Methods of occupancy state determination and computer programs

Method of constructing a weighted characteristic matrix for use in at least one of defining and determining occupancy states for at least one space comprising the steps of:

• (a) obtaining at least one signal, from at least one of a first type of sensor, characteristic of said space having therein a predetermined configuration of objects, said characteristic signal defining a first sensor space-empty signal profile;
• (b) processing said at least one first sensor signal to generate a plurality of first sensor space-empty feature signals;
• (c) obtaining at least one signal from at least one of a second type of sensor characteristic of said space-empty state defining a second sensor space-empty signal profile;
• (d) processing said at least one second sensor signal to generate a plurality of second sensor space-empty feat signals;
• (e) fusing a plurality of said space-empty feature signals selected from said first and said second space-empty feature signals to produce at least one fused feature signal having at least one characteristic value defining a space-empty state;
• (f) repeating steps (a)-(e) on each member of a plurality of known objects in said space to produce a corresponding plurality of fused feature signal characteristic values each of which corresponds to at least one of said known objects associated therewith defining a series of space-occupied states;
• (g) ordering said characteristic known state values in a confidence weighted matrix of occupancy state values;
• (h) storing said matrix for comparison to fused feature signal values of at least one sensed unknown object to generate probability confidence levels selected from at least one of the nature and location of said sensed unknown object in said space.

A method of constructing a multidimensional confidence criteria matrix to represent a variety of occupancy states involving different types and positions of occupants of an automobile seat, comprising:

• (a) obtaining a plurality of data sets from a plurality of sensors under a plurality of different occupant type and position combinations;
• (b) combining elements of said data sets to generate a weighted confidence level correlating a probability that each such element represents a particular occupant type and position combination;
• and
• (c) assigning each of the confidence levels determined in step (b) to a position in a multidimensional confidence criteria matrix corresponding to a particular sensor and a particular occupant type and position combination.