Wide-Area Persistent Airborne Video: Architecture and Challenges

Palaniappan, Kannappan; Rao, Raghuveer M.; Seetharaman, Guna

doi:10.1007/978-0-85729-127-1_24

Cited by 52 publications

(32 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In sequential image capture, we know which frames are adjacent to each other, as in persistent aerial WAMI [39] or hyper-lapse first person videos [27]. By leveraging this powerful temporal consistency constraint between images as prior information, we reduce the time complexity of matching, N c cameras, from O(N 2 c ) to O(N c ), without compromising the quality of BA results [45].…”

Section: Building Feature Tracksmentioning

confidence: 99%

“…However, many (inexpensive) aerial platforms produce IMU and GPS values of limited accuracy due to measurement and timing errors which then need to be refined for accurate SfM [24]. Extracting and incorporating 3D information in WAMI processing [39,11] will be very useful for mitigating parallax effects in video summarization [52], better stabilization and appearance models for tracking [38], depth map filtering of motion detections [53], and improving video analytics like object tracking [41,40].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Structure from Motion for Sequential and Wide Area Motion Imagery

Aliakbarpour

Palaniappan

Seetharaman

2015

2015 IEEE International Conference on Computer Vision Workshop (ICCVW)

Self Cite

View full text Add to dashboard Cite

We present a fast and efficient Structure-from-Motion (SfM) pipeline for refinement of camera parameters and 3D scene reconstruction given initial noisy camera metadata measurements. Examples include aerial Wide Area Motion Imagery (WAMI) which is typically acquired in a circular trajectory and other sequentially ordered multiview stereo imagery like Middlebury [46], Fountain [50] or body-worn videos [27]. Image frames are assumed (partially) ordered with approximate camera position and orientation information available from (imprecise) IMU and GPS sensors. In the proposed BA4S pipeline the noisy camera parameters or poses are directly used in a fast Bundle Adjustment (BA) optimization. Since the sequential ordering of the cameras is known, consecutive frame-to-frame matching is used to find a set of feature correspondences for the triangulation step of SfM. These putative correspondences are directly used in the BA optimization without any early-stage filtering (i.e. no RANSAC) using a statistical robust error function based on co-visibility, to deal with outliers (mismatches), which significantly speeds up our SfM pipeline by more than 100 times compared to VisualSfM.

show abstract

Section: Building Feature Tracksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fast Structure from Motion for Sequential and Wide Area Motion Imagery

Aliakbarpour

Palaniappan

Seetharaman

2015

2015 IEEE International Conference on Computer Vision Workshop (ICCVW)

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, Wide Area Surveillance (WAS): the environment is continuously monitored by a sensing system One source of data is the wide-area large format (WALF) video that is airborne imagery characterized by large spatial coverage, high resolution of about 25 cm GSD (Ground Sampling Distance) and low frame rate of a few frames per second. Wide-area large format imagery is also known by several other terms including wide-area aerial surveillance (WAAS), wide-area persistent surveillance (WAPS), Large Volume Streaming Data (LVSD) and wide-area motion imagery (WAMI) [1,4,6,7].…”

Section: Motivationmentioning

confidence: 99%

Modelling and Characterisation of Detection Models in WAMI for Handling Negative Information

Julier¹,

Gning²,

Teacy³

et al. 2014

Self Cite

View full text Add to dashboard Cite

Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing the burden, to Department of Defense, Washington Headquarters Services, Directorate for Information SPONSOR/MONITOR'S ACRONYM(S)AFRL/AFOSR/IOE (EOARD) SPONSOR/MONITOR'S REPORT NUMBER(S) AFRL-AFOSR-UK-TR-2014-000612. DISTRIBUTION/AVAILABILITY STATEMENT Distribution A: Approved for public release; distribution is unlimited. SUPPLEMENTARY NOTES ABSTRACTThe objective of the project reported here was to develop, implement and evaluate a model of the probability of detection of moving objects in Wide Area Motion Imagery (WAMI) that incorporates the effects of the target, the platform, and the environment. Developing situation awareness is vital for almost any kind of military operation. Through understanding the state and nature of the environment, military personnel can plan and respond accordingly. Situation awareness is often treated as the problem of knowing where all the potential targets are. Through knowing the locations of these targets, threats can be identified and countered. Another important source of awareness is to understand where targets cannot be. Regions that are free of targets can be used to constrain where targets might be. To meet these needs, Wide Area Surveillance (WAS) systems have been developed that are able to sense large swaths of an environment simultaneously and at high resolution. However, the next key challenge is to automatically analyze this image data to, for example, track the locations of targets and identify potential anomalous behavior. This report begins to explore how the output from a WAS system can be used by a state-of-the-art multi-target tracker. In particular, we considered how the output of the image processing and matching algorithms used in the Likelihood of Features Tracker (LoFT) could be combined with a Probabilistic Hypothesis Density (PHD) Filter. Using machine learning techniques, we have developed a formalism and algorithms to automatically predict how the visual appearance of a vehicle can change over time. Using this prediction model, we are then able to automatically threshold and detect potential candidate vehicle locations, and assess both probability of detection and the probability of clutter. SUBJECT TERMS Executive SummaryDeveloping situation awareness is vital for almost any kind of military operation. Through understanding the state and nature of the environment, military personnel can plan and respond accordingly. Situation awareness is often treated as the problem of knowing where all the potential targets are. Through knowing the locations of these targets, threats can be identified and countered. To meet these needs, Wide Area Su...

show abstract

“…11 Since the landmark publication by Porter, 12 feature extraction has been an important component of WAMI exploitation for tracking, 13,14,17,18 architecture design, 15 and registration. 16 Feature extraction has also supported methods for learning, 19 situation awareness, 20 and semantic uncertainty analysis.…”

Section: Introductionmentioning

confidence: 99%

Efficient feature extraction from wide-area motion imagery by MapReduce in Hadoop

Cheng

Blaisse

et al. 2014

SPIE Proceedings

View full text Add to dashboard Cite

Wide-Area Motion Imagery (WAMI) feature extraction is important for applications such as target tracking, traffic management and accident discovery. With the increasing amount of WAMI collections and feature extraction from the data, a scalable framework is needed to handle the large amount of information. Cloud computing is one of the approaches recently applied in large scale or big data. In this paper, MapReduce in Hadoop is investigated for large scale feature extraction tasks for WAMI. Specifically, a large dataset of WAMI images is divided into several splits. Each split has a small subset of WAMI images. The feature extractions of WAMI images in each split are distributed to slave nodes in the Hadoop system. Feature extraction of each image is performed individually in the assigned slave node. Finally, the feature extraction results are sent to the Hadoop File System (HDFS) to aggregate the feature information over the collected imagery. Experiments of feature extraction with and without MapReduce are conducted to illustrate the effectiveness of our proposed Cloud-Enabled WAMI Exploitation (CAWE) approach.

show abstract

Wide-Area Persistent Airborne Video: Architecture and Challenges

Cited by 52 publications

References 18 publications

Fast Structure from Motion for Sequential and Wide Area Motion Imagery

Fast Structure from Motion for Sequential and Wide Area Motion Imagery

Modelling and Characterisation of Detection Models in WAMI for Handling Negative Information

Efficient feature extraction from wide-area motion imagery by MapReduce in Hadoop

Contact Info

Product

Resources

About