kapitel 11 tracking – p. 1 tracking fundamentals object representation object detection object...

Kapitel 11 “Tracking” – p. 1

Tracking

Fundamentals Object representation Object detection Object tracking (Point, Kernel, Silhouette) Articulated tracking

A. Yilmaz, O. Javed, and M. Shah: Object tracking: A survey. ACM

Computing Surveys, Vol. 38, No. 4, 1-45, 2006

Kapitel 11


Fundamentals (1)


Fundamentals (2)

Applications of object tracking:

motion-based recognition: human identification based on gait, automatic object detection, etc.

automated surveillance: monitoring a scene to detect suspicious activities or unlikely events

video indexing: automatic annotation and retrieval of videos in multimedia databases

human-computer interaction: gesture recognition, eye gaze tracking for data input to computers, etc.

traffic monitoring: real-time gathering of traffic statistics to direct traffic flow

vehicle navigation: video-based path planning and obstacle avoidance capabilities


Fundamentals (3)

Tracking task:

In the simplest form, tracking can be defined as the problem of estimating the trajectory of an object in the image plane as it moves around a scene. In other words, a tracker assigns consistent labels to the tracked objects in different frames of a video. Additionally, depending on the tracking domain, a tracker can also provide object-centric information, such as orientation, area, or shape of an object.

Two subtasks:

• Build some model of what you want to track

• Use what you know about where the object was in the previous frame(s) to make predictions about the current frame and restrict the search

Repeat the two subtasks, possibly updating the model


Fundamentals (4)

Tracking objects can be complex due to:

loss of information caused by projection of 3D world on 2D image noise in images complex object shapes / motion nonrigid or articulated nature of objects partial and full object occlusions scene illumination changes real-time processing requirements

Simplify tracking by imposing constraints: Almost all tracking algorithms assume that the object motion is

smooth with no abrupt changes The object motion is assumed to be of constant velocity Prior knowledge about the number and the size of objects, or the

object appearance and shape


Object represention (1)

Object representation = Shape + Appearance

Shape representations:

Points. The object is represented by a point, that is, the centroid or by a set of points; suitable for tracking objects that occupy small regions in an image

Primitive geometric shapes. Object shape is represented by a rectangle, ellipse, etc. Object motion for such representations is usually modeled by translation, affine, or projective transformation. Though primitive geometric shapes are more suitable for representing simple rigid objects, they are also used for tracking nonrigid objects.



Object silhouette and contour. Contour = boundary of an object. Region inside the contour = silhouette. Silhouette and contour representations are suitable for tracking complex nonrigid shapes.

Articulated shape models. Articulated objects are composed of body parts (modelled by cylinders or ellipses) that are held together with joints. Example: human body = articulated object with torso, legs, hands, head, and feet connected by joints. The relationship between the parts are governed by kinematic motion models, e.g. joint angle, etc.

Skeletal models. Object skeleton can be extracted by applying medial axis transform to the object silhouette. Skeleton representation can be used to model both articulated and rigid objects.



Object representations. (a) Centroid, (b) multiple points, (c) rectangularpatch, (d) elliptical patch, (e) part-based multiple patches, (f) object skeleton, (g) control points on object contour, (h) complete object contour, (i) object silhouette



Appearance representations:

Templates. Formed using simple geometric shapes or silhouettes. Suitable for tracking objects whose poses do not vary considerably during the course of tracking. Self-adapation of templates during the tracking is possibe.

http://www.cs.toronto.edu/vis/projects/dudekfaceSequence.html

Kapitel 11 “Tracking” – p.

Probability densities of object appearance can either be parametric (Gaussian and mixture of Gaussians) or nonparametric (histograms, Parzen estimation)

Characterize an image region by its statistics.If the statistics differ from background, theyshould enable tracking.

• nonparametric: histogram (grayscale or color)

10


Kapitel 11 “Tracking” – p.11


• parametric: 1D Gaussian distribution



• parametric: n-D Gaussian distribution

Centered at (1,3) with a standard deviation of 3 in roughly the (0.878, 0.478) direction and of 1 in the orthogonal direction



• parametric: Gaussian Mixture Models (GMM; Chapter “Bayes Klassifikator“)



Beispiel: Mixture of three Gaussians in 2D space. (a) Contours of constant density for each mixture component. (b) Contours of constant density of mixture distribution p(x). (c) Surface plot of p(x).



Object representations are chosen according to the application

Point representations appropriate for tracking objects, which appear very small in an image (e.g. track distant birds)

For the objects whose shapes can be approximated by rectangles or ellipses, primitive geometric shape representations are more appropriate (e.g. face)

For tracking objects with complex shapes, for example, humans, a contour or a silhouette-based representation is appropriate (surveillance applications)



Feature selection for tracking:

Color: RGB, L u v , L a b , HSV, etc. There is no last word on ∗ ∗ ∗ ∗ ∗ ∗which color space is more effective; a variety of color spaces have been used.

