scholarly journals Attitude estimation using horizon detection in thermal images

2018 ◽  
Vol 10 (4) ◽  
pp. 352-361 ◽  
Author(s):  
Adrian Carrio ◽  
Hriday Bavle ◽  
Pascual Campoy
Keyword(s):  
Unmanned Aerial Vehicles ◽  
Infinite Horizon ◽  
Attitude Estimation ◽  
Thermal Image ◽  
Image Sensors ◽  
Image Resolution ◽  
Estimation Methods ◽  
Operation Conditions ◽  
Aerial Vehicles ◽  
Horizon Detection

The lack of redundant attitude sensors represents a considerable yet common vulnerability in many low-cost unmanned aerial vehicles. In addition to the use of attitude sensors, exploiting the horizon as a visual reference for attitude control is part of human pilots’ training. For this reason, and given the desirable properties of image sensors, quite a lot of research has been conducted proposing the use of vision sensors for horizon detection in order to obtain redundant attitude estimation onboard unmanned aerial vehicles. However, atmospheric and illumination conditions may hinder the operability of visible light image sensors, or even make their use impractical, such as during the night. Thermal infrared image sensors have a much wider range of operation conditions and their price has greatly decreased during the last years, becoming an alternative to visible spectrum sensors in certain operation scenarios. In this paper, two attitude estimation methods are proposed. The first method consists of a novel approach to estimate the line that best fits the horizon in a thermal image. The resulting line is then used to estimate the pitch and roll angles using an infinite horizon line model. The second method uses deep learning to predict attitude angles using raw pixel intensities from a thermal image. For this, a novel Convolutional Neural Network architecture has been trained using measurements from an inertial navigation system. Both methods presented are proven to be valid for redundant attitude estimation, providing RMS errors below 1.7° and running at up to 48 Hz, depending on the chosen method, the input image resolution and the available computational capabilities.

scholarly journals ON PRACTICAL ACCURACY ASPECTS OF UNMANNED AERIAL VEHICLES EQUIPPED WITH SURVEY GRADE LASER SCANNERS

2020 ◽  
Vol XLIII-B1-2020 ◽  
pp. 343-348
Author(s):  
K. Nakano ◽  
Y. Tanaka ◽  
H. Suzuki ◽  
K. Hayakawa ◽  
M. Kurodai
Keyword(s):  
Unmanned Aerial Vehicles ◽  
High Performance ◽  
Laser Scanner ◽  
Image Sensors ◽  
Measuring Devices ◽  
Aerial Vehicles ◽  
Laser Scanners ◽  
Surface Models ◽  
Reconstruction Software ◽  
Practical Accuracy

Abstract. Unmanned aerial vehicles (UAVs) equipped with image sensors, which have been widely used in various fields such as construction, agriculture, and disaster management, can obtain images at the millimeter to decimeter scale. Useful tools that produce realistic surface models using 3D reconstruction software based on computer vision technologies are generally used to produce datasets from acquired images using UAVs. However, it is difficult to obtain the feature points from surfaces with limited texture, such as new asphalt or concrete, or detect the ground in areas such as forests, which are commonly concealed by vegetation. A promising method to address such issues is the use of UAV-equipped laser scanners. Recently, low and high performance products that use direct georeferencing devices integrated with laser scanners have been available. Moreover, there have been numerous reports regarding the various applications of UAVs equipped with laser scanners; however, these reports only discuss UAVs as measuring devices. Therefore, to understand the functioning of UAVs equipped with laser scanners, we investigated the theoretical accuracy of the survey grade laser scanner unit from the viewpoint of photogrammetry. We evaluated the performance of the VUX-1HA laser scanner equipped on a Skymatix X-LS1 UAV at a construction site. We presented the theoretical values obtained using the observation equations and results of the accuracy aspects of the acquired data in terms of height.

scholarly journals Using Unmanned Aerial Vehicles (UAV) for free-roaming dog population size estimation

2019 ◽  
Author(s):  
Charlotte Warembourg ◽  
Monica Berger-González ◽  
Danilo Alvarez ◽  
Filipe Maximiano Sousa ◽  
Alexis López Hernández ◽  
...  
Keyword(s):  
Statistical Model ◽  
Unmanned Aerial Vehicles ◽  
Population Size ◽  
Census Data ◽  
Population Size Estimation ◽  
Domestic Dog ◽  
Estimation Methods ◽  
Size Estimation ◽  
Aerial Vehicles ◽  
Capture Recapture

