H.264 COMPRESSED VIDEO CLASSIFICATION USING HISTOGRAM OF ORIENTED MOTION VECTORS (HOMV)

In this paper, we have proposed a simple and effective approach to classify H.264 compressed videos, by capturing orientation information from the motion vectors. Our major contribution involves computing Histogram of Oriented Motion Vectors (HOMV) for overlapping hierarchical Space-Time cubes. The Space-Time cubes selected are partially overlapped. HOMV is found to be very effective to define the motion characteristics of these cubes. We then use Bag of Features (B OF) approach to define the video as histogram of HOMV keywords, obtained using k-means clustering. The video feature, thus computed, is found to be very effective in classifying videos. We demonstrate our results with experiments on two large publicly available video database.

Capture-Induced, Fast, Distributed, Splitting Based Selection with Imperfect Power Control

Opportunistic selection selects the node that improves the overall system performance the most. Selecting the best node is challenging as the nodes are geographically distributed and have only local knowledge. Yet, selection must be fast to allow more time to be spent on data transmission, which exploits the selected node's services. We analyze the impact of imperfect power control on a fast, distributed, splitting based selection scheme that exploits the capture effect by allowing the transmitting nodes to have different target receive powers and uses information about the total received power to speed up selection. Imperfect power control makes the received power deviate from the target and, hence, affects performance. Our analysis quantifies how it changes the selection probability, reduces the selection speed, and leads to the selection of no node or a wrong node. We show that the effect of imperfect power control is primarily driven by the ratio of target receive powers. Furthermore, we quantify its effect on the net system throughput.

Experimental investigation of biofuel drop impact on stainless steel surface

Blends of conventional fuels such as Jet-A1 (aviation kerosene) and diesel with bio-derived components, referred to as biofttels, are gradually replacing the conventional fuels in aircraft and automobile engines. There is a lack of understanding on the interaction of spray drops of such biofuels with solid surfaces. The present study is an experimental investigation on the impact of biofuel drops onto a smooth stainless steel surface. The biofuel is a mixture of 90% commercially available camelina-derived biofuel and 10% aromatics. Biofuel drops were generated using a syringe-hypodermic needle arrangement. On demand, the needle delivers an almost spherical drop with drop diameter in the range 2.05-2.15 mm. Static wetting experiments show that the biofuel drop completely wets the stainless steel surface and exhibits an equilibrium contact angle of 5.6. High speed video camera was used to capture the impact dynamics of biofuel drops with Weber number ranging from 20 to 570. The spreading dynamics and maximum spreading diameter of impacting biofuel drops on the target surface were analyzed. For the impact of high Weber number biofuel drops, the spreading law suggests beta similar to tau(0.5) where beta is the spread factor and tau, the nondimensionalized time. The experimentally observed trend of maximum spread factor, beta(max) of camelina biofuel drop on the target surface with We compares well with the theoretically predicted trend from Ukiwe-Kwok model. After reaching beta(max), the impacting biofuel drop undergoes a prolonged sluggish spreading due to the high wetting nature of the camelina biofuel-stainless steel system. As a result, the final spread factor is found to be a little more than beta(max). (C) 2014 Elsevier Inc. All rights reserved.

RAPID HUMAN ACTION RECOGNITION IN H.264/AVC COMPRESSED DOMAIN FOR VIDEO SURVEILLANCE

This paper discusses a novel high-speed approach for human action recognition in H. 264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of our work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can effect in reduced hardware utilization and fast recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust in outdoor as well as indoor testing scenarios. We have tested our method on two benchmark action datasets and achieved more than 85% accuracy. The proposed algorithm classifies actions with speed (>2000 fps) approximately 100 times more than existing state-of-the-art pixel-domain algorithms.

PMV model is insufficient to capture subjective thermal response from Indians

A controlled laboratory experiment was carried out on forty Indian male college students for evaluating the effect of indoor thermal environment on occupants' response and thermal comfort. During experiment, indoor temperature varied from 21 degrees C to 33 degrees C, and the variables like relative humidity, airflow, air temperature and radiant temperature were recorded along with subject's physiological parameters (skin (T-sk) and oral temperature (T-c)) and subjective thermal sensation responses (TSV). From T-sk and T-c, body temperature (T-b) was evaluated. Subjective Thermal Sensation Vote (TSV) was recorded using ASHRAE 7-point scale. In PMV model, Fanger's T-sk equation was used to accommodate adaptive response. Step-wise regression analysis result showed T-b was better predictor of TSV than T-sk and T-c. Regional skin temperature response, suppressed sweating without dipping, lower sweating threshold temperature and higher cutaneous threshold for sweating were observed as thermal adaptive responses. These adaptive responses cannot be considered in PMV model. To incorporate subjective adaptive response, mean skin temperature (T-sk) is considered in dry heat loss calculation. Along with these, PMV-model and other two methodologies are adopted to calculate PMV values and results are compared. However, recent literature is limited to measure the sweat rate in Indians and consideration of constant Ersw in PMV model needs to be corrected. Using measured T-sk in PMV model (Method(1)), thermal comfort zone corresponding to 0.5 <= PMV <= 0.5 was evaluated as (22.46-25.41) degrees C with neutral temperature of 23.91 degrees C, similarly while using TSV response, wider comfort zone was estimated as (23.25-26.32) degrees C with neutral temperature at 24.83 degrees C, which was further increased to with TSV-PPDnew, relation. It was observed that PMV-model overestimated the actual thermal response. Interestingly, these subjects were found to be less sensitive to hot but more sensitive to cold. A new TSV-PPD relation (PPDnew) was obtained from the population distribution of TSV response with an asymmetric distribution of hot-cold thermal sensation response from Indians. The calculations of human thermal stress according to steady state energy balance models used on PMV model seem to be inadequate to evaluate human thermal sensation of Indians. Relevance to industry: The purpose of this paper is to estimate thermal comfort zone and optimum temperature for Indians. It also highlights that PMV model seems to be inadequate to evaluate subjective thermal perception in Indians. These results can be used in feedback control of HVAC systems in residential and industrial buildings. (C) 2014 Elsevier B.V. All rights reserved.