Edges: Less sensitive to illumination changes compared to color features. Algorithms that track the object boundary usually use edges as features. Because of its simplicity and accuracy, the most popular edge detection approach is the Canny Edge detector.

Texture: Measure of the intensity variation of a surface which quantifies properties such as smoothness and regularity

In general, the most desirable property of a visual feature is its uniqueness so that the objects can be easily distinguished in the feature space



Mostly features are chosen manually by the user depending on the application domain. Among all features, color is one of the most widely used for tracking.

Automatic feature selection (see Chapter “Merkmale“):

Filter methods

Wrapper methods

Principal Component Analysis: transformation of a number of (possibly) correlated variables into a smaller number of uncorrelated, linearly combined variables called the principal components


Object detection (1)

Object detection mechanism: required by every tracking method either at the beginning or when an object first appears in the video

Point detectors: find interest points in images which have an expressive texture in their respective localities (Chapter “Detection of Interest Points“)

Segmentation: partition the image into perceptually similar regions



Background subtraction:

Object detection can be achieved by building a representation of the scene called the background model and then finding deviations from the model for each incoming frame. Any significant change in an image region from the background model signifies a moving object. The pixels constituting the regions undergoing change are marked for further processing. Usually, a connected component algorithm is applied to obtain connected regions corresponding to the objects.



Frame differencing of temporally adjacent frames:



Bildsequenz: ≈ 5 Bilder/s



Bildsubtraktion: Variante 1

Schwäche: Doppelbild eines Fahrzeugs (aus dem letzten und aktuellen Bild); Aufteilung einer konstanten Fläche



Bildsubtraktion: Variante 2

Referenzbild fr(r, c): Mittelung einer langen Sequenz von Bildern



Statistical modeling of background:

Learn gradual changes in time by Gaussian, I (x, y) ∼ N(μ(x, y), (x, y)), from the color observations in several consecutive frames. Once the background model is derived for every pixel (x, y) in the input frame, the likelihood of its color coming from N(μ(x, y), (x, y)) is computed.

Example: C. Stauffer and W. Grimson: Learning patterns of activity using real time tracking. IEEE T-PAMI, 22(8): 747-757, 2000.

A pixel in the current frame is checked against the background model by comparing it with every Gaussian in the model until a matching Gaussian is found. If a match is found, the mean and variance of the matched Gaussian is updated, otherwise a new Gaussian with (mean = current pixel color) and some initial variance is used to replace the least probable Gaussian. Each pixel is classified based on whether the matched distribution represents the background process.



Mixture of Gaussian modeling for background subtraction. (a) Image from a sequence in which a person is walking across the scene. (b) The mean of the highest-weighted Gaussians at each pixel position. These means represent the most temporally persistent per-pixel color and hence should represent the stationary background. (c) The means of the Gaussian with the second-highest weight; these means represent colors that are observed less frequently. (d) Background subtraction result. The foreground consists of the pixels in the current frame that matched a low-weighted Gaussian.


Object tracking (1)

Task of detecting the object and establishing correspondence between the object instances across frames can be performed

separately

Possible object regions in every frame are obtained by means of an object detection algorithm, and then the tracker corresponds objects across frames

jointly

The object region and correspondence is jointly estimated by iteratively updating object location and region information obtained from previous frames.


Object tracking (2)


Object tracking (3)

(a) Point Tracking. Objects detected in consecutive frames are represented by points, and a point matching is done. This approach requires an external mechanism to detect the objects in every frame.

(a) Kernel Tracking. Kernel = object shape and appearance. E.g. kernel = a rectangular template or an elliptical shape with an associated histogram. Objects are tracked by computing the motion (parametric transformation such as translation, rotation, and affine) of the kernel in consecutive frames.

(c)+(d) Silhouette Tracking. Such methods use the information encoded inside the object region (appearance density and shape models). Given the object models, silhouettes are tracked by either shape matching (c) or contour evolution (d). The latter one can be considered as object segmentation applied in the temporal domain using the priors generated from the previous frames.


Point tracking (1)

Point correspondence. (a) All possible associations of a point (object) in frame t − 1 with points (objects) in frame t, (b) unique set of associations plotted with bold lines, (c) multi-frame correspondences.


Point tracking (2)

Results of two point correspondence algorithms. (a) Tracking using an algorithm proposed by Veenman et al. 2001 in the rotating dish sequence color segmentation was used to detect black dots on a white dish. (b) Tracking birds using an algorithm proposed by Shafique and Shah 2003; birds are detected using background subtraction.


