To Sandra iii Acknowledgements I would like to thank my advisor Professor Narendra Ahuja for sharing his wisdom with me, and the members of the Beckman Institute Computer Vision and Robotics Lab for creating the stimulating and supportive environment in the group. I am also very grateful to Professors David Kriegman, Michael Garland, and Yizhou Yu for their suggestions and criticisms that helpe...

Current state-of-the-art human action recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. In this work we address the problem of action localisation and instance segmentation in which multiple concurrent actions of the same class may be segmented out of an image sequence. We cast the action tube extraction as an energy maximisatio...

This paper presents a new adaptive binarization technique for degraded hand-held camera-captured document images. The state-of-the-art locally adaptive binarization methods are sensitive to the values of free parameter. This problem is more critical when binarizing degraded camera-captured document images because of distortions like non-uniform illumination, bad shading, blurring, smearing and ...

BACKGROUND AND AIMS Basmati rice grown in the Indian subcontinent is highly valued for its unique culinary qualities. Production is, however, often constrained by diseases such as bacterial blight (BB), blast and sheath blight (ShB). The present study developed Basmati rice with inbuilt resistance to BB, blast and ShB using molecular marker-assisted selection. METHODOLOGY The rice cultivar 'I...

We propose an efficient way to account for spatial smoothness in foreground-background segmentation of video sequences. Most statistical background modeling techniques regard the pixels in an image as independent and disregard the fundamental concept of smoothness. In contrast, we model smoothness of the foreground and background with a Markov random field, in such a way that it can be globally...

BACKGROUND Blast caused by the fungus Magnaporthe oryzae is a significant disease threat to rice across the world and is especially prevalent in Malaysia. An elite, early-maturing, high-yielding Malaysian rice variety, MR263, is susceptible to blast and was used as the recurrent parent in this study. To improve MR263 disease resistance, the Pongsu Seribu 1 rice variety was used as donor of the ...

This paper presents an approach for evaluating multiple color histograms during object tracking. The method adaptively selects histograms that well distinguish foreground from background. The variance ratio is utilized to measure the separability of object and background and to extract top-ranked discriminative histograms. Experimental results demonstrate how this method adapts to changing appe...

We present a catalog of 49 spectroscopic strong gravitational lens candidates selected from a Sloan Digital Sky Survey sample of 50996 luminous red galaxies. Potentially lensed star-forming galaxies are detected through the presence of background oxygen and hydrogen nebular emission lines in the spectra of these massive foreground galaxies. This multiline selection eliminates the ambiguity of s...

We introduce a new approach to perform background subtraction in moving camera scenarios. Unlike previous treatments of the problem, we do not restrict the camera motion or the scene geometry. The proposed approach relies on Bayesian selection of the transformation that best describes the geometric relation between consecutive frames. Based on the selected transformation, we propagate a set of ...

This work presents a new robust PCA method for foreground-background separation on freely moving camera video with possible dense and sparse corruptions. Our proposed method registers the frames of the corrupted video and then encodes the varying perspective arising from camera motion as missing data in a global model. This formulation allows our algorithm to produce a panoramic background comp...