Skip Decision and Reference Frame Selection for Low-Complexity H.264/AVC Surveillance Video Coding

H. 264/advanced video coding surveillance video encoders use the Skip mode specified by the standard to reduce bandwidth. They also use multiple frames as reference for motion-compensated prediction. In this paper, we propose two techniques to reduce the bandwidth and computational cost of static camera surveillance video encoders without affecting detection and recognition performance. A spatial sampler is proposed to sample pixels that are segmented using a Gaussian mixture model. Modified weight updates are derived for the parameters of the mixture model to reduce floating point computations. A storage pattern of the parameters in memory is also modified to improve cache performance. Skip selection is performed using the segmentation results of the sampled pixels. The second contribution is a low computational cost algorithm to choose the reference frames. The proposed reference frame selection algorithm reduces the cost of coding uncovered background regions. We also study the number of reference frames required to achieve good coding efficiency. Distortion over foreground pixels is measured to quantify the performance of the proposed techniques. Experimental results show bit rate savings of up to 94.5% over methods proposed in literature on video surveillance data sets. The proposed techniques also provide up to 74.5% reduction in compression complexity without increasing the distortion over the foreground regions in the video sequence.

VIRTUAL VIEW SYNTHESIS BY NON-LOCAL MEANS FILTERING USING TEMPORAL DATA

A novel algorithm for Virtual View Synthesis based on Non-Local Means Filtering is presented in this paper. Apart from using the video frames from the nearby cameras and the corresponding per-pixel depth map, this algorithm also makes use of the previously synthesized frame. Simple and efficient, the algorithm can synthesize video at any given virtual viewpoint at a faster rate. In the process, the quality of the synthesized frame is not compromised. Experimental results prove the above mentioned claim. The subjective and objective quality of the synthesized frames are comparable to the existing algorithms.

Timer-Based Distributed Node Selection Scheme Exploiting Power Control and Capture

Opportunistic selection in multi-node wireless systems improves system performance by selecting the ``best'' node and by using it for data transmission. In these systems, each node has a real-valued local metric, which is a measure of its ability to improve system performance. Our goal is to identify the best node, which has the largest metric. We propose, analyze, and optimize a new distributed, yet simple, node selection scheme that combines the timer scheme with power control. In it, each node sets a timer and transmit power level as a function of its metric. The power control is designed such that the best node is captured even if. other nodes simultaneously transmit with it. We develop several structural properties about the optimal metric-to-timer-and-power mapping, which maximizes the probability of selecting the best node. These significantly reduce the computational complexity of finding the optimal mapping and yield valuable insights about it. We show that the proposed scheme is scalable and significantly outperforms the conventional timer scheme. We investigate the effect of. and the number of receive power levels. Furthermore, we find that the practical peak power constraint has a negligible impact on the performance of the scheme.

An evaluation of antigen capture assays for detecting active filarial antigens

Lymphatic filariasis is a parasitic disease of tropical countries. This is a disfiguring and painful disease contracted in childhood, but the symptoms become apparent only in later years. Diagnosis of filarial infection is very crucial for the management of the disease. The main objective of this study was to develop a filarial antigen-based immunological assay for the diagnosis and surveillance of the disease. Monoclonal and polyclonal antibodies were raised to the recombinant protein Brugia malayi vespid allergen homologue (VAH). Capture enzyme-linked immunosorbent assay (ELISA) was standardized utilizing various combinations of antibodies and evaluated with serum samples of endemic normal (EN, n = 110), microfilaraemic (MF, n = 65), chronic pathology (CP, n = 45) and non-endemic normal (NEN, n = 10) individuals. Of the 230 samples tested, VAHcapture assay detected circulating antigen in 97.91% of bancroftian and 100% of brugian microfilaraemic individuals, and 5% of endemic normal individuals, comparable to the earlier reported SXP-1 antigen detection assay. However, the combination of VAH and SXP-1 (VS) capture ELISA was found to be more robust, detecting 100% of microfilaraemic individuals and with higher binding values. Thus an antigen capture immunoassay has been developed, which can differentiate active infection from chronic infection by detecting circulating filarial antigens in clinical groups of endemic areas.

