Tracking in Wide Area Motion Imagery Using Phase Vector Fields

Santhaseelan, Varun; Asari, Vijayan K.

doi:10.1109/cvprw.2013.123

Cited by 12 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using (7), the intersection of any vector P c in the camera CS and the image plane can be found. For example, the vector P c from the aircraft to a point on the ground may have a magnitude -» -> P c | = 6 × 10 6 m, but the image plane vector P 1 can still be found using (7). Equation (7) is used in the calibration process to per form the inverse projection operation.…”

Section: Transformation F^from Image To Cameramentioning

confidence: 99%

Camera models for the wright patterson air force base (WPAFB) 2009 wide-area motion imagery (WAMI) data set

Cohenour

Graas

Price

et al. 2015

IEEE Aerosp. Electron. Syst. Mag.

View full text Add to dashboard Cite

This article provides an introduction to the Air Force Research Laboratory (AFRL) Wright Patterson Air Force Base (WPAFB) 2009 wide area image data set. The data set is useful for those doing research on projection, tracking, georegistration, and other image-related activities. The data set includes raw images, pose data, and projected images. For users that would like to project the data, a camera model and calibration are provided here. The camera model and calibration developed here provide a signifcant improvement over the projected images included with the data.Wide-area motion imagery (WAMI) is characterized as per sistent image collection over a city-sized area, at a low frame rate, with a medium resolution. Typically, the data are collected from an orbiting aircraft over a period of many hours. The aircraft or bital radius, altitude, and the camera focal length are arranged such that the observation area is on the order of 4-8 km in di ameter. Images are recorded at a rate of 1 or 2 Hz. The ground sample distance may be from 1 to 0.25 m. To achieve wide-area coverage, the image data may be collected using a bank of six or eight cameras, allowing for lighter and less costly lenses.WAMI data have both civilian and military applications. Ci vilian applications include monitoring the movement of people and vehicles for urban development, traffc analysis, emergency response, law enforcement [1], and border security. Military ap plications include improved situational awareness [2] by using the technology known as layered sensing [3]. Layered sensing may include electro-optical (EO) or visible light, infrared, syn thetic aperture radar, moving target indicator [4], and signals intelligence. A primary requirement for layered sensing is each sensor (layer) must be georegistered to allow the sensors to align with each other [5].

show abstract

Section: Transformation F^from Image To Cameramentioning

confidence: 99%

Camera models for the wright patterson air force base (WPAFB) 2009 wide-area motion imagery (WAMI) data set

Cohenour

Graas

Price

et al. 2015

IEEE Aerosp. Electron. Syst. Mag.

View full text Add to dashboard Cite

show abstract

“…We used a local information image for registration instead of ultrasound images because their natural properties (speckle noise, high attenuation, and low contrast) will degrade the performance of the registration. To take advantage of both the structural information from the local phase and the geometric information from the local orientation [41], we proposed a confidence coefficient to combine the local orientation and local phase. Furthermore, we altered the SRAD filter before registration to improve the longitudinal disturbance suppression performance.…”

Section: Introductionmentioning

confidence: 99%

A Preprocess Method of External Disturbance Suppression for Carotid Wall Motion Estimation Using Local Phase and Orientation of B-Mode Ultrasound Sequences

Qiang

2019

BioMed Research International

View full text Add to dashboard Cite

Estimating the motions of the common carotid artery wall plays a very important role in early diagnosis of the carotid atherosclerotic disease. However, the disturbances caused by either the instability of the probe operator or the breathing of subjects degrade the estimation accuracy of arterial wall motion when performing speckle tracking on the B-mode ultrasound images. In this paper, we propose a global registration method to suppress external disturbances before motion estimation. The local vector images, transformed from B-mode images, were used for registration. To take advantage of both the structural information from the local phase and the geometric information from the local orientation, we proposed a confidence coefficient to combine them two. Furthermore, we altered the speckle reducing anisotropic diffusion filter to improve the performance of disturbance suppression. We compared this method with schemes of extracting wall displacement directly from B-mode or phase images. The results show that this scheme can effectively suppress the disturbances and significantly improve the estimation accuracy.

show abstract

“…Target tracking has been extensively investigated as described in many papers [ 13 , 14 , 15 , 16 , 17 ]. Santhaseelan et al [ 18 ] proposed a robust feature-based method to track objects in WAMI data by exploiting local phased and orientation information based on the monogenic signal representation. However, this method does not present a systematical architecture for a prototype.…”

Section: Introductionmentioning

confidence: 99%

A Real-Time High Performance Computation Architecture for Multiple Moving Target Tracking Based on Wide-Area Motion Imagery via Cloud and Graphic Processing Units

Liu

Wei

Chen

et al. 2017

Sensors

View full text Add to dashboard Cite

This paper presents the first attempt at combining Cloud with Graphic Processing Units (GPUs) in a complementary manner within the framework of a real-time high performance computation architecture for the application of detecting and tracking multiple moving targets based on Wide Area Motion Imagery (WAMI). More specifically, the GPU and Cloud Moving Target Tracking (GC-MTT) system applied a front-end web based server to perform the interaction with Hadoop and highly parallelized computation functions based on the Compute Unified Device Architecture (CUDA©). The introduced multiple moving target detection and tracking method can be extended to other applications such as pedestrian tracking, group tracking, and Patterns of Life (PoL) analysis. The cloud and GPUs based computing provides an efficient real-time target recognition and tracking approach as compared to methods when the work flow is applied using only central processing units (CPUs). The simultaneous tracking and recognition results demonstrate that a GC-MTT based approach provides drastically improved tracking with low frame rates over realistic conditions.

show abstract

Tracking in Wide Area Motion Imagery Using Phase Vector Fields

Cited by 12 publications

References 13 publications

Camera models for the wright patterson air force base (WPAFB) 2009 wide-area motion imagery (WAMI) data set

Camera models for the wright patterson air force base (WPAFB) 2009 wide-area motion imagery (WAMI) data set

A Preprocess Method of External Disturbance Suppression for Carotid Wall Motion Estimation Using Local Phase and Orientation of B-Mode Ultrasound Sequences

A Real-Time High Performance Computation Architecture for Multiple Moving Target Tracking Based on Wide-Area Motion Imagery via Cloud and Graphic Processing Units

Contact Info

Product

Resources

About