Automatic Bird Species Filtering Using a Multimodel Approach

We report a filtering algorithm for bird species detection using videos captured by uncalibrated moving cameras, a typical characteristic of crowd sourced videos. The algorithm tracks both body and wing motion dimensions of a flying bird to form signatures for species filtering. In the body model, we consider both cases when background motion introduced by the camera can and cannot be directly recognized using key point matching. We are also able to recover intrinsic camera parameters in the body motion tracking. In the wing model, we consider both periodic wing flapping and gliding motion patterns. These models are combined to form a multimodel framework. We have tested the algorithm and compared its performance with single model approaches in physical experiments. Results show that the new algorithm significantly reduces the false positive rate, while maintaining a low false negative rate. The area under ROC curve is 92.86%.

[1]  Dezhen Song,et al.  System and algorithms for an autonomous observatory assisting the search for the Ivory-Billed Woodpecker , 2008, 2008 IEEE International Conference on Automation Science and Engineering.

[2]  Jinhai Cai,et al.  Sensor Network for the Monitoring of Ecosystem: Bird Species Recognition , 2007, 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information.

[3]  Margrit Betke,et al.  Tracking Large Variable Numbers of Objects in Clutter , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Dezhen Song,et al.  Automatic bird species detection using periodicity of salient extremities , 2013, 2013 IEEE International Conference on Robotics and Automation.

[5]  Rama Chellappa,et al.  Shape-and-Behavior Encoded Tracking of Bee Dances , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  M. Dunn,et al.  Machine Vision Classification of Animals , 2003 .

[7]  Vincent Lepetit,et al.  Stable real-time 3D tracking using online and offline information , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Hans-Joachim Wünsche,et al.  Monocular model-based 3D vehicle tracking for autonomous vehicles in unstructured environment , 2011, 2011 IEEE International Conference on Robotics and Automation.

[9]  David A. Forsyth,et al.  Using temporal coherence to build models of animals , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[10]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[11]  Javier Civera,et al.  Interacting multiple model monocular SLAM , 2008, 2008 IEEE International Conference on Robotics and Automation.

[12]  Tianshu Liu,et al.  Avian Wing Geometry and Kinematics , 2006 .

[13]  Dezhen Song,et al.  A Low False Negative Filter for Detecting Rare Bird Species From Short Video Segments Using a Probable Observation Data Set-Based EKF Method , 2010, IEEE Transactions on Image Processing.

[14]  Dezhen Song,et al.  Automatic Bird Species Detection From Crowd Sourced Videos , 2014, IEEE Transactions on Automation Science and Engineering.

[15]  Subhash Challa,et al.  Vision based data fusion for autonomous vehicles target tracking using interacting multiple dynamic models , 2008, Comput. Vis. Image Underst..

[16]  S.S. Blackman,et al.  Multiple hypothesis tracking for multiple target tracking , 2004, IEEE Aerospace and Electronic Systems Magazine.

[17]  Lang Hong,et al.  Multirate interacting multiple model particle filter for terrain-based ground target tracking , 2006 .

[18]  R. F.,et al.  Mathematical Statistics , 1944, Nature.

[19]  T. Burghardt,et al.  Analysing animal behaviour in wildlife videos using face detection and tracking , 2006 .

[20]  Colin J Pennycuick,et al.  Predicting Wingbeat Frequency and Wavelength of Birds , 1990 .

[21]  C. Pennycuick,et al.  Speeds and wingbeat frequencies of migrating birds compared with calculated benchmarks. , 2001, The Journal of experimental biology.

[22]  Miguel A. Olivares-Méndez,et al.  3D pose estimation based on planar object tracking for UAVs control , 2010, 2010 IEEE International Conference on Robotics and Automation.

[23]  Steven G Hall,et al.  A Comparison of Image Processing Techniques for Bird Recognition , 2006, Biotechnology progress.

[24]  Li-Chen Fu,et al.  Online 3D tracking of human arms with a single camera , 2012, 2012 IEEE International Conference on Robotics and Automation.

[25]  Neal Finch,et al.  Machine vision classification of animals , 2003 .

[26]  Éric Marchand,et al.  Real-time 3D model-based tracking: combining edge and texture information , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[27]  József Bokor,et al.  Multi-Mode Extended Kalman Filter for Aircraft Attitude Estimation* , 2011 .

[28]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[29]  Amir Averbuch,et al.  Interacting Multiple Model Methods in Target Tracking: A Survey , 1988 .

[30]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .