Classification of UAV and bird target in low-altitude airspace with surveillance radar data

2019 ◽  
Vol 123 (1260) ◽  
pp. 191-211 ◽  
Author(s):  
W. S. Chen ◽  
J. Liu ◽  
J. Li
Keyword(s):  
Ground Truth ◽  
Radar Data ◽  
Motion Models ◽  
Algorithm Comparison ◽  
Aerial Vehicle ◽  
Low Altitude ◽  
The Time Domain ◽  
Model Conversion ◽  
Traditional Surveillance

ABSTRACTIn order to ensure low-altitude safety, a tracking and recognition method of unmanned aerial vehicle (UAV) and bird targets based on traditional surveillance radar data is proposed. First, several motion models for UAV and flying bird targets are established. Second, the target trajectories are filtered and smoothed with multiple motion models. Third, by calculating the time-domain variance of the model occurrence probability, the model conversion probability of the target is estimated, and then the target type is identified and classified. The effectiveness and robustness of the algorithm is demonstrated by several groups of Monte Carlo simulation experiments, including setting different recognition steps, different model transformation probability, filtering and smoothing algorithm comparison. The algorithm is also successfully applied on the ground-truth radar data collected by the low-altitude surveillance radar at airport and coastal environments, where the targets of UAVs and flying birds could be tracked and recognised.

Development of the navigation complex structure for a high-precision unmanned aerial vehicle for flight in the atmosphere

2020 ◽  
Keyword(s):  
Mathematical Modeling ◽  
Unmanned Aerial Vehicle ◽  
High Precision ◽  
Kalman Filters ◽  
Inertial Navigation System ◽  
Complex Structure ◽  
Navigation Systems ◽  
Aerial Vehicle ◽  
Low Altitude ◽  
System Errors

The navigation systems as part of the navigation complex of a high-precision unmanned aerial vehicle in conditions of different altitude flight are investigated. The working contours of the navigation complex with correction algorithms for an unmanned aerial vehicle during high-altitude and low-altitude flights are formed. Mathematical models of inertial navigation system errors used in non-linear and linear Kalman filters are presented. The results of mathematical modeling demonstrate the effectiveness of the working contours effectiveness of the navigation complex with correction algorithms. Keywords high-precision unmanned aerial vehicle; navigation complex; multi-altitude flight; work circuit; passive noises; Kalman filter; correction

scholarly journals Reference Measurements in Developing UAV Systems for Detecting Pests, Weeds, and Diseases

2021 ◽  
Vol 13 (7) ◽  
pp. 1238
Author(s):  
Jere Kaivosoja ◽  
Juho Hautsalo ◽  
Jaakko Heikkinen ◽  
Lea Hiltunen ◽  
Pentti Ruuttunen ◽  
...  
Keyword(s):  
Reference Data ◽  
Measurement Techniques ◽  
Synthetic Data ◽  
Ground Truth ◽  
Precision Farming ◽  
Aerial Imaging ◽  
Aerial Vehicle ◽  
Uav Images ◽  
Reference Measurements

The development of UAV (unmanned aerial vehicle) imaging technologies for precision farming applications is rapid, and new studies are published frequently. In cases where measurements are based on aerial imaging, there is the need to have ground truth or reference data in order to develop reliable applications. However, in several precision farming use cases such as pests, weeds, and diseases detection, the reference data can be subjective or relatively difficult to capture. Furthermore, the collection of reference data is usually laborious and time consuming. It also appears that it is difficult to develop generalisable solutions for these areas. This review studies previous research related to pests, weeds, and diseases detection and mapping using UAV imaging in the precision farming context, underpinning the applied reference measurement techniques. The majority of the reviewed studies utilised subjective visual observations of UAV images, and only a few applied in situ measurements. The conclusion of the review is that there is a lack of quantitative and repeatable reference data measurement solutions in the areas of mapping pests, weeds, and diseases. In addition, the results that the studies present should be reflected in the applied references. An option in the future approach could be the use of synthetic data as reference.

Classification of ground-truth fire debris samples using artificial neural networks

2021 ◽  
Vol 23 ◽  
pp. 100313
Author(s):  
Nicholas A. Thurn ◽  
Taylor Wood ◽  
Mary R. Williams ◽  
Michael E. Sigman
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Ground Truth ◽  
Fire Debris ◽  
Artificial Neural

scholarly journals Classification of unlabeled online media

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Sakthi Kumar Arul Prakash ◽  
Conrad Tucker
Keyword(s):  
Social Media ◽  
Real World ◽  
Graphical Model ◽  
Ground Truth ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Social Media Networks ◽  
Online Social Media ◽  
Wide Range

