scholarly journals Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle

2021 ◽  
Vol 13 (5) ◽  
pp. 965
Author(s):  
Marek Kraft ◽  
Mateusz Piechocki ◽  
Bartosz Ptak ◽  
Krzysztof Walas
Keyword(s):  
Neural Networks ◽  
Unmanned Aerial Vehicle ◽  
Low Cost ◽  
Detection Algorithm ◽  
Aerial Images ◽  
Detection Accuracy ◽  
Deep Convolutional Neural Networks ◽  
Domain Specific ◽  
Aerial Vehicle ◽  
Low Altitude

Public littering and discarded trash are, despite the effort being put to limit it, still a serious ecological, aesthetic, and social problem. The problematic waste is usually localised and picked up by designated personnel, which is a tiresome, time-consuming task. This paper proposes a low-cost solution enabling the localisation of trash and litter objects in low altitude imagery collected by an unmanned aerial vehicle (UAV) during an autonomous patrol mission. The objects of interest are detected in the acquired images and put on the global map using a set of onboard sensors commonly found in typical UAV autopilots. The core object detection algorithm is based on deep, convolutional neural networks. Since the task is domain-specific, a dedicated dataset of images containing objects of interest was collected and annotated. The dataset is made publicly available, and its description is contained in the paper. The dataset was used to test a range of embedded devices enabling the deployment of deep neural networks for inference onboard the UAV. The results of measurements in terms of detection accuracy and processing speed are enclosed, and recommendations for the neural network model and hardware platform are given based on the obtained values. The complete system can be put together using inexpensive, off-the-shelf components, and perform autonomous localisation of discarded trash, relieving human personnel of this burdensome task, and enabling automated pickup planning.

scholarly journals Parallel Ensemble Deep Learning for Real-Time Remote Sensing Video Multi-Target Detection

2021 ◽  
Vol 13 (21) ◽  
pp. 4377
Author(s):  
Long Sun ◽  
Jie Chen ◽  
Dazheng Feng ◽  
Mengdao Xing
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Unmanned Aerial Vehicle ◽  
Target Detection ◽  
Template Matching ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Information Warfare ◽  
Aerial Vehicle ◽  
Uav Images

Unmanned aerial vehicle (UAV) is one of the main means of information warfare, such as in battlefield cruises, reconnaissance, and military strikes. Rapid detection and accurate recognition of key targets in UAV images are the basis of subsequent military tasks. The UAV image has characteristics of high resolution and small target size, and in practical application, the detection speed is often required to be fast. Existing algorithms are not able to achieve an effective trade-off between detection accuracy and speed. Therefore, this paper proposes a parallel ensemble deep learning framework for unmanned aerial vehicle video multi-target detection, which is a global and local joint detection strategy. It combines a deep learning target detection algorithm with template matching to make full use of image information. It also integrates multi-process and multi-threading mechanisms to speed up processing. Experiments show that the system has high detection accuracy for targets with focal lengths varying from one to ten times. At the same time, the real-time and stable display of detection results is realized by aiming at the moving UAV video image.

scholarly journals Photogrammetric mapping using unmanned aerial vehicle

2014 ◽  
Vol XL-1 ◽  
pp. 129-133 ◽  
Author(s):  
N. Graça ◽  
E. Mitishita ◽  
J. Gonçalves
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Rural Areas ◽  
Low Cost ◽  
Direct Determination ◽  
Aerial Images ◽  
Image Block ◽  
Exterior Orientation ◽  
Aerial Vehicle ◽  
Urban And Rural Areas ◽  
Orientation Parameters

Nowadays Unmanned Aerial Vehicle (UAV) technology has attracted attention for aerial photogrammetric mapping. The low cost and the feasibility to automatic flight along commanded waypoints can be considered as the main advantages of this technology in photogrammetric applications. Using GNSS/INS technologies the images are taken at the planned position of the exposure station and the exterior orientation parameters (position Xo, Yo, Zo and attitude ω, φ, χ) of images can be direct determined. However, common UAVs (off-the-shelf) do not replace the traditional aircraft platform. Overall, the main shortcomings are related to: difficulties to obtain the authorization to perform the flight in urban and rural areas, platform stability, safety flight, stability of the image block configuration, high number of the images and inaccuracies of the direct determination of the exterior orientation parameters of the images. In this paper are shown the obtained results from the project photogrammetric mapping using aerial images from the SIMEPAR UAV system. The PIPER J3 UAV Hydro aircraft was used. It has a micro pilot MP2128g. The system is fully integrated with 3-axis gyros/accelerometers, GPS, pressure altimeter, pressure airspeed sensors. A Sony Cyber-shot DSC-W300 was calibrated and used to get the image block. The flight height was close to 400 m, resulting GSD near to 0.10 m. The state of the art of the used technology, methodologies and the obtained results are shown and discussed. Finally advantages/shortcomings found in the study and main conclusions are presented

Implementation of vision-based automatic guidance system on a fixed-wing unmanned aerial vehicle

2012 ◽  
Vol 116 (1183) ◽  
pp. 895-914 ◽  
Author(s):  
C-S Lee ◽  
F-B Hsiao
Keyword(s):  
Image Processing ◽  
Unmanned Aerial Vehicle ◽  
Low Cost ◽  
Image Plane ◽  
Guidance System ◽  
Aerial Images ◽  
Colour Properties ◽  
Image Processing Algorithm ◽  
Automatic Guidance ◽  
Aerial Vehicle

