Snapshot capture for a communication session

• US 9,509,741 B2
• Filed: 04/10/2015
• Issued: 11/29/2016
• Est. Priority Date: 04/10/2015
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Barjonas, Hamish Rory, Lucas, Simon, Blundell, Carl David, Wass, Mark Christopher
• Primary Examiner(s): SMITH, CREIGHTON H
• Application Number:
  US14/683,819
• Publication Number:
  US 20160301727A1
• Time in Patent Office: 599 Days
• Field of Search: 348/14.07
• US Class Current: 1/1
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06V 40/169 Holistic features and representations, i.e. based on the facial image taken as a whole
• CPC Class Codes: H04L 65/1083 In-session procedures
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04L 65/75 Media network packet handling
• CPC Class Codes: H04L 65/80 Responding to QoS
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

Techniques for snapshot capture for a communication session are described. According to various embodiments, a communication session is established that includes a video feed that is streamed between devices involved in the communication session. The video feed is sampled to extract still images (e.g., frames) from the video feed that include images of a particular participant in the communication session. A snapshot is then selected from the images based on one or more selection criteria, such as an image score for the snapshot. Should a quality of the video feed fall below an acceptable video quality threshold during the communication session, the snapshot is used in place of the video feed for a visual representation of the participant during the communication session.

Claims

1. A system comprising:

at least one processor; and

one or more computer-readable storage media including instructions stored thereon that, responsive to execution by the at least one processor, cause the system to perform operations including;

ascertaining that a video feed is established at a first device as part of a communication session between the first device and a second device;

sampling the video feed to extract images of a participant in the communication session that is present at the second device;

scoring the images to generate a score for each of the images;

selecting a snapshot from the one or more images based on a score for the snapshot; and

causing the snapshot to be displayed as part of the communication session in place of the video feed at the first device responsive to the video feed falling below a quality threshold.

2. A system as recited in claim 1, wherein said sampling and said selecting are performed automatically and independent of user interaction.

3. A system as recited in claim 1, wherein the operations are performed at least in part at the first device.

4. A system as recited in claim 1, wherein the operations are performed at least in part by a network-based service.

5. A system as recited in claim 1, wherein said scoring for a particular image is based on one or more of a technical score for the particular image, a facial score for the particular image, or a motion score for the particular image.

6. A system as recited in claim 1, wherein said scoring for a particular image is based at least in part on a facial score for a face image detected in the particular image, and wherein the facial score is generated based on one or more of a position score for the face image, a size score for the face image, a technical score for the face image, or an eye measurement score for the face image.

7. A system as recited in claim 1, wherein said scoring for a particular image is based at least in part on a position score for a face image detected in the particular image, and wherein the position score is generated based on a proximity of a center of the face image to a center of the particular image.

8. A system as recited in claim 1, wherein said scoring for a particular image is based at least in part on an eye measurement score for a face image detected in the particular image, and wherein the eye measurement score is generated based on an eye visibility score for one or more images of one or more eyes recognized in the face image.

9. A system as recited in claim 1, wherein said scoring for a particular image is based at least in part on an eye measurement score for a face image detected in the particular image, and wherein the eye measurement score is generated based on a gaze detection score for one or more images of one or more eyes recognized in the face image.

10. A system as recited in claim 1, wherein said scoring for a particular image is based at least in part on an age for the particular image.

11. A system as recited in claim 1, wherein said scoring for a particular image comprises:

ascertaining an age for the particular image; and

reducing an existing score for the particular image based on the age.

12. A computer-implemented method, comprising:

ascertaining that a video feed is established at a first device as part of a communication session between the first device and a second device;

sampling by a computing system the video feed to extract one or more images of a participant in the communication session that is present at the second device;

selecting by the computing system a snapshot from the one or more images based on one or more predefined criteria for the snapshot; and

causing the snapshot to be displayed as part of the communication session in place of the video feed at the first device responsive to the video feed falling below a quality threshold.

13. A method as described in claim 12, wherein said sampling and said selecting are performed by the computing system automatically and independent of user interaction.

14. A method as described in claim 12, wherein the one or more predefined criteria comprise one or more scoring criteria utilized to calculate an image score for the snapshot.

15. A method as described in claim 12, wherein the one or more predefined criteria comprise one or more scoring criteria utilized to calculate an image score for the snapshot, and wherein the snapshot is selected based on the image score exceeding one or more other image scores for one or more other images.

16. A method as described in claim 12, wherein the one or more predefined criteria comprise one or more scoring criteria utilized to calculate an image score for the snapshot, and wherein the one or more scoring criteria comprise one or more of a technical score for the snapshot, a facial score for the snapshot, or a motion score for the snapshot.

17. A method as described in claim 12, wherein the one or more predefined criteria comprise one or more scoring criteria utilized to calculate an image score for the snapshot, and wherein the one or more scoring criteria comprise a gaze detection score generated for eyes of a face image recognized in the snapshot.

18. A computer-implemented method, comprising:

sampling a video feed of a communication session to extract one or more images of a participant in the communication session;

selecting by a computing system a snapshot from the one or more images based on one or more predefined criteria for the snapshot; and

causing the snapshot to be displayed as part of the communication session in place of the video feed responsive to the video feed falling below a quality threshold.

19. A method as described in claim 18, wherein said sampling and said selecting are performed automatically and independent of user interaction.

20. A method as described in claim 18, further comprising:

ascertaining, subsequent to said causing the snapshot to be displayed as part of the communication session in place of the video feed, that the video feed meets the quality threshold;

causing the video feed to be displayed in place of the snapshot as part of the communication session; and

resuming capturing one or more snapshots of the video feed.