System and method of generating enhanced video by removing fog for vehicle navigation
The present invention relates to the field of dynamic content creation and management and more particularly to dynamically create and insert immersive promotional content in a multimedia. The multimedia requested by a user is procured from a media server ( 105 ) and the one or more objects present in the multimedia is determined. The content of the multimedia is analyzed, and a decision is taken to immerse the promotional content in the multimedia based on the analysis of the multimedia. Further, a promotional content is created in real time using the components present in the asset database ( 106 ) based on the personalized user profile. The created promotional content is overlaid and blended with a at least one object from the one or more objects in the multimedia. The created promotional content and the multimedia is joined to form a composite media and is streamed to the user device.
1. A method of generating enhanced video by removing fog for vehicle navigation, wherein the method comprises:
identifying, by an image enhancing unit, a Region of Interest (ROI) in a plurality of frames extracted from a captured video associated with a vehicle;
computing, by the image enhancing unit, a plurality of function parameters indicative of variation of saturation across the plurality of frames for the identified ROI;
modifying, by the image enhancing unit, the plurality of function parameters across the plurality of frames for the identified ROI, based on a speed of the vehicle;
enhancing, by the image enhancing unit, a saturation value in a new frame received subsequent to the plurality of frames of the captured video, based on the modified plurality of function parameters across the plurality of frames to obtain an enhanced video, wherein the enhanced saturation value is further dynamically tuned by updating the plurality of function parameters; and
navigating, by the image enhancing unit, the vehicle based on the enhanced video.
2. The method of claim 1 , wherein the identifying the ROI comprises:
generating boundaries of one or more objects in each frame of the plurality of frames;
extracting the one or more objects by filling pixels within the generated boundaries having same energy as compared with seed pixels; and
identifying the extracted one or more objects based on a trained image classifier.
3. The method of claim 1 , wherein the identified ROI comprises at least one of a road region, a plurality of road signs, one or more traffic signals, a natural object, or one or more other vehicles.
4. The method of claim 1 , wherein the computing the plurality of function parameters comprises;
determining a mean saturation for a plurality of dominated hue components in the determined ROI across the plurality of frames; and
fitting a function for the determined mean saturation across the plurality of frames for computing the plurality of function parameters.
5. The method of claim 1 , wherein the modifying the plurality of function parameters comprises:
determining speed variation of the vehicle;
calculating number of frames captured based on the determined speed variation of the vehicle; and
modifying the plurality of function parameters based on the calculated number of frames.
6. The method of claim 1 , wherein the enhancing the saturation value in the new frame comprises:
computing initial saturation of the corresponding ROI; and
updating the initial saturation based on the plurality of function parameters and the calculated number of frames.
7. An image enhancing unit, for generating enhanced video by removing fog for vehicle navigation comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores the processor instructions, which, on execution, causes the processor to:
identify a Region of Interest (ROI) in a plurality of frames extracted from a captured video associated with a vehicle;
compute a plurality of function parameters indicative of variation of saturation across the plurality of frames for the identified ROI;
modify the plurality of function parameters across the plurality of frames for the identified ROI, based on a speed of the vehicle;
enhance a saturation value in a new frame received subsequent to the plurality of frames of the captured video, based on the modified plurality of function parameters across the plurality of frames to obtain an enhanced video, wherein the enhanced saturation value is further dynamically tuned by updating the plurality of function parameters; and
navigate the vehicle based on the enhanced video.
8. The image enhancing unit of claim 7 , wherein the processor is configured to identify the ROI comprises:
generating boundaries of one or more objects in each frame of the plurality of frames;
extracting the one or more objects by filling pixels within the generated boundaries having same energy as compared with seed pixels; and
identifying the extracted one or more objects based on a trained image classifier.
9. The image enhancing unit of claim 7 , wherein the identifying ROI includes at least one of a road region, a plurality of road signs, one or more traffic signals, a natural object, or one or more other vehicles.
10. The image enhancing unit of claim 7 , wherein the processor is configured to compute the plurality of function parameters comprises:
determining a mean saturation for a plurality of dominated hue components in the determined ROI across the plurality of frames; and
fitting a function for the determined mean saturation across the plurality of frames for computing the plurality of function parameters.
11. The image enhancing unit of claim 7 , wherein the processor is configured to modify the plurality of function parameters comprises:
determining speed variation of the vehicle;
calculating number of frames captured based on the determined speed variation of the vehicle; and
modifying the plurality of function parameters based on the calculated number of frames.
12. The image enhancing unit of claim 7 , wherein the processor is configured to enhance a saturation value in new frame comprises:
computing initial saturation of the corresponding ROI; and
updating the initial saturation based on the plurality of function parameters and the calculated number of frames.
13. A non-transitory computer readable medium including instructions stored thereon for generating enhanced video by removing fog for vehicle navigation that when processed by at least one processor cause a device to perform operations comprising:
identifying a Region of Interest (ROI) in a plurality of frames extracted from a captured video associated with a vehicle;
computing a plurality of function parameters indicative of variation of saturation across the plurality of frames for the identified ROI;
modifying the plurality of function parameters across the plurality of frames for the identified ROI, based on a speed of the vehicle;
enhancing a saturation value in a new frame received subsequent to the plurality of frames of the captured video, based on the modified plurality of function parameters across the plurality of frames to obtain an enhanced video, wherein the enhanced saturation value is further dynamically tuned by updating the plurality of function parameters; and
navigating the vehicle based on the enhanced video.