Compressed domain human action recognition in H.264/AVC video streams

This paper discusses a novel high-speed approach for human action recognition in H.264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of the proposed work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can result in reduced hardware utilization and faster recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust to outdoor as well as indoor testing scenarios. We have evaluated the performance of the proposed method on two benchmark action datasets and achieved more than 85 % accuracy. The proposed algorithm classifies actions with speed (> 2,000 fps) approximately 100 times faster than existing state-of-the-art pixel-domain algorithms.

SeamSeg: Video Object Segmentation using Patch Seams

In this paper, we propose a technique for video object segmentation using patch seams across frames. Typically, seams, which are connected paths of low energy, are utilised for retargeting, where the primary aim is to reduce the image size while preserving the salient image contents. Here, we adapt the formulation of seams for temporal label propagation. The energy function associated with the proposed video seams provides temporal linking of patches across frames, to accurately segment the object. The proposed energy function takes into account the similarity of patches along the seam, temporal consistency of motion and spatial coherency of seams. Label propagation is achieved with high fidelity in the critical boundary regions, utilising the proposed patch seams. To achieve this without additional overheads, we curtail the error propagation by formulating boundary regions as rough-sets. The proposed approach out-perform state-of-the-art supervised and unsupervised algorithms, on benchmark datasets.

Activity Recognition in Egocentric Life-Logging Videos

With the increasing availability of wearable cameras, research on first-person view videos (egocentric videos) has received much attention recently. While some effort has been devoted to collecting various egocentric video datasets, there has not been a focused effort in assembling one that could capture the diversity and complexity of activities related to life-logging, which is expected to be an important application for egocentric videos. In this work, we first conduct a comprehensive survey of existing egocentric video datasets. We observe that existing datasets do not emphasize activities relevant to the life-logging scenario. We build an egocentric video dataset dubbed LENA (Life-logging EgoceNtric Activities) (http://people.sutd.edu.sg/similar to 1000892/dataset) which includes egocentric videos of 13 fine-grained activity categories, recorded under diverse situations and environments using the Google Glass. Activities in LENA can also be grouped into 5 top-level categories to meet various needs and multiple demands for activities analysis research. We evaluate state-of-the-art activity recognition using LENA in detail and also analyze the performance of popular descriptors in egocentric activity recognition.

Anomaly detection in compressed H.264/AVC video

Real time anomaly detection is the need of the hour for any security applications. In this article, we have proposed a real time anomaly detection for H.264 compressed video streams utilizing pre-encoded motion vectors (MVs). The proposed work is principally motivated by the observation that MVs have distinct characteristics during anomaly than usual. Our observation shows that H.264 MV magnitude and orientation contain relevant information which can be used to model the usual behavior (UB) effectively. This is subsequently extended to detect abnormality/anomaly based on the probability of occurrence of a behavior. The performance of the proposed algorithm was evaluated and bench-marked on UMN and Ped anomaly detection video datasets, with a detection rate of 70 frames per sec resulting in 90x and 250x speedup, along with on-par detection accuracy compared to the state-of-the-art algorithms.

A survey on compressed domain video analysis techniques

Image and video analysis requires rich features that can characterize various aspects of visual information. These rich features are typically extracted from the pixel values of the images and videos, which require huge amount of computation and seldom useful for real-time analysis. On the contrary, the compressed domain analysis offers relevant information pertaining to the visual content in the form of transform coefficients, motion vectors, quantization steps, coded block patterns with minimal computational burden. The quantum of work done in compressed domain is relatively much less compared to pixel domain. This paper aims to survey various video analysis efforts published during the last decade across the spectrum of video compression standards. In this survey, we have included only the analysis part, excluding the processing aspect of compressed domain. This analysis spans through various computer vision applications such as moving object segmentation, human action recognition, indexing, retrieval, face detection, video classification and object tracking in compressed videos.

No More HF: Teflon-Assisted Ultrafast Removal of Silica to Generate High-Surface-Area Mesostructured Carbon for Enhanced CO2 Capture and Supercapacitor Performance

An innovative technique to obtain high-surface-area mesostructured carbon (2545m(2)g(-1)) with significant microporosity uses Teflon as the silica template removal agent. This method not only shortens synthesis time by combining silica removal and carbonization in a single step, but also assists in ultrafast removal of the template (in 10min) with complete elimination of toxic HF usage. The obtained carbon material (JNC-1) displays excellent CO2 capture ability (ca. 26.2wt% at 0 degrees C under 0.88bar CO2 pressure), which is twice that of CMK-3 obtained by the HF etching method (13.0wt%). JNC-1 demonstrated higher H-2 adsorption capacity (2.8wt%) compared to CMK-3 (1.2wt%) at -196 degrees C under 1.0bar H-2 pressure. The bimodal pore architecture of JNC-1 led to superior supercapacitor performance, with a specific capacitance of 292Fg(-1) and 182Fg(-1) at a drain rate of 1Ag(-1) and 50Ag(-1), respectively, in 1m H2SO4 compared to CMK-3 and activated carbon.