An Object Recognition Strategy Base upon Foreground Detection

Unmanned aerial vehicles equipped with surveillance system have begun to play an increasingly important role in recent years, which has provided valuable information for us. Object recognition is necessary in processing video information. However, traditional recognition methods based on object segmentation can hardly meet the system demands for running online. In this paper, we have made use of SVM based upon HOG feature descriptors to achieve online recognizing passersby in an UAV platform, and designed an object recognition framework based on foreground detection. In order to accelerate the processing speed of the system, our scheme adopts recognizing objects only in the foreground areas which largely reduces searching scope. In conclusion, our methods can recognize specified objects and have a strong antijamming capability to the background noise.

[1]  Amir Averbuch,et al.  Fast gradient methods based global motion estimation for video compression , 2002, Proceedings. International Conference on Image Processing.

[2]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[3]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  D C Van Essen,et al.  Neural activity in areas V1, V2 and V4 during free viewing of natural scenes compared to controlled viewing , 1998, Neuroreport.

[5]  Manuel Blum,et al.  Peekaboom: a game for locating objects in images , 2006, CHI.

[6]  Tomaso A. Poggio,et al.  A Trainable System for Object Detection , 2000, International Journal of Computer Vision.

[7]  Amir Averbuch,et al.  Fast gradient methods based on global motion estimation for video compression , 2003, IEEE Trans. Circuits Syst. Video Technol..

[8]  William T. Freeman,et al.  Orientation Histograms for Hand Gesture Recognition , 1995 .

[9]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

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

[11]  Mubarak Shah,et al.  Human identity recognition in aerial images , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[13]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  David A. McAllester,et al.  Cascade object detection with deformable part models , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Navneet Dalal,et al.  Finding People in Images and Videos , 2006 .

[16]  David D. Cox,et al.  Untangling invariant object recognition , 2007, Trends in Cognitive Sciences.