Kernel tracking (1)

Template Matching: brute force method for tracking single objects

Define a search area

Place the template defined from the previous frame at each position of the search area and compute a similarity measure between the template and the candidate

Select the best candidate with the maximal similarity measure

The similarity measure can be a direct template comparison or statistical measures between two probability densities

Limitation of template matching: high computation cost due to the brute force search limit the object search to the vicinity of its previous position


Kernel tracking (2)

Direct comparison: between template t(i,j) and candidate g(i,j)

Bhattacharyya measure (metric) between two distributions:


Kernel tracking (3)

Example: Eye tracking (direct grayvalue comparison)


Kernel tracking (4)

Example: Head tracking (C/C++ source code available at: http://robotics.stanford.edu/~birch/headtracker/)

S. Birchfield: Elliptical head tracking using intensity gradients and color histograms. Proc. of CVPR, 232-237, 1998


Kernel tracking (5)

Gradient module: gs(i) is the intensity gradient at perimeter pixel i of the ellipse at each hypothesized location s

Color module: histogram intersection between model histogram M and image histogram I at each hypothesized location s (see Chapter “Inhaltsbasierte Suche in Bilddatenbanken”)


Kernel tracking (6)

Efficient template matching:

H. Schweitzer, J.W. Bell, F. Wu: Very fast template matching. Proc. of ECCV (4): 358-372, 2002

H. Schweitzer, R.A. Deng, R.F. Anderson: A dual-bound algorithm for very fast and exact template matching. IEEE-TPAMI, 33(3): 459-470, 2011


Kernel tracking (7)

Mean-shift tracking (instead of brute force search). (a) estimated object location at time t − 1, (b) frame at time t with initial location estimate using the previous object position, (c), (d), (e) location update using mean-shift iterations, (f) final object position at time t.

D. Comaniciu, V. Ramesh, and P. Meer: Kernel-based object tracking. IEEE-TPAMI, 25, 564–575, 2003 (mean shift tracking)


Kernel tracking (8)

Target model: represented by its pdf q in the feature space

Target candidate defined at location y: characterized by its pdf p(y)

To satisfy the low-computational cost imposed by real-time processing, discrete densities, i.e., m-bin histograms are used


Kernel tracking (9)

Bhattacharyya coefficient


Kernel tracking (10)

Weights:

Kronecker delta function:

Function b: R2 {1, …, m} associates to pixel xi the index b(xi) of its bin in the histogram



Mean shift:

xi, i=1, …, nh: pixel locations of the target candidate

g = -k‘(x) k(x): kernel function assigns smaller weights to pixels farther from the center



Example: The subject turning away (frame 150), in-plane rotations of the head (frame 498), and foreground/background saturation due to back-lighting (frame 576). The tracked face is shown in the small upper-left window.

frames 39, 150, 163, 498, 576, and 619



Football sequence, tracking player number 75. The frames 30, 75, 105, 140, and 150 are shown.



Surface obtained by computing the Bhattacharyya coefficient for the 81x81 pixels rectangle marked in frame 105. The target model (the elliptical region selected in frame 30) has been compared with the target candidates obtained by sweeping in frame 105 the elliptical region inside the rectangle. Instead of an exhaustive search in the rectangle to find the maximum, the mean shift algorithm converged in four iterations.


Silhouette tracking (1)

Objects may have complex shapes, e.g. hands, head, and shoulders that cannot be well described by simple geometric shapes. Silhouette-based methods provide an accurate shape description for these objects.

Shape matching

search for the object silhouette in the current frame

Contour tracking

evolve an initial contour to its new position in the current frame, e.g. by minimization of some energy functional



Shape matching:

Distance transform based matchingChapter “Binärisierung und Verarbeitung von binären Bildern“

The silhouette is assumed to only translate from the current frame to the next, therefore nonrigid object motion is not explicitly handled



Contour evolution: iteratively evolve an initial contour in the previous frame to its new position in the current frame. This technique requires that some part of the object in the current frame overlaps with the object region in the previous frame. (see also Chapter “Bildsegmentierung: Detektion komplexer Konturen”)

Example: Mansouri: Region tracking via level set pdes without motion computation. IEEE-TPAMI, 24(7): 947-961, 2002



Example: A. Yilmaz, X. Li, M. Shah: Contour based object tracking with occlusion handling in video acquired using mobile cameras. IEEE-TPAMI, 26(11):1531-1536, 2004

(a) tracking of a tennis player, (b) tracking in presence of occlusion


Articulated tracking

D. Ramanan, D.A. Forsyth, A. Zisserman: Tracking People by Learning their Appearance. IEEE-TPAMI, 29(1): 65-81, 2007(http://www.ics.uci.edu/~dramanan/papers/pose/index.html)

kapitel 11 tracking – p. 1 tracking fundamentals object representation object detection object...

Documents