WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Efficient track linking methods for track graphs using network-flow and set-cover techniques
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Coupling detection and data association for multiple object tracking
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
| Hi-index | 0.00 |
Analysis of bird and bat flight with computer vision algorithms provides a new perspective on how animals move through three-dimensional space. This is important for understanding the intricacies of flight and the interactions of airborne animals that fly in groups. Results can be applied to a large array of tasks, for example, bio-inspired engineering of airplanes [3] and censusing of populations of bats [1], [2], [6]. Censusing populations of bats is imperative for quantifying the ecological and economic impact of these animals on terrestrial ecosystems [5]. Colonies of Brazilian free-tailed bats are of particular interest because they represent some of the largest aggregations of mammals known to mankind. It is challenging to census these bats accurately, since they emerge in large numbers at night from their day-time roosting sites. We have used infrared thermal cameras to record Brazilian free-tailed bats in California, Massachusetts, New Mexico, and Texas, and developed automated image analysis methods that detect, track, and count emerging bats [1]. We have developed guidelines of camera setup and calibration procedures in the field [7]. Our computer vision algorithms use stereography to analyze the three-dimensional flight paths of bats and birds. Our techniques include detection of individual animals in each camera view, reconstruction of their positions in three-dimensional space, across-time and across-space data association and multiple-object tracking [3], [8]-[11]. We found that six colonies of Brazilian free-tailed bats in the southwestern United States may have plummeted from 54 million members to 4 million since 1957 [2]. Analysis of emergence flights from dusk through darkness also revealed patterns in group behavior. Flow patterns of bats during emergence flights exhibited characteristic single or multiple episodes. A consistent rhythmic pattern of flow episodes and pauses was revealed across colonies and was independent of emergence tempo.