AbstractPopulation size estimation is performed for several reasons including disease surveillance and control, for example to design adequate control strategies such as vaccination programs or to estimate a vaccination campaign coverage. In this study, we aimed at assessing the benefits and challenges of using Unmanned Aerial Vehicles (UAV) to estimate the size of free-roaming domestic dog (FRDD) populations and compare the results with two regularly used methods for population estimations: a Bayesian statistical model based on capture-recapture data and the human:dog ratio estimation. Three studies sites of one square kilometer were selected in Petén department, Guatemala. UAV flight were conducted twice during two consecutive days per study site. The UAV’s camera was set to regularly take pictures and cover the entire surface of the selected areas. A door-to-door survey was conducted in the same areas, all available dogs were marked with a collar and owner were interviewed. Simultaneously to the UAV’s flight, transect walks were performed and the number of collared and non-collared dogs were recorded. Data collected during the interviews and the number of dogs counted during the transect walks informed a Bayesian statistical model. The number of dogs counted on the UAV’s pictures and the estimates given by the Bayesian statistical model, as well as the estimates derived from using a 5:1 human:dog ratio were compared to dog census data. FRDD could be detected using the UAV’s method. However, the method lacked of sensitivity, which could be overcome by choosing the flight timing and the study area wisely, or using infrared camera or automatic detection of the dogs. We also suggest to combine UAV and capture-recapture methods to obtain reliable FRDD population size estimated. This publication may provide helpful directions to design dog population size estimation methods using UAV.

scholarly journals ANALYSIS OF THE EFFICIENCY OF SPECTRAL ESTIMATION METHODS FOR DETECTION OF UAV ACOUSTIC SIGNALS

2021 ◽  
pp. 4-15
Author(s):  
М. V. Buhaiov ◽  
V. V. Branovytskyi ◽  
Y. O. Khorenko
Keyword(s):  
Acoustic Emission ◽  
Unmanned Aerial Vehicles ◽  
Acoustic Signal ◽  
Spectral Estimation ◽  
Acoustic Signals ◽  
Frequency Resolution ◽  
Estimation Methods ◽  
Signal To Noise ◽  
Statistical Quality ◽  
Aerial Vehicles

One of the most important components of counteracting small unmanned aerial vehicles is their reliable detection. You can use propeller noise to detect such objects at short distances. An energy or harmonic detector is used to receive unmanned aerial vehicles acoustic emission. At low signal-to-noise ratios , which is most common in practice, the harmonic detector provides a higher probability of detection compared to energy. The principle of the harmonic detector is based on spectral analysis of acoustic signals. A mathematical model of the acoustic signal of an aircraft-type unmanned aerial vehicles is proposed. It is shown that at short time intervals (tens of milliseconds) such signals can be considered as stationary and for its analysis can be used known methods of spectral estimation. Nonparametric, parametric and subspace methods of spectral estimation are considered for processing of acoustic emission of unmanned aerial vehicles. To conduct a comparative analysis of different methods of spectral estimation, a statistical quality index was used, which can be calculated as a variation of the estimation of power spectral density. This index characterizes the method of spectral estimation in terms of frequency resolution and the ability to detect harmonic components of the signal into noise and not create interference that exceeds the amplitude of the signal. As a result of researches it was established that at high signal-to-noise ratios parametric methods are more effective in comparison with nonparametric. However, such a statement will be valid only if the correct order of the model. It is shown that the use of spatial methods is impractical for the analysis of acoustic signals of unmanned aerial vehicles. The use of the value of the statistical quality indicator as a threshold for deciding on the presence or absence of the acoustic signal of the unmanned aerial vehicles in the adopted implementation and its further processing should be used at SNR values greater than 5 dB.

scholarly journals UAV attitude estimation based on MARG and optical flow sensors using gated recurrent unit

