Keyframe scheduling method and apparatus, electronic device, program and medium

1. A key frame scheduling method, comprising:

performing feature extraction on a current frame via a first network layer of a neural network to obtain a low-level feature of the current frame;

obtaining a scheduling probability of the current frame according to a low-level feature of a previous key frame adjacent to the current frame and the low-level feature of the current frame, wherein the low-level feature of the previous key frame is obtained by performing feature extraction on the previous key frame via the first network layer, and the scheduling probability is a probability that the current frame is scheduled as a key frame;

determining whether the current frame is scheduled as a key frame according to the scheduling probability of the current frame; and

responsive to determining that the current frame is scheduled as a key frame, using the current frame as a current key frame and buffering a low-level feature of the current key frame, and performing feature extraction on the low-level feature of the current key frame via a second network layer of the neural network to obtain a high-level feature of the current key frame, wherein a network depth of the first network layer is less than a network depth of the second network layer.

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

determining an initial key frame;

performing feature extraction on the initial key frame via the first network layer to obtain a low-level feature of the initial key frame and buffer the low-level feature of the initial key frame; and

performing feature extraction on the low-level feature of the initial key frame via the second network layer to obtain a high-level feature of the initial key frame.

3. The method according to claim 2 , further comprising:

performing semantic segmentation on the initial key frame to output a semantic label of the initial key frame.

4. The method according to claim 1 , wherein the obtaining a scheduling probability of the current frame according to a low-level feature of a previous key frame adjacent to the current frame and the low-level feature of the current frame comprises:

splicing the low-level feature of the previous key frame and the low-level feature of the current frame to obtain a spliced feature; and

obtaining, via a key frame scheduling network, a scheduling probability of the current frame based on the spliced feature.

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

performing semantic segmentation on the current key frame to output a semantic label of the current key frame.

6. A key frame scheduling apparatus, comprising:

a processor; and

a memory for storing instructions executed by the processor,

wherein the processor is configured to:

perform feature extraction on a current frame via a first network layer of a neural network to obtain a low-level feature of the current frame;

obtain a scheduling probability of the current frame according to a low-level feature of a previous key frame adjacent to the current frame and the low-level feature of the current frame, wherein the low-level feature of the previous key frame is obtained by performing feature extraction on the previous key frame via the first network layer, and the scheduling probability is a probability that the current frame is scheduled as a key frame;

determine whether the current frame is scheduled as a key frame according to the scheduling probability of the current frame; and

responsive to determining that the current frame is scheduled as a key frame, use the current frame as a current key frame and buffer a low-level feature of the current key frame, and perform feature extraction on the low-level feature of the current key frame to obtain a high-level feature of the current key frame, wherein a network depth of the first network layer is less than a network depth of the second network layer.

7. The apparatus according to claim 6 , wherein the previous key frame comprises a predetermined initial key frame; and

the processor is further configured to buffer a low-level feature of the initial key frame.

8. The apparatus according to claim 6 , wherein the processor is configured to:

splice the low-level feature of the previous key frame and the low-level feature of the current frame to obtain a spliced feature; and

obtain a scheduling probability of the current frame based on the spliced feature.

9. The apparatus according to claim 6 , wherein the processor is configured to:

perform semantic segmentation on the key frame to output a semantic label of the key frame, the key frame comprising at least one of: the initial key frame, the previous key frame, or the current key frame.

10. An electronic device, comprising the key frame scheduling apparatus according to claim 6 .

11. A non-transitory computer readable medium, having stored thereon computer readable instructions that, when being executed, implement a key frame scheduling method comprising:

performing feature extraction on a current frame via a first network layer of a neural network to obtain a low-level feature of the current frame;

obtaining a scheduling probability of the current frame according to a low-level feature of a previous key frame adjacent to the current frame and the low-level feature of the current frame, wherein the low-level feature of the previous key frame is obtained by performing feature extraction on the previous key frame via the first network layer, and the scheduling probability is a probability that the current frame is scheduled as a key frame;

determining whether the current frame is scheduled as a key frame according to the scheduling probability of the current frame; and

responsive to determining that the current frame is scheduled as a key frame, using the current frame as a current key frame and buffering a low-level feature of the current key frame, and performing feature extraction on the low-level feature of the current key frame via a second network layer of the neural network to obtain a high-level feature of the current key frame, wherein a network depth of the first network layer is less than a network depth of the second network layer.

12. The non-transitory computer readable medium according to claim 11 , wherein the method further comprises:

determining an initial key frame;

performing feature extraction on the initial key frame via the first network layer to obtain a low-level feature of the initial key frame and buffer the low-level feature of the initial key frame; and

performing feature extraction on the low-level feature of the initial key frame via the second network layer to obtain a high-level feature of the initial key frame.

13. The non-transitory computer readable medium according to claim 12 , wherein the method further comprises:

performing semantic segmentation on the initial key frame to output a semantic label of the initial key frame.

14. The non-transitory computer readable medium according to claim 11 , wherein the obtaining a scheduling probability of the current frame according to a low-level feature of a previous key frame adjacent to the current frame and the low-level feature of the current frame comprises:

splicing the low-level feature of the previous key frame and the low-level feature of the current frame to obtain a spliced feature; and

obtaining, via a key frame scheduling network, a scheduling probability of the current frame based on the spliced feature.

15. The non-transitory computer readable medium according to claim 11 , wherein the method further comprises:

performing semantic segmentation on the current key frame to output a semantic label of the current key frame.

16. The method according to claim 1 , wherein obtaining a scheduling probability of the current frame according to a low-level feature of a previous key frame adjacent to the current frame and the low-level feature of the current frame, comprises:

determining a difference value between the low-level feature of the previous key frame and the low-level feature of the current frame; and

obtaining a scheduling probability of the current frame according to the determined difference value between the low-level feature of the previous key frame and the low-level feature of the current frame,

the method further comprising:

when the difference value between the low-level feature of the previous key frame and the low-level feature of the current frame is greater than a preset threshold, determining that the current frame is scheduled as the current key frame.