AbstractsComputer Science

Rotation Invariant Histogram Features for Object Detection and Tracking in Aerial Imagery

by Alex Mathew

Institution: University of Dayton
Department: Electrical Engineering
Degree: PhD
Year: 2014
Keywords: Electrical Engineering; Computer Science; Computer Engineering; Engineering; Rotation invariant feature; Aerial object detection; Pattern recognition; Object detection; Object tracking; Integral DFT
Record ID: 2027712
Full text PDF: http://rave.ohiolink.edu/etdc/view?acc_num=dayton1397662849


Object detection and tracking in imagery captured by aerial systems are becoming increasingly important in computer vision research. In aerial imagery, objects can appear in any orientation, varying sizes and in different lighting conditions. Due to the exponential growth in sensor technology, increasing size and resolution of aerial imagery are becoming a challenge for real-time computation. A rotation invariant feature extraction technique for detecting and tracking objects in aerial imagery is presented in this dissertation. Rotation invariance in the feature representation is addressed by considering concentric circular regions centered at visually salient locations of the object. The intensity distribution characteristics of the object region are used to represent an object effectively. A set of intensity-based features is derived from intensity histograms of the circular regions and they are inherently rotation invariant. An integral histogram computation approach is used to compute these features efficiently. To improve the representational strength of the feature set for rotation and illumination-invariant object detection, a gradient-based feature set is derived from normalized gradient orientation histograms of concentric regions. Rotation invariance is achieved by considering the magnitude of the Discrete Fourier Transform (DFT) of the gradient orientation histograms. A novel computational framework called Integral DFT is presented for fast and efficient extraction of gradient-based features in large imagery. A part-based model, which relies on a representation of an object as an aggregation of significant parts, using the gradient-based features is also presented in this dissertation. Integrating the features of significant parts gives robustness to partial occlusions and slight deformations, thus leading to a better object representation. The effectiveness of the intensity-based feature is demonstrated in tracking objects in Wide Area Motion Imagery (WAMI) data. The object detection capability of the gradient-based feature extraction technique is evaluated on three different types of targets in low altitude aerial imagery. It is observed that the speed of computation is several times faster than state-of-the-art methods while maintaining comparable detection accuracies. Research work is continuing to automatically identify significant parts of an object to build the part-based model. Another direction of this research is to use the gradient-based rotation invariant features for scene matching.