Object detection in an image

A method of performing, by an image processing device, object detection in an image comprising:

• performing one or more tests of a test sequence for detecting a first object, on pixel values of a plurality of at least partially overlapping sub-regions of a first search window;
• generating a cumulative score based on results of said one or more tests on said plurality of sub-regions;
• comparing said cumulative score with a threshold value;
• when the cumulative score is greater than the threshold, performing one or more of said tests of said test sequence on at least one further sub-region of said first search window, said at least one further sub-region at least partially overlapping each of said plurality of sub-regions;
• and
• when the cumulative score is not greater than said threshold, performing one or more tests of said test sequence on a plurality of at least partially overlapping sub-regions of a second search window, wherein said second search window is offset with respect to the first search window by a plurality of pixels in at least one direction.

An image processing device comprising:

• a memory storing an image;
• and
• a processing device programmed to:
• perform one or more tests of a test sequence for detection of a first object on pixels values of a plurality of at least partially overlapping sub-regions of a first search window;
• generate a cumulative score based on results of the one or more tests on the plurality of sub-regions;
• compare the cumulative score with a threshold value;
• when the cumulative score is greater than the threshold, perform one or more of the tests of the test sequence on at least one further sub-region of the first search window, the at least one further sub-region at least partially overlapping each of the plurality of sub-regions;
• and
• when the cumulative score is not greater than the threshold, perform one or more tests of the test sequence on a plurality of at least partially overlapping sub-regions of a second search window, wherein the second search window is offset with respect to the first search window by a plurality of pixels in at least one direction.

A method of performing, by an image processing device, object detection in an image comprising:

• receiving the image;
• storing the image in a first memory;
• performing the following operations by running instructions on a processor:
• performing one or more tests of a test sequence for detecting a first object, on pixel values of a plurality of at least partially overlapping sub-regions of a first search window;
• generating a cumulative score based on results of said one or more tests on said plurality of sub-regions;
• comparing said cumulative score with a threshold value;
• and
• based on said comparison, either performing one or more tests of said test sequence on at least one further sub-region of said first search window or skipping said tests on a remainder of untested at least partially overlapping sub-regions of said first search window, said at least one further sub-region at least partially overlapping each of said plurality of sub-regions;
• and
• providing an indication of the detected object.

A device for performing object detection in an image comprising:

• means for storing said image;
• means for performing one or more tests of a test sequence for detection of a first object on pixels values of a plurality of at least partially overlapping sub-regions of a first search window;
• means for generating a cumulative score based on results of said one or more tests on said plurality of sub-regions;
• means for comparing said cumulative score with a threshold value;
• and
• means for, based on said comparison, either performing one or more tests of said test sequence on at least one further sub-region of said first search window or skipping said tests on a remainder of untested at least partially overlapping sub-regions of said first search window, said at least one further sub-region at least partially overlapping each of said plurality of sub-regions.