System and method for selectable semantic codec pairs for very low data-rate video transmission
View Patent ↗A system and method for using computer image processing for selectable task-based digital video compression is described. The system is intended to reduce travel of experts and let these experts direct field agents in performing tasks remotely. The tasks to be performed in the remote field can be monitoring, manipulating, and navigating. A field agent performs the manipulation and navigation operations, this agent can be a human being or a robot. The task-based compression algorithms use computer vision techniques to extract the bare minimum amount of information from the remote field scenery to allow the task to be performed. High frame rate photo-realistic reconstruction of the remote scene is not generally necessary.
1. A system for compressing one or more video streams comprising:
one or more image input devices creating the one or more video streams; and
a selector process that selects a semantic compression process out of a set of semantic compression processes, the selected semantic compression process compressing the one or more video streams based on a task that required the compression of the one or more video streams and that utilizes content of the one or more video streams.
2. A system, as in claim 1 , where the task includes any one or more of the following: surveillance, diagnosis, inspection, navigation, objection localization, control, and maintenance.
3. A system, as in claim 1 , where the selected semantic compression process is a lossy process having a compression ratio greater than 100 to 1.
4. A system, as in claim 1 , where the set of semantic compression processes includes one or more of the following compression processes: selective edge retention, line finding, motion segmentation, patch tracking, template matching, object tracking, Motion Picture Experts Group compression standards, M-JPEG, M-JIBIG, H.261, H.323, and region segmentation.
5. A system, as in claim 1 , where one of the selected semantic compression processes is a line finding process and the task is a diagnostic task.
6. A system, as in claim 1 , where one of the selected semantic compression processes is a region segmentation process and the task is a driving task.
7. A system, as in claim 1 , where one of the selected semantic compression processes is an object tracking process and the task is a control task.
8. A system, as in claim 1 , where one of the selected semantic compression processes is a motion segmentation process and the task is the localization of an object.
9. A system, as in claim 1 , where one of the selected semantic compression processes is a template matching process and the task is the localization of an object.
10. A system, as in claim 1 , where one of the selected semantic compression processes is a spatially varying resolution process and the task is an observation of an anchor patch.
11. A system, as in claim 1 , where the one or more image input devices are connected to the selector process running on a remote device, where the remote device is connected to the one or more image input devices over one or more networks.
12. A system, as in claim 1 , where the selector changes one or more of the selected semantic compression processes during transmission of the one or more video streams.
13. A system, as in claim 1 , that is used for one or more of the following: diagnostics with an expert at a remote site, an observation, a scene inspection, a scene surveillance, a navigation procedure, an objection localization, a control procedure, a maintenance procedure, and a diagnostic procedure.
14. A method for compressing video streams, the method comprising the steps of:
inputting one or more video streams; and
selecting a semantic compression process out of a set of semantic compression processes, the selected semantic compression process compressing the one or more video streams based on a task that required the compression of the one or more video streams and that utilizes content of the one or more video streams.
15. A system for compressing video streams, the system comprising:
means for inputting one or more video streams; and
means for selecting a semantic compression process out of a set of semantic compression processes, the selected semantic compression process compressing the one or more video streams based on a task that required the compression of the one or more video streams and that utilizes content of the one or more video streams.
16. A computer program process having the steps of:
inputting one or more video streams; and
selecting a semantic compression process out of a set of semantic compression processes, the selected semantic compression process compressing the one or more video streams based on a task that required the compression of the one or more video streams and that utilizes content of the one or more video streams.
17. A system for compressing one or more video streams comprising:
one or more image input devices creating one or more video streams; and
a selector process that selects a plurality of compression processes out of a set of compression processes, the selected plurality of compression processes each compressing one or more regions of the one or more video streams based on a task that required the compression of the one or more video streams and that utilizes content of the one or more video streams.