AbstractThis work investigates the ability to classify misinformation in online social media networks in a manner that avoids the need for ground truth labels. Rather than approach the classification problem as a task for humans or machine learning algorithms, this work leverages user–user and user–media (i.e.,media likes) interactions to infer the type of information (fake vs. authentic) being spread, without needing to know the actual details of the information itself. To study the inception and evolution of user–user and user–media interactions over time, we create an experimental platform that mimics the functionality of real-world social media networks. We develop a graphical model that considers the evolution of this network topology to model the uncertainty (entropy) propagation when fake and authentic media disseminates across the network. The creation of a real-world social media network enables a wide range of hypotheses to be tested pertaining to users, their interactions with other users, and with media content. The discovery that the entropy of user–user and user–media interactions approximate fake and authentic media likes, enables us to classify fake media in an unsupervised learning manner.

scholarly journals Evaluation of Fengyun-4A Lightning Mapping Imager (LMI) Performance during Multiple Convective Episodes over Beijing

2021 ◽  
Vol 13 (9) ◽  
pp. 1746
Author(s):  
Zhixiong Chen ◽  
Xiushu Qie ◽  
Juanzhen Sun ◽  
Xian Xiao ◽  
Yuxin Zhang ◽  
...  
Keyword(s):  
Doppler Radar ◽  
Detection Efficiency ◽  
Ground Truth ◽  
Radar Data ◽  
Detection Capability ◽  
Cloud Properties ◽  
Order Of Magnitude ◽  
Total Lightning ◽  
Matching Criteria ◽  
Event Based

This study investigates the characteristics of space-borne Lightning Mapping Imager (LMI) lightning products and their relationships with cloud properties using ground-based total lightning observations from the Beijing Broadband Lightning Network (BLNET) and cloud information from S-band Doppler radar data. LMI showed generally consistent lightning spatial distributions with those of BLNET, and yielded a considerable lightning detection capability over regions with complex terrain. The ratios between the LMI events, groups and flashes were approximately 9:3:1, and the number of LMI-detected flashes was roughly one order of magnitude smaller than the number of BLNET-detected flashes. However, in different convective episodes, the LMI detection capability was likely to be affected by cloud properties, especially in strongly electrified convective episodes associated with frequent lightning discharging and thick cloud depth. As a result, LMI tended to detect lightning flashes located in weaker and shallower cloud portions associated with fewer cloud shielding effects. With reference to the BLNET total lightning data as the ground truth of observation (both intra-cloud lightning and cloud-to-ground lightning flashes), the LMI event-based detection efficiency (DE) was estimated to reach 28% under rational spatiotemporal matching criteria (1.5 s and 65 km) over Beijing. In terms of LMI flash-based DE, it was much reduced compared with event-based DE. The LMI flash-based ranged between 1.5% and 3.5% with 1.5 s and 35–65 km matching scales. For 330 ms and 35 km, the spatiotemporal matching criteria used to evaluate Geostationary Lightning Mapper (GLM), the LMI flash-based DE was smaller (<1%).

scholarly journals fNIRS Signal Classification Based on Deep Learning in Rock-Paper-Scissors Imagery Task

2021 ◽  
Vol 11 (11) ◽  
pp. 4922
Author(s):  
Tengfei Ma ◽  
Wentian Chen ◽  
Xin Li ◽  
Yuting Xia ◽  
Xinhua Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Total Duration ◽  
Signal Classification ◽  
Imagery Task ◽  
Neural Activities ◽  
Computer Interfaces ◽  
Acquisition Device ◽  
The Time Domain ◽  
The Brain

To explore whether the brain contains pattern differences in the rock–paper–scissors (RPS) imagery task, this paper attempts to classify this task using fNIRS and deep learning. In this study, we designed an RPS task with a total duration of 25 min and 40 s, and recruited 22 volunteers for the experiment. We used the fNIRS acquisition device (FOIRE-3000) to record the cerebral neural activities of these participants in the RPS task. The time series classification (TSC) algorithm was introduced into the time-domain fNIRS signal classification. Experiments show that CNN-based TSC methods can achieve 97% accuracy in RPS classification. CNN-based TSC method is suitable for the classification of fNIRS signals in RPS motor imagery tasks, and may find new application directions for the development of brain–computer interfaces (BCI).

INTEGRATING FUZZY C-MEANS AND MAHALANOBIS METRIC CLASSIFICATION FOR EXUDATE DETECTION IN COLOR FUNDUS IMAGING

2015 ◽  
Vol 15 (05) ◽  
pp. 1550085 ◽  
Author(s):  
MADHURI TASGAONKAR ◽  
MADHURI KHAMBETE
Keyword(s):  
Diabetic Retinopathy ◽  
Early Detection ◽  
Ground Truth ◽  
Vital Role ◽  
Detection Accuracy ◽  
Fuzzy C Means ◽  
Fundus Imaging ◽  
Imaging Detection ◽  
Retinal Structure

