Krishna Reddy Konda | University of Trento (original) (raw)

Uploads

Papers by Krishna Reddy Konda

In this paper we propose a novel dynamic camera recon gu- ration algorithm for multi-camera netwo... more In this paper we propose a novel dynamic camera recon gu-
ration algorithm for multi-camera networks. The algorithm
relies on the analysis of the entropy of the acquired scene.
Based on the obtained values it assigns the cameras to act as
global or target sensors. While global sensors aim at guar-
anteeing the overall coverage of the observed space, target
sensors focus on moving objects. To this aim, the entropy
information is used di erently according to the operation
mode of each camera. The visual entropy of the captured
image is used to control the con guration of the global sen-
sors, whereas the disorder of the motion eld is adopted as
a metric to drive the recon guration of the target sensors.
In order to achieve real-time operational capabilities, the al-
gorithm works in the compressed video domain, rather than
the traditional pixel domain. The algorithm has been tested
in vitro, and also by deploying a camera network in a real
indoor surveillance environment. In particular, recon gura-
tion capability of the system has been tested with respect to
the presence of people moving in the observed environment.

Illumination is one of the most important aspects of any surveillance system. The quality of imag... more Illumination is one of the most important aspects of any surveillance system. The quality of images or videos captured by
the cameras heavily depends on the positioning and the intensity of the light sources in the environment. However, exhaustive
visualization of the illumination for different placement configurations is next to impossible due to the sheer number
of possible combinations. In this paper we propose a novel 3D modelling of a given environment in a synthetic domain,
combined with a generic quality metric, is based on entropy measurement in a given image. The synthetic modelling of the
environment allows us to evaluate the optimization problem a priori before the physical deployment of the light sources.
Entropy is a general measure of the amount of information in an image, so we propose to maximize the entropy out of all
possible light placement configurations. In order to model the environment in the virtual domain, we use the POVRAY
software, a tool based on ray tracing. Particle swarm optimization is then adopted to find the optimal solution. The total
entropy of the system is measured as sum of entropy of the virtual snapshots in the camera system.

In this paper we present a camera positioning and reconfiguration algorithm for complex indoor en... more In this paper we present a camera positioning and reconfiguration algorithm for complex indoor environments. The algorithm initially optimizes the global coverage of the selected environment in order to maximize the visibility on the entire area. Reconfiguration of the devices is then performed after the camera installation, in order locally optimize coverage according to the application requirements.

Scalable video coding (SVC) has found more and more applications in a variety of the adaptive net... more Scalable video coding (SVC) has found more and more applications in a variety of the adaptive network streaming and the terminal. In the current SVC, an exhaustive search technique is employed to select the best coding mode for each macro block. This technique achieves the optimal trade-off between the bit-rate and distortion, but it results in extremely large encoding time

IEEE Transactions on Consumer Electronics, 2009

The 3D video extension of High Efficiency Video Coding (3D-HEVC) is the state-of-the-art video co... more The 3D video extension of High Efficiency Video Coding (3D-HEVC) is the state-of-the-art video coding standard for the compression of the multiview video plus depth (MVD) format. In the 3D-HEVC design, new depth-modeling modes (DMMs) are utilized together with the existing intra prediction modes for depth intra coding. The DMMs can provide more accurate prediction signals and thereby achieve better compression efficiency. However, testing the DMMs in the intra mode decision process causes a drastic increase in the computational complexity. In this paper, we propose a fast mode decision algorithm for depth intra coding. The proposed algorithm first performs a simple edge classification in the Hadamard transform domain. Then, based on the edge classification results, the proposed algorithm selectively omits unnecessary DMMs in the mode decision process. Experimental results demonstrate that the proposed algorithm speeds up the mode decision process by up to 37.65% with negligible loss of coding efficiency.

ABSTRACT More and more applications are being discovered for scalable video coding (SVC) in netwo... more ABSTRACT More and more applications are being discovered for scalable video coding (SVC) in network-adaptive video streaming and storage systems. In the SVC encoder, an exhaustive search technique is employed to select the best coding mode for each macro block. This technique achieves the highest possible coding efficiency, but it results in extremely large encoding time. In this paper, we propose an adaptive fast mode decision algorithm for inter layer coding for spatial scalability and coarse grain quality scalability (CGS). In the proposed method, we select candidate modes adaptively for estimation in enhancement layer using the information of base layer and rate distortion (RD) cost of base layer skip mode. RD cost of base layer skip mode gives the correlation information of enhancement layer with base layer and base layer mode is used to reduce the number of candidate modes. We verify that the overall encoding time can be reduced up to 63 % through the analysis of experimental results.

IEEE Transactions on Consumer Electronics, 2009