Adaptive tracking of people and vehicles using mobile platforms

Abstract

Tracking algorithms have important applications in detection of humans and vehicles for border security and other areas. For large-scale deployment of such algorithms, it is critical to provide methods for their cost-and energy-efficient realization. To this end, commodity mobile devices have significant potential for use as prototyping and testing platforms due to their low cost, widespread availability, and integration of advanced communications, sensing, and processing features. Prototypes developed on mobile platforms can be tested, fine-tuned, and demonstrated in the field and then provide reference implementations for application-specific disposable sensor node implementations that are targeted for deployment. In this paper, we develop a novel, adaptive tracking system that is optimized for energy-efficient, real-time operation on off-the-shelf mobile platforms. Our tracking system applies principles of dynamic data-driven application systems (DDDAS) to periodically monitor system operating characteristics and apply these measurements to dynamically adapt the specific classifier configurations that the system employs. Our resulting adaptive approach enables powerful optimization of trade-offs among energy consumption, real-time performance, and tracking accuracy based on time-varying changes in operational characteristics. Through experiments employing an Android-based tablet platform, we demonstrate the efficiency of our proposed tracking system design for multimode detection of human and vehicle targets.

Design and Implementation of Android-Based Autonomous Human Tracking Vehicle

“…Salem et al implemented an adaptive system for detecting and tracking human footsteps and vehicles from mobile devices. They enabled powerful optimization of trade-offs among energy consumption, real-time performance, and tracking accuracy based on time-varying changes in operational characteristics [5]. Lu and Payandeh [6] proposed a novel hybrid visual tracking system with a stationary camera and a pan/tilt/zoom (PTZ) camera.…”

A Novel Electric Bicycle Battery Monitoring System Based on Android Client

“…The equalization circuit can improve the consistency of series connected cells. Scientific and technological progress has brought the smart phones to numerous households allowing for the monitoring of information of electric bicycle batteries by mobile phone [17].…”

“…Each application can design its unique function module and when the module is set up in accordance with the rules of the application framework, it can gain the support of the Android system and interact with other function modules. Based on the advantages of Android [17], the smart phone's efficient processor and large high-resolution screens can efficiently monitor the lithium battery pack of electric bicycle using smart phones [21].…”

An optimized embedded target detection system using acoustic and seismic sensors

“…Damarla and Kaplan develop a decision-level fusion architecture for tracking groups of people using acoustic and seismic signal processing [2]. Ben Salem et al present an adaptive target detection system that employs mobile devices as sensor node platforms, and applies different acoustic signal processing techniques for different signal-to-noise ratio conditions, and energy consumption constraints [5]. Our work in this paper differs from these prior works in that we simultaneously handle (1) multiple sensing modalities (acoustic and seismic); (2) both decision and feature level fusion for improved accuracy; and (3) design optimization for energy-and resource-constrained embedded implementation.…”