Providing virtual inserts using image tracking with camera and position sensors

A processor-implemented method for processing image data, comprising the processor-implemented steps of:

• obtaining an image of a live event, the image includes a pixel representation of an object which is moving in the live event, the object have an appearance, and the image is captured at a point in time in the live event by at least one camera;
• determining an orientation of the object in the live event for the point in time;
• determining a position of the object in the live event for the point in time;
• based on the position, determining a distance between the at least one camera and the object for the point in time;
• based on the distance and a zoom setting of the at least one camera, estimating a size of the pixel representation of the object in the image;
• based on the position and registration data of the at least one camera, estimating a position of the pixel representation of the object in the image;
• providing a template comprising a model which mimics the appearance of the object, the model has an orientation which corresponds to the determined orientation of the object, and the template has a size which corresponds to the estimated size of the pixel representation of the object in the image;
• and
• detecting the pixel representation of the object in the image by correlating the template with different candidate pixel representations of the object in the image to select an optimum candidate pixel representation of the object in the image, the candidate pixel representations are based on the estimated position of the pixel representation of the object in the image.