Abstract: A method and system for rendering object detection graphics on image frames is disclosed. The method includes receiving an object detection information for an image frame. The object detection information includes bounding box data and a class label data associated with an object in the image frame. The method further includes determining a first value for each pixel in a first set of pixels associated with a bounding box for the object and determining a second value for each pixel in a second set of pixels associated with a class label for the object. The method includes modifying values for each of the first set of pixels based on the associated first value to render the bounding box on the image frame and modifying values for each of the second set of pixels based on the associated second value to render the class label on the image frame.

Abstract: The disclosure relates to method and system for image scaling. The method includes determining a nature of image scaling required to be performed on an input image based on a vertical scaling ratio and a horizontal scaling ratio and includes determining if the image scaling is an upscaling or a downscaling, a symmetric scaling or an asymmetric scaling. The method further includes determining an overall scaling ratio based on a lower or an equal of the vertical scaling ratio and the horizontal scaling ratio. The method further includes scaling an input image to a target image using a polyphase finite impulse response (FIR) scaling filter based on the nature of the image scaling, the overall scaling ratio, and a structure of the polyphase FIR scaling filter. The scaling includes dynamically performing at least one of duplication of lines, addition of filler lines, duplication of pixels, and addition of filler pixels.

Abstract: A method and system for rendering object detection graphics on image frames is disclosed. The method includes receiving an object detection information for an image frame. The object detection information includes bounding box data and a class label data associated with an object in the image frame. The method further includes determining a first value for each pixel in a first set of pixels associated with a bounding box for the object and determining a second value for each pixel in a second set of pixels associated with a class label for the object. The method includes modifying values for each of the first set of pixels based on the associated first value to render the bounding box on the image frame and modifying values for each of the second set of pixels based on the associated second value to render the class label on the image frame.