Tracking - Introduction to Video and Image Processing - page 133

that the model for a particular object is very likely to change over time and should
therefore be updated from image to image. The simple solution is to replace the
model with the detection, but this is dangerous since the detection could be incorrect.
A gradual update scheme, like in Eq. 9.3 , is therefore suggested.

9.4 Further Information

An excellent way of implementing the predict-match-update framework is through
the Kalman filter [19]. It does not cover the detection and matching blocks, but it has
built-in mechanisms for updating the state based on the detections, the predictions
and the related uncertainties. When is comes to tracking noisy detections, a branch
of methods exist, which do not only predict where the objects are most likely to
be, but also predict a number of likely hypotheses and maintain those over time.
Such methods are known as Particle Filters, the Condensation algorithm, Sequential
Monte Carlo filtering, or Multiple Hypothesis filters. One place to start a journey
into such methods is [11].
Color features can be improved by also including information about position.
One such method is the color correlogram [20]. But when it comes to more advanced
tracking, texture is often preferred over color. A good tracking framework based on
texture is the KLT-tracker [16]. It finds candidate rectangles containing a high level
of texture and tracks these rectangles over time. The rectangles are small and a
number of these should therefore be used to track a large object. The tracker detects
when the texture of a particular rectangle has changed too much compared to when
it was initiated and the tracker then reinitializes a new rectangle to be tracked.
If the texture changes too much between two images, template matching-based
methods will not suffice and more advanced methods are required. A good example
is the SIFT algorithm [13]. It represents the pixels in a rectangle by their gradient
information. This is done in a clever way making the representation invariant to ro-
tation and scale. In Fig. 9.10 an example is shown where the object is standing still,
but the camera is moving. This is equivalent to when the camera is fixed and the
object is moving. The SIFT algorithm is here used to find and track 100 points be-
tween two images. Note that such approaches often refer to the process of relocating
features as finding the correspondence rather than tracking.

9.5 Exercises

Exercise 1: Explain the following concepts: state vector, trajectory, prediction, mo-
tion model, tracking, tracking-by-detection, data association, predict-match-update
framework.