Diabetes affects retinal structure of a diabetic patient by generating various lesions. Early detection of these lesions can avoid the loss of vision. Automation of detection process can be made easily feasible to masses by the use of fundus imaging. Detection of exudates is significant in diabetic retinopathy (DR) as they are earlier signs and can cause blindness. Finding the exact location as well as correct number of exudates play vital role in the overall treatment of a patient. This paper presents an algorithm for automatic detection of exudates for DR. The algorithm combines the advantages of supervised and unsupervised techniques. It uses fuzzy-C means (FCM) segmentation on coarse level and mahalanobis metric for finer classification of segmented pixels. Mahalanobis criterion gives significance to most relevant features and thus proves a better classifier. The results are validated using DIARETDB0 and DIARETDB1 databases and the ground truth provided with it. This evaluation provided 95.77% detection accuracy.

scholarly journals Gaussian Model Adaptive Processing in Time Domain (GMAP-TD) for Weather Radars

2013 ◽  
Vol 30 (11) ◽  
pp. 2571-2584 ◽  
Author(s):  
Cuong M. Nguyen ◽  
V. Chandrasekar
Keyword(s):  
Time Domain ◽  
Gaussian Model ◽  
Radar Data ◽  
Adaptive Processing ◽  
Colorado State University ◽  
Weather Radars ◽  
Ground Clutter ◽  
Moment Estimation ◽  
Interpolation Procedure ◽  
The Time Domain

Abstract The Gaussian model adaptive processing in the time domain (GMAP-TD) method for ground clutter suppression and signal spectral moment estimation for weather radars is presented. The technique transforms the clutter component of a weather radar return signal to noise. Additionally, an interpolation procedure has been developed to recover the portion of weather echoes that overlap clutter. It is shown that GMAP-TD improves the performance over the GMAP algorithm that operates in the frequency domain using both signal simulations and experimental observations. Furthermore, GMAP-TD can be directly extended for use with a staggered pulse repetition time (PRT) waveform. A detailed evaluation of GMAP-TD performance and comparison against the GMAP are done using simulated radar data and observations from the Colorado State University–University of Chicago–Illinois State Water Survey (CSU–CHILL) radar using uniform and staggered PRT waveform schemes.

scholarly journals Identifying Potential Mosquito Breeding Grounds: Assessing the Efficiency of UAV Technology in Public Health

Robotics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 91
Author(s):  
Jared Schenkel ◽  
Paul Taele ◽  
Daniel Goldberg ◽  
Jennifer Horney ◽  
Tracy Hammond
Keyword(s):  
Form Factor ◽  
Unmanned Aerial Vehicles ◽  
Ground Truth ◽  
Gps Receivers ◽  
Aerial Vehicles ◽  
Breeding Grounds ◽  
Aerial Vehicle ◽  
Mosquito Breeding ◽  
Small Form Factor ◽  
Local Transmission

Human ecology has played an essential role in the spread of mosquito-borne diseases. With standing water as a significant factor contributing to mosquito breeding, artificial containers disposed of as trash—which are capable of holding standing water—provide suitable environments for mosquito larvae to develop. The development of these larvae further contributes to the possibility for local transmission of mosquito-borne diseases in urban areas such as Zika virus. One potential solution to address this issue involves leveraging unmanned aerial vehicles that are already systematically becoming more utilized in the field of geospatial technology. With higher pixel resolution in comparison to satellite imagery, as well as having the ability to update spatial data more frequently, we are interested in investigating the feasibility of unmanned aerial vehicles as a potential technology for efficiently mapping potential breeding grounds. Therefore, we conducted a comparative study that evaluated the performance of an unmanned aerial vehicle for identifying artificial containers to that of conventionally utilized GPS receivers. The study was designed to better inform researchers on the current viability of such devices for locating a potential factor (i.e., small form factor artificial containers that can host mosquito breeding grounds) in the local transmission of mosquito-borne diseases. By assessing the performance of an unmanned aerial vehicle against ground-truth global position system technology, we can determine the effectiveness of unmanned aerial vehicles on this problem through our selected metrics of: timeliness, sensitivity, and specificity. For the study, we investigated these effectiveness metrics between the two technologies of interest in surveying a study area: unmanned aerial vehicles (i.e., DJI Phantom 3 Standard) and global position system-based receivers (i.e., Garmin GPSMAP 76Cx and the Garmin GPSMAP 78). We first conducted a design study with nine external participants, who collected 678 waypoint data and 214 aerial images from commercial GPS receivers and UAV, respectively. The participants then processed these data with professional mapping software for visually identifying and spatially marking artificial containers between the aerial imagery and the ground truth GPS data, respectively. From applying statistical methods (i.e., two-tailed, paired t-test) on the participants’ data for comparing how the two technologies performed against each other, our data analysis revealed that the GPS method performed better than the UAV method for the study task of identifying the target small form factor artificial containers.

Sign in / Sign up

Export Citation Format

Share Document