Anup Mohan

A system for large-scale analysis of distributed cameras

Thousands of cameras are connected to the Internet providing streaming data (videos or periodic images). The images contain information that can be used to determine the scene contents such as traffic, weather, and the environment. Analyzing the data from these cameras presents many challenges, such as (i) retrieving data from geographically distributed and heterogeneous cameras, (ii) providing a software environment for users to simultaneously analyze large amounts of data from the cameras, (iii) allocating and managing computation and storage resources. This paper presents a system designed to address these challenges. The system enables users to execute image analysis and computer vision techniques on a large scale with only slight changes to the existing methods. It currently includes more than 65,000 cameras deployed worldwide. Users can select cameras for the types of analysis they can do. The system allocates Amazon EC2 and Windows Azure cloud instances for executing the analysis. Our experiments demonstrate that this system can be used for a variety of image analysis techniques (e.g. motion analysis and human detection) using 2.7 million images from 1274 cameras for three hours using 15 cloud instances to analyze 141 GB of images (at 107 Mbps).

Cloud Resource Management for Image and Video Analysis of Big Data from Network Cameras

With the existence of millions of public network cameras capturing countless events around the world, there is a need for a system to retrieve, save, and analyze the tremendous amount of visual data from the cameras. The knowledge from the data will ultimately help better understand the world. Such a system needs to allocate and manage significant amounts of resources in order to meet the analysis requirements. In order to reduce the overall analysis cost, this paper presents a cloud resource manager that allocates cost-effective cloud instances, monitors and automatically scales the cloud resources. The paper presents a system that uses the proposed resource manager for image and video analysis of the big data from global network cameras. Our experiments show that the resource manager can lead to 13% reduction in cost. The experiments use four analysis programs which represent different workloads in terms of CPU and memory. The experiments show that different cloud instances are more cost-effective for different analysis programs. One experiment analyzes data streams from 1026 cameras simultaneously for six hours using different analysis programs at different frame rates. The experiment analyzes 5.5 million images, totalling 260GB data.

Location Based Cloud Resource Management for Analyzing Real-Time Videos from Globally Distributed Network Cameras

The use of video data for a variety of applications has gained immense popularity. These applications include traffic monitoring, surveillance, retail store management, etc. Thousands of publicly accessible network cameras distributed around the world are potential sources of video data. The applications analyzing data from network cameras have different resource requirements (CPU, memory, etc.) and performance requirements (video frame rate). A preferred way to meet these requirements is to use a cloud infrastructure and a pay-per-use model of the cloud. Cloud computing offers resources, referred to as cloud instances, with different capacities and at different locations. The cost of these instances are dependent on their capacities and locations. The frame rate of the video data obtained from a network camera impacts the accuracy of the analysis and is dependent on the location of the cloud instance. Hence it is important to select the locations of the instances to meet the application performance requirements. This paper presents a resource management approach to select the locations, types, and number of cloud instances to analyze real-time video data from the network cameras while meeting the performance requirements and reducing the analysis cost. We model the resource management problem as a variable size bin packing problem and describe a heuristic algorithm to find a solution. This paper uses Amazon EC2 to evaluate our new resource manager, and observes that our method can reduce the analysis cost up to 56% compared with two other strategies for selecting instance locations.

Developing a high-volume batch submission system for earthquake engineering

NEES is a network of 14 earthquake engineering labs distributed across the United States. As a part of the NEES effort NEESComm operates a comprehensive cyberinfrastructure that consists of the NEEShub and the NEES Project Warehouse. NEESComm provides consistent access to several High Performance Computing (HPC) venues. These venues include XSEDE, the Open Science Grid (OSG), Purdue Supercomputers, and NEEShub servers. In this paper, we describe the system we developed, Batchsubmit, which allows NEES researchers to make use of all these venues through the NEEShub science gateway.

Improve safety using public network cameras

Surveillance cameras, also called CCTV (closed-circuit television), are widely deployed as one of the solutions to improve public safety. The visual data from these cameras are usually unavailable to the public. In recent years, many organizations have deployed network cameras with diverse purposes such as monitoring traffic congestion and observing natural scenes. The data are available to anyone connected to the Internet, without any password. Although the cameras are not deployed for surveillance purposes, the cameras can be utilized to increase public safety by properly integrating to current surveillance systems. Suspicious activities may be monitored in real-time and coverage can be increased along with CCTVs deployed by law enforcement. Integrating public cameras into a surveillance system has many challenges such as inaccurate locations, diverse sources, and different methods to access the visual data. This paper presents how to discover public cameras from heterogeneous sources and find the accurate locations and orientations of the cameras. We propose a proof-of-concept system to improve public safety by integrating public cameras into our previous visualization tool.

Batchsubmit: a high-volume batch submission system for earthquake engineering simulation

Network for Earthquake Engineering Simulation (NEES) is a network of 14 earthquake engineering labs distributed across the USA. As a part of the NEES effort NEESComm operates a comprehensive cyberinfrastructure that consists of the NEEShub and the NEES Project Warehouse. NEESComm provides consistent access to several high performance computing (HPC) venues. These venues include Extreme Science and Engineering Discovery Environment, the Open Science Grid, Purdue Supercomputers, and NEEShub servers. In this paper, we describe the system we developed, batchsubmit, which allows NEES researchers to make use of all these venues through the NEEShub science gateway. Copyright

Internet of video things in 2030: A world with many cameras

The Internet of Things (IoT) is the internetworking of a variety of devices, including sensors. Among all sensors, visual sensors (i.e. cameras) are special because they can provide rich and versatile information. The world already has more than one billion cameras on mobile phones. We define the internet-working of visual sensors as the Internet of Video Things. This article estimates the number of cameras the world will see in 2030 and the implications of a large number of cameras. Transmitting, storing, and analyzing the data from cameras could impose significant challenges to existing technological infrastructures. This paper surveys recent progress in relevant technologies and suggests directions for future research.

Cloud Resource Management for Analyzing Big Real-Time Visual Data from Network Cameras

Thousands of network cameras stream real-time visual data for different environments, such as streets, shopping malls, and natural scenes. The big visual data from these cameras can be useful for many applications, but analyzing the large quantities of data requires significant amounts of resources. These resources can be obtained from cloud vendors offering cloud instances (referred to as instances in this paper) with different capabilities and hourly costs. It is a challenging problem to manage cloud resources to reduce the cost for analyzing the big real-time visual data from network cameras while meeting the performance requirements. That is because the problem is affected by many factors related to the analysis programs, the cameras, and the instances. This paper proposes a cloud resource manager (referred to as manager in this paper) that aims at solving this problem. The manager estimates the resource requirements of analyzing the data stream from each camera, formulates the resource allocation problem as a 2D vector bin packing problem, and solves it using a heuristic algorithm. The resource manager monitors the allocated instances; it allocates more instances if needed and deallocates existing instances to reduce the cost if possible. The experiments show that the resource manager is able to reduce up to 60 percent of the overall cost. The experiments use multiple analysis programs, such as moving objects detection, feature tracking, and human detection. One experiment analyzes more than 97 million images (3.3 TB of data) from 5,310 cameras simultaneously over 24 hours using 15 Amazon EC2 instances costing

Analysis of Large-Scale Distributed Cameras Using the Cloud

188.