Video summarization using semantic information
Example apparatus disclosed herein are to process a first image of a first video segment from the image capture sensor with a machine learning algorithm to determine a first score for the first image, the machine learning algorithm to detect actions associated with images, the actions associated with labels. Disclosed example apparatus are also to determine a second score for the first video segment based on respective first scores for corresponding images in the first video segment. Disclosed example apparatus are further to determine, based on the second score, whether to retain the first video segment in the memory.
1. An electronic device comprising:
an image capture sensor;
memory to store video segments;
wireless communication circuitry; and
one or more processors to:
process a first image of a first video segment from the image capture sensor with a machine learning algorithm, the machine learning algorithm to process the first image to output a first score for the first image, the machine learning algorithm trained to detect actions associated with frames of image data input to the machine learning algorithm, the actions associated with labels;
determine a second score for the first video segment from respective first scores output by the machine learning algorithm for corresponding images in the first video segment; and
at least one of retain the first video segment in the memory or discard the first video segment from the memory based on the second score.
2. The electronic device of claim 1 , wherein the machine learning algorithm is to output a confidence that the first image is associated with a first one of the labels.
3. The electronic device of claim 1 , wherein the first video segment has a duration of at least five seconds.
4. The electronic device of claim 1 , wherein the labels correspond to a group of labels having a size of at least hundreds of labels.
5. The electronic device of claim 1 , wherein the electronic device is a wearable device.
6. The electronic device of claim 1 , wherein the wireless communication circuitry includes at least one of WiFi hardware, Bluetooth hardware or cellular hardware.
7. The electronic device of claim 1 , wherein the machine learning algorithm is implemented with a convolutional neural network trained to detect the actions associated with the images.
8. The electronic device of claim 1 , further including:
a display;
a microphone; and
at least one of a keyboard, a touchpad or a touchscreen.
9. At least one memory device comprising computer readable instructions that, when executed, cause an electronic device to at least:
process a first image of a first video segment from an image capture sensor of the electronic device with a machine learning algorithm, the machine learning algorithm to process the first image to output a first score for the first image, the machine learning algorithm trained to detect an action associated with at least one frame of image data input to the machine learning algorithm, the action associated with a label;
determine a second score for the first video segment from respective first scores output by the machine learning algorithm for corresponding images in the first video segment; and
at least one of retain the first video segment in the electronic device or discard the first video segment from the electronic device based on the second score.
10. The at least one memory device of claim 9 , wherein the machine learning algorithm is to output a confidence that the first image is associated with the label.
11. The at least one memory device of claim 9 , wherein the first video segment has a duration of at least five seconds.
12. The at least one memory device of claim 9 , wherein the label is one of a group of labels having a size of at least hundreds of labels.
13. The at least one memory device of claim 9 , wherein the machine learning algorithm is implemented with a convolutional neural network trained to detect the action.
14. An electronic device comprising:
means for capturing images;
means for storing video segments; and
means for determining whether to retain a first video segment, the means for determining to:
process a first image of the first video segment with a machine learning algorithm, the machine learning algorithm to process the first image to output a first score for the first image, the machine learning algorithm trained to detect actions associated with frames of image data input to the machine learning algorithm, the actions associated with labels;
determine a second score for the first video segment from respective first scores output by the machine learning algorithm for corresponding images in the first video segment; and
at least one of retain the first video segment or discard the first video segment based on the second score.
15. The electronic device of claim 14 , wherein the machine learning algorithm is to output a confidence that the first image is associated with a first one of the labels.
16. The electronic device of claim 14 , wherein the first video segment has a duration of at least five seconds.
17. The electronic device of claim 14 , wherein the labels correspond to a group of labels having a size of at least hundreds of labels.
18. The electronic device of claim 14 , further including means for transmitting data via a WiFi network.
19. The electronic device of claim 14 , wherein the machine learning algorithm is implemented with a convolutional neural network trained to detect the actions associated with the images.
20. A method comprising:
processing, by executing an instruction with processor circuitry of an electronic device, a first image of a first video segment with a machine learning algorithm, the machine learning algorithm to process the first image to output a first score for the first image, the machine learning algorithm trained to detect actions associated with frames of image data input to the machine learning algorithm, the actions associated with labels, the first video segment from an image capture sensor of the electronic device;
determining, by executing an instruction with the processor circuitry, a second score for the first video segment based on respective first scores for corresponding images in the first video segment; and
at least one of retaining the first video segment in the electronic device or discarding the first video segment from the electronic device based on the second score.
21. The method of claim 20 , wherein the machine learning algorithm is to output a confidence that the first image is associated with a first one of the labels.
22. The method of claim 20 , wherein the first video segment has a duration of at least five seconds.
23. The method of claim 20 , wherein the labels correspond to a group of labels having a size of at least hundreds of labels.
24. The method of claim 20 , wherein the machine learning algorithm is implemented with a convolutional neural network trained to detect the actions associated with the images.