Intel Corporation

Stojan Rakic

Zdravko Pantic

Bosko Mihic

Dragomir El Mezeni

Nemanja Tonic

Dusan Zoric

Video stabilization is described using content-aware camera motion estimation. In some versions a luminance target frame and a luminance source frame of a sequence of video frames of a scene are received. Motion is extracted from the received luminance target and source frames and the motion is represented as a motion vector field and weights. The weights are divided into a first set of zeros weights for motion in the motion vector field that is near zero motion and a second set of peak weights for motion in the motion field that is not near zero. The zeros weights are compared to a threshold to determine whether there is motion in the scene and if the zeros weights exceed the threshold then selecting a zero motion motion model. A frame of the video sequence is adjusted corresponding to the target frame based on the selected motion model.

Video stabilization using content-aware camera motion estimation

Techniques are provided for spatially adaptive tone mapping for display or reproduction of HDR images on devices with lower dynamic range capability. An example system may include a log-conversion circuit to convert luminance data, from a received image, to a logarithm domain. The system may also include an edge-aware filter circuit to decompose the log domain luminance data into a base layer, a small scale detail layer, and a large scale detail layer. The system may further include an amplitude adjustment circuit to shift and scale data amplitudes in each of the layers to a selected range and a linear-conversion circuit to convert the adjusted layers from the log domain back to the linear domain. The system may further include a tone compression circuit to generate compressed linear domain layers and a luminance data reconstruction circuit to generate compressed luminance data based on the compressed linear domain layers.

Growing community of inventors

Belgrade, Republic of Serbia

Stojan Rakic