Tracking Objects Based on Multiple Particle Filters for Multipart Combined Moving Directions Information

Algorithm 1

Particle filter integrated motion direction.

	Input: Particles pf, Observation image, motion direction
	Output: New particles represent , estimating the state of the object in the observed image.
	Step 1:
	Translate particles in pf by
	Translate particles in pf by
	Translate particles in pf by
	Translate particles in pf by
	Translate particles in pf by
	Translate particles in pf by
	Translate particles in pf by
	Translate particles in pf by
	Step 2:
	for i = 1 to do
	Beginfor
	/∗ (with is i th particle) ∗/
	Get
	Get
	Get
	Calculate
	Calculate by Algorithm 8
	Update weight of i th particle:
	Endfor
	Step 3:
	Calculate the total
	for i = 1 to do
	Beginfor
	Standardize weight
	Endfor
	Step 4: Calculate
	Step 5:
	if then
	Endif
	Step 6: Estimate the state of the object in the kth image by calculating the average of the new set of particles