Acoustical unmanned aerial vehicle detection in indoor scenarios using logistic regression model

2020 ◽  
pp. 1351010X2091785
Author(s):  
Gino Iannace ◽  
Giuseppe Ciaburro ◽  
Amelia Trematerra
Keyword(s):  
Logistic Regression ◽  
Unmanned Aerial Vehicle ◽  
Indoor Environment ◽  
Vehicle Detection ◽  
Sound Level ◽  
Shopping Center ◽  
Model Based ◽  
Aerial Vehicle ◽  
Level Meter ◽  
Indoor Scenarios

In this study, the data obtained from the acoustic measurements were used to train a model based on logistic regression in order to detect a quadrotor’s vehicle in indoor environment. To simulate a real environment, we made sound recordings in a shopping center. The sounds related to two scenarios were recorded: only anthropic noise and anthropic noise with background music. Later, we reproduced these sounds in an indoor environment of the same size and characteristics as the shopping center. During the simulation test, a drone placed at different distances from the sound level meter was turned on at different speeds to identify their presence in complex acoustic scenarios. Subsequently, these measurements were used to implement a model based on logistic regression for the automatic detection of the unmanned aerial vehicle. Logistic regression is widely used in pattern recognition of the binary dependent variable. This model returns high value of accuracy (0.994), indicating a high number of correct detections. The results obtained in this study suggest the use of this tool for unmanned aerial vehicle detection applications.

scholarly journals Research for the Presence of Unmanned Aerial Vehicle inside Closed Environments with Acoustic Measurements

Buildings ◽  
2020 ◽  
Vol 10 (5) ◽  
pp. 96
Author(s):  
Giuseppe Ciaburro ◽  
Gino Iannace ◽  
Amelia Trematerra
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Sound Level ◽  
Anthropogenic Noise ◽  
Acoustic Measurements ◽  
Noise Emission ◽  
Tonal Component ◽  
Aerial Vehicle ◽  
Level Meter ◽  
Closed Environment ◽  
Typical Frequency

Small UAVs (unmanned aerial vehicle) can be used in many sectors such as the acquisition of images or the transport of objects. Small UAVs have also been used for terrorist activities or to disturb the flight of airplanes. Due to the small size and the presence of only rotating parts, drones escape traditional controls and therefore represent a danger. This paper reports a methodology for identifying the presence of small UAVs inside a closed environment by measuring the noise emitted during the flight. Acoustic measurements of the noise emitted by a drone inside a large environment (12.0 × 30.0 × 12.0 m) were performed. The noise was measured with a sound level meter placed at different distances (5, 10, and 15 m), to characterize the noise in the absence of anthropic noise. In this configuration, a typical tonal component of drone noise is highlighted at the frequency of one-third of an octave at 5000 Hz due to the rotation of the blades. This component is also present 15 m away from the source point. Subsequent measurements were performed by introducing into the environment, through a loudspeaker, the anthropogenic noise produced by the buzz of people and background music. It is possible to distinguish the typical tonal component of UAV noise at the frequency of 5000 Hz even when the level of recording of anthropogenic noise emitted by the loudspeaker is at the maximum power tested. It is therefore possible to search for the presence of small UAVs inside a specific closed environment with only acoustic measurements, paying attention to the typical frequency of noise emission equal to 5000 Hz.

Fuzzy Model Based Control of Unmanned Aerial Vehicle

2012 ◽  
Vol 45 (1) ◽  
pp. 109-114 ◽  
Author(s):  
Shaaban A. Salman ◽  
Sreenatha G. Anavatti
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Fuzzy Model ◽  
Model Based Control ◽  
Model Based ◽  
Aerial Vehicle

scholarly journals Affine-Function Transformation-Based Object Matching for Vehicle Detection from Unmanned Aerial Vehicle Imagery

2019 ◽  
Vol 11 (14) ◽  
pp. 1708 ◽  
Author(s):  
Shuang Cao ◽  
Yongtao Yu ◽  
Haiyan Guan ◽  
Daifeng Peng ◽  
Wanqian Yan
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Vehicle Detection ◽  
Location Estimation ◽  
Affine Function ◽  
Response Elimination ◽  
Object Matching ◽  
Function Transformation ◽  
Segmentation Strategy ◽  
Aerial Vehicle ◽  
Uav Images

Vehicle detection from remote sensing images plays a significant role in transportation related applications. However, the scale variations, orientation variations, illumination variations, and partial occlusions of vehicles, as well as the image qualities, bring great challenges for accurate vehicle detection. In this paper, we present an affine-function transformation-based object matching framework for vehicle detection from unmanned aerial vehicle (UAV) images. First, meaningful and non-redundant patches are generated through a superpixel segmentation strategy. Then, the affine-function transformation-based object matching framework is applied to a vehicle template and each of the patches for vehicle existence estimation. Finally, vehicles are detected and located after matching cost thresholding, vehicle location estimation, and multiple response elimination. Quantitative evaluations on two UAV image datasets show that the proposed method achieves an average completeness, correctness, quality, and F1-measure of 0.909, 0.969, 0.883, and 0.938, respectively. Comparative studies also demonstrate that the proposed method achieves compatible performance with the Faster R-CNN and outperforms the other eight existing methods in accurately detecting vehicles of various conditions.

Model-Based Design of UAV Autopilot Software

2013 ◽  
Vol 756-759 ◽  
pp. 2115-2119
Author(s):  
Ming Zuo ◽  
Ying Liu ◽  
Yi Qian ◽  
Xiong Wen Hu ◽  
Xiao Chuan Zhao ◽  
...  
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Field Trials ◽  
Hardware In The Loop ◽  
Control Logic ◽  
Model Based ◽  
Aerial Vehicle ◽  
Trial Cost

This paper presents a Model-Based approach to develop UAV (Unmanned Aerial Vehicle) autopilot software. It employs Simulink to design the flight controller, Stateflow to implement control logic and Matlab coder to automatically generate embedded C code from the model developed. Software in the loop (SIL) and hardware in the loop (HIL) simulations are performed in the laboratory to validate the software developed. Flight trial cost and risks are minimized and the design cycles are greatly shortened. The feasibility and the effectiveness of the approach are verified through results from lab simulations and field trials.

Sign in / Sign up

Export Citation Format

Share Document