In this article, we present a multiagent framework for real-time large-scale 3-D reconstruction applications. In SLAM, researchers usually build and update a 3-D map after applying nonlinear pose graph optimization techniques. Moreover, many multiagent systems are prevalently using odometry information from additional sensors. These methods generally involve extensive computer vision algorithms and are tightly coupled with various sensors. We develop a generic method for the key challenging scenarios in multiagent 3-D mapping based on different camera systems. The proposed framework performs actively in terms of localizing each agent after the first loop closure between them. It is shown that the proposed system only uses monocular cameras to yield real-time multiagent large-scale localization and 3-D global mapping. Based on the initial matching, our system can calculate the optimal scale difference between multiple 3-D maps and then estimate an accurate relative pose transformation for large-scale global mapping.

The ability to localize in the co-ordinate system of a 3D model presents an opportunity for safe trajectory planning. While SLAM-based approaches provide estimates of incremental poses with respect to the first camera frame, they do not provide global localization. With the availability of mobile GPUs like the Nvidia TX1 etc., our method provides a novel, elegant and high performance visual method for model based robot localization. We propose a method to learn an environment representation with deep residual nets for localization in a known 3D model representing a real-world area of 25,000 sq. meters. We use the power of modern GPUs and game engines for rendering training images mimicking a downward looking high flying drone using a photorealistic 3D model. We use these images to drive the learning loop of a 50-layer deep neural network to learn camera positions. We next propose to do data augmentation to accelerate training and to make our trained model robust for cross domain generalization, which has been verified with experiments. We test our trained model with synthetically generated data as well as real data captured from a downward looking drone. It takes about 25 miliseconds of GPU processing to predict camera pose. Unlike previous methods, the proposed method does not do rendering at test time and does independent prediction from a learned environment representation.

Multispectral demosaicking, which is an extension of color demosaicking, is a challenging problem because each band is significantly undersampled and thus precise reconstruction is needed for the restoration of high-frequency components, such as edges, textures etc. In general, existing algorithms borrow high-frequency information either from different bands via inter-color correlation or from within the bands, and produces artifact in the reconstructed image. To meet this inherent shortcoming, we propose to incorporate two different high-frequency components and integrate them optimally in the linear minimum mean square sense (LMMSE) for the precise reconstruction of undersampled components. Experimental results demonstrate that the proposed algorithm based on the optimized high-frequency achieves superior performance compared to existing algorithms both in terms of objective and subjective quality.

There has been a paradigm shifting trend towards feature-less methods due to their elegant formulation, accuracy and ever increasing computational power. In this work, we present a direct edge alignment approach for 6-DOF tracking. We argue that photo-consistency based methods are plagued by a much smaller convergence basin and are extremely sensitive to noise, changing illumination and fast motion. We propose to use the Distance Transform in the energy formulation which can significantly extend the influence of the edges for tracking. We address the problem of non-differentiability of our cost function and of the previous methods by use of a sub-gradient method. Through extensive experiments we show that the proposed method gives comparable performance to the previous method under nominal conditions and is able to run at 30 Hz in single threaded mode. In addition, under large motion we demonstrate our method outperforms previous methods using the same runtime configuration for our method.

In this paper we address the problem of multiview color consistency. We propose to use a graph model of 3d positions obtained using matched dense feature points. We define an energy functional on this model which captures relationship of the colors across views while also imposing a smoothness cost to obtain optimal colors for the 3d positions. We finally recolorize the images using these optimal colors at re-projected co-ordinates. An important feature of the proposed method is that it does not use a reference view. Finally we present a qualitative evaluation of our method with methods that use a reference view.

In this paper, we propose a 2-Sieve model for the detection of mitosis in breast cancer multispectral images. Multiresolution wavelet features & Gray Level Entropy Matrix (GLEM) features have been computed for each candidate on all the spectral bands. A novel dimensionality selection algorithm has been introduced and its performance compared with other existing algorithms. Data imbalance and data cleaning have been taken care of using classical data mining techniques. Furthermore, a Second Sieve classification is performed to increase the Positive Predictive Value (PPV) with minimal loss in Sensitivity. A final Sensitivity and PPV of 82.35% & 73.04% respectively was achieved over the testing set using the proposed scheme.