Method and device of multi-focal sensing of an obstacle and non-volatile computer-readable storage medium

1. A method for multi-focal sensing of an obstacle, comprising:

acquiring detection results of obstacles at multiple moments by utilizing a camera with long focus lens and a camera with short focus lens;

performing a target tracking to the acquired detection results, to obtain at least two tracking sequences, wherein each tracking sequence comprises detection results acquired at the multiple moments for a same obstacle; and

matching two random tracking sequences of the at least two tracking sequences, and combining the two random tracking sequences into a combined tracking sequence, if the matching is successful.

2. The method according to claim 1 , wherein the matching two random tracking sequences of the at least two tracking sequences comprises:

selecting the two random tracking sequences from the at least two tracking sequences;

acquiring, for each moment, detection results from the selected two tracking sequences respectively, and projecting detection results acquired by the camera with the long focus lens onto an imaging plane acquired by the camera with the short focus lens, if the detection results from the selected two tracking sequences respectively are acquired by cameras with different focus lenses, and calculating an Intersection over Union (IoU) of the projected detection results and detection results acquired by the camera with the short focus lens;

determining an average of the IoUs calculated for the multiple moments; and

determining the matching of the selected two tracking sequences is successful if the average is greater than a preset threshold.

3. The method according to claim 1 , wherein the combining the two random tracking sequences into a combined tracking sequence comprises:

combining detection results of the two random tracking sequences to obtain a combined tracking sequence.

4. The method according to claim 1 , further comprising:

acquiring a new detection result, and determining whether the new detection result is correlated with the combined tracking sequence;

creating a new tracking sequence if the new detection result is not correlated with the combined tracking sequence, wherein the new tracking sequence comprises the new detection result; or

incorporating the new detection result into the combined tracking sequence if the new detection result is correlated with the combined tracking sequence.

5. A device of multi-focal sensing of an obstacle, comprising:

a camera with long focus lens for acquiring detection results of obstacles;

a camera with short focus lens for acquiring detection results of obstacles; and

a controller comprising a memory and a processor, wherein the memory has computer programs stored thereon, and the computer programs are executed by the processor to cause the processor to:

acquire detection results of the obstacles at multiple moments by utilizing the camera with the long focus lens and the camera with the short focus lens;

perform a target tracking to the acquired detection results, to obtain at least two tracking sequences, wherein each tracking sequence comprises detection results acquired at the multiple moments for a same obstacle; and

match two random tracking sequences of the at least two tracking sequences, and combining the two random tracking sequences into a combined tracking sequence, if the matching is successful.

6. The device according to claim 5 , wherein the computer programs are executed by the processor to cause the processor to further:

select the two random tracking sequences from the at least two tracking sequences;

acquire, for each moment, detection results from the selected two tracking sequences respectively, and project detection results acquired by the camera with the long focus lens onto an imaging plane acquired by the camera with the short focus lens, if the detection results from the selected two tracking sequences respectively are acquired by cameras with different focus lenses, and calculate an Intersection over Union (IoU) of the projected detection results and detection results acquired by the camera with the short focus lens;

determine an average of the IoUs calculated for the multiple moments; and

determine the matching of the selected two tracking sequences is successful if the average is greater than a preset threshold.

7. The device according to claim 5 , wherein the computer programs are executed by the processor to cause the processor to further:

combine detection results of the two random tracking sequences to obtain a combined tracking sequence if the matching is successful.

8. The device according to claim 5 , wherein the computer programs are executed by the processor to cause the processor to further:

acquire a new detection result, and determine whether the new detection result is correlated with the combined tracking sequence, creating a new tracking sequence if the new detection result is not correlated with the combined tracking sequence, wherein the new tracking sequence comprises the new detection result, or incorporate the new detection result into the combined tracking sequence if the new detection result is correlated with the combined tracking sequence.

9. A non-transitory computer readable storage medium, in which a computer program is stored, wherein the program, when executed by a processor, causes the processor to execute a method for multi-focal sensing of an obstacle, comprising:

acquiring detection results of obstacles at multiple moments by utilizing a camera with long focus lens and a camera with short focus lens;

performing a target tracking to the acquired detection results, to obtain at least two tracking sequences, wherein each tracking sequence comprises detection results acquired at the multiple moments for a same obstacle; and

matching two random tracking sequences of the at least two tracking sequences, and combining the two random tracking sequences into a combined tracking sequence, if the matching is successful.