Earlier version of an indigenously developed Pressure Wave Generator (PWG) could not develop the ... more Earlier version of an indigenously developed Pressure Wave Generator (PWG) could not develop the necessary pressure ratio to satisfactorily operate a pulse tube cooler, largely due to high blow by losses in the piston cylinder seal gap and due to a few design deficiencies. Effect of different parameters like seal gap, piston diameter, piston stroke, moving mass and the piston back volume on the performance is studied analytically. Modifications were done to the PWG based on analysis and the performance is experimentally measured. A significant improvement in PWG performance is seen as a result of the modifications. The improved PWG is tested with the same pulse tube cooler but with different inertance tube configurations. A no load temperature of 130 K is achieved with an inertance tube configuration designed using Sage software. The delivered PV power is estimated to be 28.4 W which can produce a refrigeration of about 1 W at 80 K.
Light Field (LF) offers unique advantages such as post-capture refocusing and depth estimation, b... more Light Field (LF) offers unique advantages such as post-capture refocusing and depth estimation, but low-light conditions severely limit these capabilities. To restore low-light LFs we should harness the geometric cues present in different LF views, which is not possible using single-frame low-light enhancement techniques. We, therefore, propose a deep neural network architecture for Low-Light Light Field (L3F) restoration, which we refer to as L3Fnet. The proposed L3Fnet not only performs the necessary visual enhancement of each LF view but also preserves the epipolar geometry across views. We achieve this by adopting a two-stage architecture for L3Fnet. Stage-I looks at all the LF views to encode the LF geometry. This encoded information is then used in Stage-II to reconstruct each LF view. To facilitate learning-based techniques for low-light LF imaging, we collected a comprehensive LF dataset of various scenes. For each scene, we captured four LFs, one with near-optimal exposure and ISO settings and the others at different levels of low-light conditions varying from low to extreme low-light settings. The effectiveness of the proposed L3Fnet is supported by both visual and numerical comparisons on this dataset. To further analyze the performance of low-light reconstruction methods, we also propose an L3F-wild dataset that contains LF captured late at night with almost zero lux values. No ground truth is available in this dataset. To perform well on the L3F-wild dataset, any method must adapt to the light level of the captured scene. To do this we propose a novel pre-processing block that makes L3Fnet robust to various degrees of low-light conditions. Lastly, we show that L3Fnet can also be used for low-light enhancement of singleframe images, despite it being engineered for LF data. We do so by converting the single-frame DSLR image into a form suitable to L3Fnet, which we call as pseudo-LF.
We present a novel approach to optimally retarget videos for varied displays with differing aspec... more We present a novel approach to optimally retarget videos for varied displays with differing aspect ratios by preserving salient scene content discovered via eye tracking. Our algorithm performs editing with cut, pan and zoom operations by optimizing the path of a cropping window within the original video while seeking to (i) preserve salient regions, and (ii) adhere to the principles of cinematography. Our approach is (a) content agnostic as the same methodology is employed to re-edit a wide-angle video recording or a close-up movie sequence captured with a static or moving camera, and (b) independent of video length and can in principle re-edit an entire movie in one shot. Our algorithm consists of two steps. The first step employs gaze transition cues to detect time stamps where new cuts are to be introduced in the original video via dynamic programming. A subsequent step optimizes the cropping window path (to create pan and zoom effects), while accounting for the original and new cuts. The cropping window path is designed to include maximum gaze information, and is composed of piecewise constant, linear and parabolic segments. It is obtained via L(1) regularized convex optimization which ensures a smooth viewing experience. We test our approach on a wide variety of videos and demonstrate significant improvement over the state-of-the-art, both in terms of computational complexity and qualitative aspects. A study performed with 16 users confirms that our approach results in a superior viewing experience as compared to gaze driven re-editing [JSSH15] and letterboxing methods, especially for wide-angle static camera recordings.
Image retrieval is an important topic in the field of pattern recognition and artificial intellig... more Image retrieval is an important topic in the field of pattern recognition and artificial intelligence. There are three categories of image retrieval methods: text-based, content-based and semantic-based. In Content-Based Image Retrieval (CBIR), images are indexed by their visual content, such as color, texture, shapes. CBIR has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems are built. While these research efforts are established the basis of CBIR, the usefulness of the proposed approaches is limited. Specially, these efforts have relatively ignored two distinct problems of CBIR systems: The semantic gap between high level concepts and low level features; Human perception of visual content. In addition to this, we have the problem of which image analysis models to use in image database to achieve a better CBIR system. This paper proposes a novel method for combining the user subjectivity in i...
Uploads
Papers by kranthi kumar