Fig 1.
Fish move in a rectangular container full of water. Three synchronized cameras capture swimming behavior from one top-view and two side-view directions. Each pair of the three directions are vertical to one another.
Fig 2.
The main skeleton obtained using different thresholds Tu.
With an increase in the value of threshold Tu, the obtained skeleton can better represent the main structure of the motion region while ignoring more details. (a) Top view. (b) Side view.
Fig 3.
(a) Fish appearance model. The blue line represents the main skeleton of fish. The endpoints of the skeleton are located at the head and tail, respectively. (b) Double feature point model (DFPM). The model consists of the central feature point and head feature point. (c) Three feature point model (TFPM). The model consists of the central feature point and two skeleton endpoints.
Fig 4.
Illustration of the epipolar constraint.
Regarding the projected point p1 in view v1, the projected point p2 in view v2 which corresponds to p1 is located in the epipolar line l2 of p1.
Fig 5.
The dashed arrows indicate the epipolar lines. An object in the top view can find k candidates on corresponding epipolar line at frame t. The matching object is determined by the maximum matching length of two trajectories under the epipolar constraint.
Fig 6.
Illustration of motion association.
(a) Motion association for DFPM. (b) Model simplification for TFPM.
Fig 7.
Example of matching association.
Table 1.
Parameter settings in the experiments.
Fig 8.
Tracking results on different data sets.
(a) 5 fish. (b) 10 fish.
Table 2.
Performance comparison of the proposed method and other two methods.
Fig 9.
Two examples of inverted images.
The red dotted circles represent the inverted images of the objects. (a) Top view. (b) Side view.
Table 3.
Tracking results of the proposed method on different views.