Abstract This paper presents the design and implementation of a vision-based automatic guidance system on a fixed-wing unmanned aerial vehicle (UAV). The system utilises a low-cost ordinary video camera and simple but efficient image processing techniques widely used in computer-vision technology. The paper focuses on the identification and extraction of geographical tracks such as rivers, coastlines, and roads from real-time aerial images. The image processing algorithm primarily uses colour properties to isolate the geographical track of interest from its background. Hough transform is eventually used to curve-fit the profile of the track which yields a reference line on the image plane. A guidance algorithm is then derived based on this information. In order to test the vision-based automatic guidance system in the laboratory without actually flying the UAV, a hardware-in-the-loop simulation system is developed. Description regarding the system and significant simulation result are presented in the paper. Finally, an actual test flight where the UAV successfully follows a stretch of a river under automatic vision-based guidance is also presented and discussed.

scholarly journals A Low Cost Approach to Disturbed Soil Detection Using Low Altitude Digital Imagery from an Unmanned Aerial Vehicle

Drones ◽  
2019 ◽  
Vol 3 (2) ◽  
pp. 50
Author(s):  
Elizabeth Parrott ◽  
Heather Panter ◽  
Joanne Morrissey ◽  
Frederic Bezombes
Keyword(s):  
Remote Sensing ◽  
Unmanned Aerial Vehicle ◽  
Low Cost ◽  
Preliminary Investigation ◽  
Digital Imagery ◽  
Disturbed Soil ◽  
Clandestine Graves ◽  
Aerial Vehicle ◽  
Low Altitude ◽  
Witness Statements

Until recently, clandestine burial investigations relied upon witness statements to determine target search areas of soil and vegetation disturbance. Due to this, remote sensing technologies are increasingly used to detect fresh clandestine graves. However, despite the increased capabilities of remote sensing, clandestine burial searches remain resourcefully intensive as the police have little access to the technology when it is required. In contrast to this, Unmanned Aerial Vehicle (UAV) technology is increasingly popular amongst law enforcement worldwide. As such, this paper explores the use of digital imagery collected from a low cost UAV for the aided detection of disturbed soil sites indicative of fresh clandestine graves. This is done by assessing the unaltered UAV video output using image processing tools to detect sites of disturbance, therefore highlighting previously unrecognised capabilities of police UAVs. This preliminary investigation provides a low cost rapid approach to detecting fresh clandestine graves, further supporting the use of UAV technology by UK police.

scholarly journals Design of Citrus Fruit Detection System Based on Mobile Platform and Edge Computer Device

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 59
Author(s):  
Heqing Huang ◽  
Tongbin Huang ◽  
Zhen Li ◽  
Shilei Lyu ◽  
Tao Hong
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Target Detection ◽  
Detection System ◽  
Citrus Fruit ◽  
Detection Algorithm ◽  
Edge Computing ◽  
Detection Accuracy ◽  
Computing Device ◽  
Adaptive Fusion ◽  
Aerial Vehicle

Citrus fruit detection can provide technical support for fine management and yield determination of citrus orchards. Accurate detection of citrus fruits in mountain orchards is challenging because of leaf occlusion and citrus fruit mutual occlusion of different fruits. This paper presents a citrus detection task that combines UAV data collection, AI embedded device, and target detection algorithm. The system used a small unmanned aerial vehicle equipped with a camera to take full-scale pictures of citrus trees; at the same time, we extended the state-of-the-art model target detection algorithm, added the attention mechanism and adaptive fusion feature method, improved the model’s performance; to facilitate the deployment of the model, we used the pruning method to reduce the amount of model calculation and parameters. The improved target detection algorithm is ported to the edge computing end to detect the data collected by the unmanned aerial vehicle. The experiment was performed on the self-made citrus dataset, the detection accuracy was 93.32%, and the processing speed at the edge computing device was 180 ms/frame. This method is suitable for citrus detection tasks in the mountainous orchard environment, and it can help fruit growers to estimate their yield.

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 Road Extraction from Unmanned Aerial Vehicle Remote Sensing Images Based on Improved Neural Networks

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4115 ◽  
Author(s):  
Yuxia Li ◽  
Bo Peng ◽  
Lei He ◽  
Kunlong Fan ◽  
Zhenxu Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Neural Networks ◽  
Unmanned Aerial Vehicle ◽  
Computational Efficiency ◽  
Neural Nets ◽  
Road Extraction ◽  
Remote Sensing Images ◽  
Feature Maps ◽  
Aerial Vehicle

Roads are vital components of infrastructure, the extraction of which has become a topic of significant interest in the field of remote sensing. Because deep learning has been a popular method in image processing and information extraction, researchers have paid more attention to extracting road using neural networks. This article proposes the improvement of neural networks to extract roads from Unmanned Aerial Vehicle (UAV) remote sensing images. D-Linknet was first considered for its high performance; however, the huge scale of the net reduced computational efficiency. With a focus on the low computational efficiency problem of the popular D-LinkNet, this article made some improvements: (1) Replace the initial block with a stem block. (2) Rebuild the entire network based on ResNet units with a new structure, allowing for the construction of an improved neural network D-Linknetplus. (3) Add a 1 × 1 convolution layer before DBlock to reduce the input feature maps, reducing parameters and improving computational efficiency. Add another 1 × 1 convolution layer after DBlock to recover the required number of output channels. Accordingly, another improved neural network B-D-LinknetPlus was built. Comparisons were performed between the neural nets, and the verification were made with the Massachusetts Roads Dataset. The results show improved neural networks are helpful in reducing the network size and developing the precision needed for road extraction.

Sign in / Sign up

Export Citation Format

Share Document