2021 ◽  
Vol 17 (4) ◽  
pp. 155014772110098
Author(s):  
Xiaoqin Liu ◽  
Xiang Li ◽  
Qi Shi ◽  
Chuanpei Xu ◽  
Yanmei Tang
Keyword(s):  
Optical Flow ◽  
Unmanned Aerial Vehicles ◽  
Three Dimensional ◽  
Flight Test ◽  
Attitude Estimation ◽  
Flow Sensors ◽  
Flow Measurements ◽  
Aerial Vehicles ◽  
Optical Flow Sensor ◽  
Gated Recurrent Unit

Three-dimensional attitude estimation for unmanned aerial vehicles is usually based on the combination of magnetometer, accelerometer, and gyroscope (MARG). But MARG sensor can be easily affected by various disturbances, for example, vibration, external magnetic interference, and gyro drift. Optical flow sensor has the ability to extract motion information from image sequence, and thus, it is potential to augment three-dimensional attitude estimation for unmanned aerial vehicles. But the major problem is that the optical flow can be caused by both translational and rotational movements, which are difficult to be distinguished from each other. To solve the above problems, this article uses a gated recurrent unit neural network to implement data fusion for MARG and optical flow sensors, so as to enhance the accuracy of three-dimensional attitude estimation for unmanned aerial vehicles. The proposed algorithm can effectively make use of the attitude information contained in the optical flow measurements and can also achieve multi-sensor fusion for attitude estimation without explicit mathematical model. Compared with the commonly used extended Kalman filter algorithm for attitude estimation, the proposed algorithm shows higher accuracy in the flight test of quad-rotor unmanned aerial vehicles.

scholarly journals 3-D Unitary ESPRIT: Accurate attitude estimation for unmanned aerial vehicles with a hexagon-shaped ESPAR array

2013 ◽  
Vol 23 (3) ◽  
pp. 701-711 ◽  
Author(s):  
Kefei Liu ◽  
João Paulo C.L. da Costa ◽  
Hing Cheung So ◽  
Florian Römer ◽  
Martin Haardt ◽  
...  
Keyword(s):  
Unmanned Aerial Vehicles ◽  
Attitude Estimation ◽  
Aerial Vehicles

scholarly journals Seed and Seedling Detection Using Unmanned Aerial Vehicles and Automated Image Classification in the Monitoring of Ecological Recovery

Drones ◽  
2019 ◽  
Vol 3 (3) ◽  
pp. 53 ◽  
Author(s):  
Buters ◽  
Belton ◽  
Cross
Keyword(s):  
Unmanned Aerial Vehicles ◽  
Substrate Surface ◽  
Morphological Characteristics ◽  
Ecological Monitoring ◽  
Image Resolution ◽  
Automated Classification ◽  
Aerial Vehicles ◽  
Novel Approach ◽  
Plant Life Cycle ◽  
Ecological Recovery

Monitoring is a crucial component of ecological recovery projects, yet it can be challenging to achieve at scale and during the formative stages of plant establishment. The monitoring of seeds and seedlings, which represent extremely vulnerable stages in the plant life cycle, is particularly challenging due to their diminutive size and lack of distinctive morphological characteristics. Counting and classifying seedlings to species level can be time-consuming and extremely difficult, and there is a need for technological approaches offering restoration practitioners with fine-resolution, rapid and scalable plant-based monitoring solutions. Unmanned aerial vehicles (UAVs) offer a novel approach to seed and seedling monitoring, as the combination of high-resolution sensors and low flight altitudes allow for the detection and monitoring of small objects, even in challenging terrain and in remote areas. This study utilized low-altitude UAV imagery and an automated object-based image analysis software to detect and count target seeds and seedlings from a matrix of non-target grasses across a variety of substrates reflective of local restoration substrates. Automated classification of target seeds and target seedlings was achieved at accuracies exceeding 90% and 80%, respectively, although the classification accuracy decreased with increasing flight altitude (i.e., decreasing image resolution) and increasing background surface complexity (increasing percentage cover of non-target grasses and substrate surface texture). Results represent the first empirical evidence that small objects such as seeds and seedlings can be classified from complex ecological backgrounds using automated processes from UAV-imagery with high levels of accuracy. We suggest that this novel application of UAV use in ecological monitoring offers restoration practitioners an excellent tool for rapid, reliable and non-destructive early restoration trajectory assessment.

Sign in / Sign up

Export Citation Format

Share Document