Design of multimedia surveillance systems

This article addresses the problem of how to select the optimal combination of sensors and how to determine their optimal placement in a surveillance region in order to meet the given performance requirements at a minimal cost for a multimedia surveillance system. We propose to solve this problem by obtaining a performance vector, with its elements representing the performances of subtasks, for a given input combination of sensors and their placement. Then we show that the optimal sensor selection problem can be converted into the form of Integer Linear Programming problem (ILP) by using a linear model for computing the optimal performance vector corresponding to a sensor combination. Optimal performance vector corresponding to a sensor combination refers to the performance vector corresponding to the optimal placement of a sensor combination. To demonstrate the utility of our technique, we design and build a surveillance system consisting of PTZ (Pan-Tilt-Zoom) cameras and active motion sensors for capturing faces. Finally, we show experimentally that optimal placement of sensors based on the design maximizes the system performance.

Farnesyltransferase Inhibitors Reduce Ras Activation and Ameliorate Acetaminophen-Induced Liver Injury in Mice

Hepatotoxicity due to overdose of the analgesic and antipyretic acetaminophen (A-PAIP) is a major cause of liver failure in adults. To better understand the contributions of different signaling pathways, the expression and role of Ras activation was evaluated after oral dosing of mice with APAP (400-500 mg/kg). Ras-guanosine triphosphate (GTP) is induced early and in an oxidative stress-dependent manner. The functional role of Ras activation was studied by a single intraperitoneal injection of the neutral sphingomyelinase and farnesyltransferase inhibitor (FTI) manumycin A (I mg/kg), which lowers induction of Ras-GTP and serum amounts of alanine aminotransferase (ALT). APAP dosing decreases hepatic glutathione amounts, which are not affected by manumycin A treatment. However, APAP-induced activation of c-Jun N-terminal kinase, which plays an important role, is reduced by manumycin A. Also, APAP-induced mitochondrial reactive oxygen species are reduced by manumycin A at a later time point during liver injury. Importantly, the induction of genes involved in the inflammatory response (including iNos, gp91phox, and Fasl) and serum amounts of proinflammatory cytokines interferon-gamma (IFN gamma) and tumor necrosis factor alpha, which increase greatly with APAP challenge, are suppressed with manumycin A. The FTI ctivity of manumycin A is most likely involved in reducing APAP-induced liver injury, because a specific neutral sphingomyelinase inhibitor, GW4869 (I mg/kg), did not show any hepatoprotective effect. Notably, a structurally distinct FTI, gliotoxin (I mg/kg), also inhibits Ras activation and reduces serum amounts of ALT and IFN-gamma after APAP dosing. Finally, histological analysis confirmed the hepatoprotective effect f manumycin A and gliotoxin during APAP-induced liver damage. Conclusion: This study identifies a key role for Ras activation and demonstrates the therapeutic efficacy of FTIs during APAP-induced liver injury.

Designing Dense Radar Networks for Weather Surveillance in Tropical Regions.

Design considerations are presented for a dense weather radar network to support multiple services including aviation. Conflicts, tradeoffs and optimization issues in the context of operation in a tropical region are brought out. The upcoming Indian radar network is used as a case study. Algorithms for data mosaicing are briefly outlined.

A design methodology for selecting and placement of sensors in multimedia surveillance systems

This paper addresses the problem of how to select the optimal number of sensors and how to determine their placement in a given monitored area for multimedia surveillance systems. We propose to solve this problem by obtaining a novel performance metric in terms of a probability measure for accomplishing the task as a function of set of sensors and their placement. This measure is then used to find the optimal set. The same measure can be used to analyze the degradation in system 's performance with respect to the failure of various sensors. We also build a surveillance system using the optimal set of sensors obtained based on the proposed design methodology. Experimental results show the effectiveness of the proposed design methodology in selecting the optimal set of sensors and their placement.

Simulation-driven design of helmets for head impact protection using an injury-based criterion

The current paper suggests a new procedure for designing helmets for head impact protection for users such as motorcycle riders. According to the approach followed here, a helmet is mounted on a featureless Hybrid 3 headform that is used in assessing vehicles for compliance to the FMVSS 201 regulation in the USA for upper interior head impact safety. The requirement adopted in the latter standard, i.e. not exceeding a threshold HIC(d) limit of 1000, is applied in the present study as a likely criterion for adjudging the efficacy of helmets. An impact velocity of 6 m/s (13.5 mph) for the helmet-headform system striking a rigid target can probably be acceptable for ascertaining a helmet's effectiveness as a countermeasure for minimizing the risk of severe head injury. The proposed procedure is demonstrated with the help of a validated LS-DYNA model of a featureless Hybrid 3 headform in conjunction with a helmet model comprising an outer polypropylene shell to the inner surface of which is bonded a protective polyurethane foam padding of a given thickness. Based on simulation results of impact on a rigid surface, it appears that a minimum foam padding thickness of 40 mm is necessary for obtaining an acceptable value of HIC(d).

Boosting-based transfer learning for multi-view head-pose classification from surveillance videos

This work proposes a boosting-based transfer learning approach for head-pose classification from multiple, low-resolution views. Head-pose classification performance is adversely affected when the source (training) and target (test) data arise from different distributions (due to change in face appearance, lighting, etc). Under such conditions, we employ Xferboost, a Logitboost-based transfer learning framework that integrates knowledge from a few labeled target samples with the source model to effectively minimize misclassifications on the target data. Experiments confirm that the Xferboost framework can improve classification performance by up to 6%, when knowledge is transferred between the CLEAR and FBK four-view headpose datasets.

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.

Exploring Transfer Learning Approaches for Head Pose Classification from Multi-view Surveillance Images

Head pose classification from surveillance images acquired with distant, large field-of-view cameras is difficult as faces are captured at low-resolution and have a blurred appearance. Domain adaptation approaches are useful for transferring knowledge from the training (source) to the test (target) data when they have different attributes, minimizing target data labeling efforts in the process. This paper examines the use of transfer learning for efficient multi-view head pose classification with minimal target training data under three challenging situations: (i) where the range of head poses in the source and target images is different, (ii) where source images capture a stationary person while target images capture a moving person whose facial appearance varies under motion due to changing perspective, scale and (iii) a combination of (i) and (ii). On the whole, the presented methods represent novel transfer learning solutions employed in the context of multi-view head pose classification. We demonstrate that the proposed solutions considerably outperform the state-of-the-art through extensive experimental validation. Finally, the DPOSE dataset compiled for benchmarking head pose classification performance with moving persons, and to aid behavioral understanding applications is presented in this work.

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.