Obstacle avoidance reminding method, electronic device and computer-readable storage medium thereof

1. An obstacle avoidance reminding method, comprising:

performing ground detection based on acquired image data to acquire ground information of a road;

performing passability detection based on the acquired ground information, and determining a traffic state of the road;

if it is determined that the road is impassable, performing road condition detection for the road to acquire a first detection result, and performing obstacle detection for the road to acquire a second detection result; and

determining obstacle avoidance reminding information based on the first detection result and the second detection result,

wherein the performing passability detection based on the acquired ground information, and determining a traffic state of the road comprises:

determining a pre-warning region based on the ground information of the road, and determining the traffic state of the road by detecting a traffic state of the pre-warning region,

wherein the determining a pre-warning region based on the ground information of the road, and determining the traffic state of the road by detecting a traffic state of the pre-warning region comprises:

constructing spatial coordinates of the pre-warning region;

determining a height of the pre-warning region under the spatial coordinates based on the around height;

determining a width and a distance of the pre-warning region under the spatial coordinates based on the obstacle information;

adjusting a position of the pre-warning region based on the ground height; and

determining the traffic state of the road by detecting a traffic state of the pre-warning region experiencing position adjustment;

wherein the traffic state comprises a passable state or an impassable state.

2. The obstacle avoidance reminding method according to claim 1 , wherein the performing ground detection based on acquired image data to acquire ground information of a road comprises:

establishing three-dimensional point cloud for the road based on the acquired image data; and

performing the ground detection in the three-dimensional point cloud to acquire the ground information of the road.

3. The obstacle avoidance reminding method according to claim 2 , wherein the performing the ground detection in the three-dimensional point cloud to acquire the ground information of the road comprises:

detecting a ground height in the three-dimensional point cloud;

determining obstacle information on the ground height; and

using the ground height and the obstacle information as the ground information of the road.

4. The obstacle avoidance reminding method according to claim 3 , wherein the determining obstacle information on the ground height comprises:

determining a ground position of the road based on the ground height; and

performing obstacle detection for the ground position of the road, and generating the obstacle information on the ground height based on an obstacle detection result.

5. The obstacle avoidance reminding method according to claim 2 , wherein the establishing three-dimensional point cloud for the road based on the acquired image data comprises:

acquiring a depth image and a posture of the camera from the image date;

calculating a scale normalization factor based on the depth image and a predetermined normalization scale;

calculating a scale-normalized depth image based on the depth image and the scale normalization factor,

constructing a three-dimensional point cloud under a coordinate system of a camera based on the depth image experience scale normalization; and

constructing a three-dimensional point cloud under a world coordinate system based on the three-dimensional point cloud under the coordinate system of the camera and the posture of the camera.

6. The obstacle avoidance reminding method according to claim 1 , wherein the performing road condition detection for the road to acquire a first detection result comprises:

determining a ground position of the road based on the ground height; and

performing traffic state detection for the ground position of the road to determine sag information on the road, and using the sag information as the first detection result;

wherein the sag information comprises existence of the sag or not and a position of the sag.

7. The obstacle avoidance reminding method according to claim 6 , wherein the performing obstacle detection for the road to acquire a second detection result comprises:

partitioning the acquired image data to obtain M×N partitions, wherein M and N are both integers greater than 1;

determining information of an obstacle in each of the partitions;

determining a pre-warning grade of each of the partitions based on the information of the obstacle in each of the partitions;

determining a decision suggestion for passing the road based on the pre-warning grade of each of the partitions; and

using the pre-warning grade of each of the partitions and the decision suggestion for passing the road as the second detection result.

8. The obstacle avoidance reminding method according to claim 7 , wherein the determining a pre-warning grade of each of the partitions based on the information of the obstacle in each of the partitions comprises:

determining a weight of each of the partitions based on the information of the obstacle in each of the partitions; and

determining the pre-warning grade of each of the partitions based on the weight of each of the partitions, wherein the weight is positively proportional to the pre-warning grade.

9. The obstacle avoidance reminding method according to claim 8 , wherein the determining a decision suggestion for passing the road based on the pre-warning grade of each of the partitions comprises:

calculating a gradient value of each of the partitions, wherein the gradient value is calculated based on the weight of the partition and weights of adjacent partitions of the partition;

determining a maximum gradient value of the gradient values of all the partitions; and

determining the decision suggestion for passing the road based on the maximum gradient value, wherein the decision suggestion comprises an optimal passing direction, and using a direction of the maximum gradient value as an optimal passing direction in the decision suggestion.

10. The obstacle avoidance reminding method according to claim 9 , wherein upon the determining obstacle avoidance reminding information based on the first detection result and the second detection result, the method further comprises:

sending an alarm signal based on the obstacle avoidance reminding information.

11. An electronic device, comprising:

at least one processor, and

a memory communicably connected to the at least one processor; wherein

the memory stores instructions executable by the at least one processor, wherein, the instructions, when being executed by the at least one processor, cause the at least one processor to perform the steps of:

performing ground detection based on acquired image data to acquire ground information of a road;

performing passability detection based on the acquired ground information, and determining a traffic state of the road;

if it is determined that the road is impassable, performing road condition detection for the road to acquire a first detection result, and performing obstacle detection for the road to acquire a second detection result; and

determining obstacle avoidance reminding information based on the first detection result and the second detection result,

wherein the performing passability detection based on the acquired ground information, and determining a traffic state of the road comprises:

determining a pre-warning region based on the ground information of the road, and determining the traffic state of the road by detecting a traffic state of the pre-warning region,

wherein the determining a pre-warning region based on the ground information of the road, and determining the traffic state of the road by detecting a traffic state of the pre-warning region comprises:

constructing spatial coordinates of the pre-warning region;

determining a height of the pre-warning region under the spatial coordinates based on the around height;

determining a width and a distance of the pre-warning region under the spatial coordinates based on the obstacle information;

adjusting a position of the pre-warning region based on the ground height; and

determining the traffic state of the road by detecting a traffic state of the pre-warning region experiencing position adjustment;

wherein the traffic state comprises a passable state or an impassable state.

12. A computer-readable storage medium, which stores a computer program; wherein the computer program, when being executed by a processor, causes the processor to perform the steps of:

performing ground detection based on acquired image data to acquire ground information of a road;

performing passability detection based on the acquired ground information, and determining a traffic state of the road, comprising

determining a pre-warning region based on the ground information of the road, and determining the traffic state of the road by detecting a traffic state of the pre-warning region;

if it is determined that the road is impassable, performing road condition detection for the road to acquire a first detection result, and performing obstacle detection for the road to acquire a second detection result; and

determining obstacle avoidance reminding information based on the first detection result and the second detection result,

wherein the performing passability detection based on the acquired ground information, and determining a traffic state of the road comprises:

determining a pre-warning region based on the ground information of the road, and determining the traffic state of the road by detecting a traffic state of the pre-warning region,

wherein the determining a pre-warning region based on the ground information of the road, and determining the traffic state of the road by detecting a traffic state of the pre-warning region comprises:

constructing spatial coordinates of the pre-warning region;

determining a height of the pre-warning region under the spatial coordinates based on the ground height;

determining a width and a distance of the pre-warning region under the spatial coordinates based on the obstacle information;

adjusting a position of the pre-warning region based on the ground height; and

determining the traffic state of the road by detecting a traffic state of the pre-warning region experiencing position adjustment;

wherein the traffic state comprises a passable state or an impassable state.