Techniques for detecting spatial anomalies in video content

One or more non-transitory computer readable media including instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:

• computing a first distribution of first-degree pixel intensity gradients associated with a first pixel based on a first frame of video content;
• computing a second distribution of second-degree pixel intensity gradients associated with the first pixel based on the first frame;
• computing a first statistical distance between the first distribution of first-degree pixel intensity gradients and the second distribution of second-degree pixel intensity gradients, including:
• calculating a mean difference vector based on the first distribution of first-degree pixel intensity gradients and the second distribution of second-degree pixel intensity gradients,
• generating a covariance matrix based on the second distribution of second-degree pixel intensity gradients, and
• calculating the first statistical distance based on the mean difference vector and the covariance matrix;
• and
• determining that the first pixel is defective based on the first statistical distance.

A system, comprising:

• one or more memories storing instructions;
• and
• one or more processors that are coupled to the one or more memories and execute the instructions to:
• compute a first plurality of pixel intensity gradients based on a first frame of video content and a first neighborhood of pixels associated with a first pixel;
• compute a second plurality of pixel intensity gradients based on the first frame and a second neighborhood of pixels associated with the first pixel, wherein the second neighborhood is larger than the first neighborhood;
• compute a first statistical distance between the first plurality of pixel intensity gradients and the second plurality of pixel intensity gradients, including instructions to:
• calculate a mean difference vector based on the first plurality of pixel intensity gradients and the second plurality of pixel intensity gradients,
• generate a covariance matrix based on the second plurality of pixel intensity gradients, and
• calculate the first statistical distance based on the mean difference vector and the covariance matrix;
• and
• determine that the first pixel is defective based on the first statistical distance.