Human Action Recognition in Compressed Domain using PBL-McRBFN Approach

Large variations in human actions lead to major challenges in computer vision research. Several algorithms are designed to solve the challenges. Algorithms that stand apart, help in solving the challenge in addition to performing faster and efficient manner. In this paper, we propose a human cognition inspired projection based learning for person-independent human action recognition in the H.264/AVC compressed domain and demonstrate a PBL-McRBEN based approach to help take the machine learning algorithms to the next level. Here, we use gradient image based feature extraction process where the motion vectors and quantization parameters are extracted and these are studied temporally to form several Group of Pictures (GoP). The GoP is then considered individually for two different bench mark data sets and the results are classified using person independent human action recognition. The functional relationship is studied using Projection Based Learning algorithm of the Meta-cognitive Radial Basis Function Network (PBL-McRBFN) which has a cognitive and meta-cognitive component. The cognitive component is a radial basis function network while the Meta-Cognitive Component(MCC) employs self regulation. The McC emulates human cognition like learning to achieve better performance. Performance of the proposed approach can handle sparse information in compressed video domain and provides more accuracy than other pixel domain counterparts. Performance of the feature extraction process achieved more than 90% accuracy using the PTIL-McRBFN which catalyzes the speed of the proposed high speed action recognition algorithm. We have conducted twenty random trials to find the performance in GoP. The results are also compared with other well known classifiers in machine learning literature.

In-doped multifilled n-type skutterudites with ZT=1.8

In this paper we maximize the thermoelectric (TE) figure of merit, ZT, of n-type skutterudites, (In,Sr,Ba,Yb)(y)Co4Sb12, via three different routes: (i) find the optimum fraction of In as fourth filler (ii) check the influence of powder particle, grain, and crystallite size on the TE properties and (iii) check thermal stability. Filled n-type (Sr, Ba, Yb)(y)Co4Sb12 was mixed in three different proportions with In0.4Co4Sb12, ball milled (regular or high-energy (HB) ball milling) and hot-pressed. Particle size analyses and SEM pictures of the broken surfaces of the hot pressed samples document that only HB produces uniform particles/grains with average crystallite sizes similar to 100 nm, proven by transmission electron microscopy. X-ray Rietveld refinements combined with EDX indicate that in all cases indium entered the icosahedral voids of the skutterudite. Temperature dependent physical properties of all three regularly ball-milled samples show that increasing In-content infers an increasing electrical resistivity, increasing Seebeck coefficient but a decreasing total thermal conductivity. Although ZT (823 K) is in the same range as for the sample without In, the ZT values in the whole temperature range are higher and consequently the TE-conversion efficiency, eta is at least 10% higher. Annealing the samples at 600 degrees C for three days shows minor changes in structure and thermoelectric properties, indicating TE stability. The HB sample, due to uniformly small particles, equally sized grains and crystallites, exhibits a high power factor (4.4 mW/m K-2 at 730 K) and a very low thermal conductivity leading to an outstanding high ZT = 1.8 at 823 K (eta(max) = 17.5%). (C) 2015 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Human action recognition in H.264/AVC compressed domain using meta-cognitive radial basis function network

In this paper, we propose a H.264/AVC compressed domain human action recognition system with projection based metacognitive learning classifier (PBL-McRBFN). The features are extracted from the quantization parameters and the motion vectors of the compressed video stream for a time window and used as input to the classifier. Since compressed domain analysis is done with noisy, sparse compression parameters, it is a huge challenge to achieve performance comparable to pixel domain analysis. On the positive side, compressed domain allows rapid analysis of videos compared to pixel level analysis. The classification results are analyzed for different values of Group of Pictures (GOP) parameter, time window including full videos. The functional relationship between the features and action labels are established using PBL-McRBFN with a cognitive and meta-cognitive component. The cognitive component is a radial basis function, while the meta-cognitive component employs self-regulation to achieve better performance in subject independent action recognition task. The proposed approach is faster and shows comparable performance with respect to the state-of-the-art pixel domain counterparts. It employs partial decoding, which rules out the complexity of full decoding, and minimizes computational load and memory usage. This results in reduced hardware utilization and increased speed of classification. The results are compared with two benchmark datasets and show more than 90% accuracy using the PBL-McRBFN. The performance for various GOP parameters and group of frames are obtained with twenty random trials and compared with other well-known classifiers in machine learning literature. (C) 2015 Elsevier B.V. All rights reserved.

Entropy Constrained Exemplar-based Image Inpainting

Image inpainting is the process of filling the unwanted region in an image marked by the user. It is used for restoring old paintings and photographs, removal of red eyes from pictures, etc. In this paper, we propose an efficient inpainting algorithm which takes care of false edge propagation. We use the classical exemplar based technique to find out the priority term for each patch. To ensure that the edge content of the nearest neighbor patch found by minimizing L-2 distance between patches, we impose an additional constraint that the entropy of the patches be similar. Entropy of the patch acts as a good measure of edge content. Additionally, we fill the image by considering overlapping patches to ensure smoothness in the output. We use structural similarity index as the measure of similarity between ground truth and inpainted image. The results of the proposed approach on a number of examples on real and synthetic images show the effectiveness of our algorithm in removing objects and thin scratches or text written on image. It is also shown that the proposed approach is robust to the shape of the manually selected target. Our results compare favorably to those obtained by existing techniques