Systems and methods for generating a video summary
Systems and method of generating video summaries are presented herein. Information defining a video may be obtained. The video may include a set of frame images. Parameter values for parameters of individual frame images of the video may be determined. Interest weights for the frame images may be determined. An interest curve for the video that characterizes the video by interest weights as a function of progress through the set of frame images may be generated. One or more curve attributes of the interest curve may be identified and one or more interest curve values of the interest curve that correspond to individual curve attributes may be determined. Interest curve values of the interest curve may be compared to threshold curve values. A subset of frame images of the video to include within a video summary of the video may be identified based on the comparison.
1. A system configured to generate a video summary, the system comprising:
one or more physical computer processors configured by computer readable instructions to:
obtain information defining a video, the video including a set of images;
determine individual parameter values for one or more parameters of individual images of the video;
determine individual interest weights of the individual images based on the individual parameter values of the one or more parameters of the individual images, wherein determining a given interest weight of a given image comprises determining impact of individual parameter values on the given interest weight;
generate an interest curve for the video based on the individual interest weights of the individual images, the interest curve characterizing the video based on the interest weights as a function of progress through the set of images;
identify curve attributes of the interest curve, the identified curve attributes characterizing a maximum and a plateau of the interest curve;
identify one or more subsets of images of the video for inclusion within the video summary based on the identified curve attributes of the interest curve; and
generate the video summary based on the identification of the one or more subsets of the images of the video.
2. The system of claim 1 , wherein the one or more subset of images of the video are identified further based on corresponding values of the interest curve being greater than one or more threshold curve values.
3. The system of claim 2 , wherein the one or more threshold curve values are specific to content of the video.
4. The system of claim 1 , wherein the identified curve attributes further characterize one or more of an overall shape, an infection point, a minimum, a rate of change, or a rate of the rate of change of the interest curve.
5. The system of claim 1 , wherein the one or more parameters include one or more of a scene parameter, a quality parameter, a capture parameter, or an audio parameter.
6. The system of claim 5 , wherein the scene parameter specifies one or more scene features of the individual images, the one or more scene features including one or more of feature points, objects, faces, colors, scene compilation, or text of the individual images.
7. The system of claim 6 , wherein the quality parameter specifics one or more quality attributes of the individual images, the one or more quality attributes including one or more of blurriness, glare, saturation, brightness, contrast, sharpness, framing of an object of interest, of a representativeness of the individual images with respect to an overall context of the video.
8. The system of claim 1 , wherein the impact of individual parameter values on the given interest weight is determined based on a convolutional neural network.
9. The system of claim 1 , wherein the information defining the video includes metadata associated with the video, and the individual parameter values for the one or more parameters of the individual images of the video are determined further based on the metadata.
10. The system of claim 9 , wherein the metadata associated with the video includes one or more of capture settings of a capture device, sensor output of one or more sensors coupled to the capture device, or user-provided information.
11. A method of generating a video summary, the method being implemented in a computer system comprising one or more physical processors and storage media storing machine-readable instructions, the method comprising:
obtaining, by the computing system, information defining a video, the video including a set of images;
determining, by the computing system, individual parameter values for one or more parameters of individual images of the video;
determining, by the computing system, interest weights of the individual images based on the individual parameter values of the one or more parameters of the individual images, wherein determining a given interest weight of a given image comprises determining impact of individual parameter values on the given interest weight;
generating, by the computing system, an interest curve for the video based on the individual interest weights of the individual images, the interest curve characterizing the video based on the interest weights as a function of progress through the set of images;
identifying, by the computing system, curve attributes of the interest curve, the identified curve attributes characterizing a maximum and a plateau of the interest curve;
identifying, by the computing system, one or more subsets of images of the video for inclusion within the video summary based on the identified curve attributes of the interest curve; and
generating, by the computing system, the video summary based on the identification of the one or more subsets of the images of the video.
12. The method of claim 11 , wherein the one or more subset of images of the video are identified further based on corresponding values of the interest curve being greater than one or more threshold curve values.
13. The method of claim 12 , wherein the one or more threshold curve values are specific to content of the video.
14. The method of claim 11 , wherein the identified curve attributes further characterize one or more of an overall shape, an infection point, a minimum, a rate of change, or a rate of the rate of change of the interest curve.
15. The method of claim 11 , wherein the one or more parameters include one or more of a scene parameter, a quality parameter, a capture parameter, or an audio parameter.
16. The method of claim 15 , wherein the scene parameter specifies one or more scene features of the individual images, the one or more scene features including one or more of feature points, objects, faces, colors, scene compilation, or text of the individual images.
17. The method of claim 16 , wherein the quality parameter specifics one or more quality attributes of the individual images, the one or more quality attributes including one or more of blurriness, glare, saturation, brightness, contrast, sharpness, framing of an object of interest, of a representativeness of the individual images with respect to an overall context of the video.
18. The method of claim 11 , wherein the impact of individual parameter values on the given interest weight is determined based on a convolutional neural network.
19. The method of claim 11 , wherein the information defining the video includes metadata associated with the video, and the individual parameter values for the one or more parameters of the individual images of the video are determined further based on the metadata.
20. The method of claim 19 , wherein the metadata associated with the video includes one or more of capture settings of a capture device, sensor output of one or more sensors coupled to the capture device, or user-provided information.