar module A first candidate radar data and a second candidate radar data are extracted from the radar data, and the acquisition time of the first candidate radar data is earlier than the acquisition time of the point cloud data, and is the same as the acquisition time of the point cloud data The time interval is the shortest, and the second candidate radar data is the previous radar data of the first candidate radar data; (H-2) For each point cloud data, according to the first candidate radar data corresponding to the point cloud data, obtain a first specific obstacle corresponding to one of the specific obstacles located in front of the mobile vehicle physical parameters; (H-3) For each point cloud data, according to the second candidate radar data corresponding to the point cloud data, obtain a second specific obstacle parameter corresponding to the specific obstacle; (H-4) For each point cloud data, according to the acquisition time of the point cloud data, the acquisition time of the first candidate radar data and the second candidate radar data corresponding to the point cloud data, the first specific obstacle parameter and The second specific obstacle parameter, calculating an estimated obstacle parameter of the specific obstacle at the time when the point cloud data is obtained; (H-5) For each point cloud data, according to the estimated obstacle parameter and a conversion rule of an obstacle parameter to the obtained interval, convert the estimated obstacle parameter to an estimated obtained interval; and (H-6) For each point cloud data, the radar data corresponding to the estimated interval is obtained from the radar data obtained by the radar module according to the estimated interval as the radar data to be fused. Obstacle detection method as described in claim item 8, in sub-step (H-4), also calculate the estimated obstacle parameter according to the following formula

:

, in,

is the time when the point cloud data was obtained,

is the acquisition time of the first candidate radar data corresponding to the point cloud data,

is the acquisition time of the second candidate radar data corresponding to the point cloud data,

is the first specific obstacle parameter, and

is the second specific obstacle parameter,

is an error value.

Images