Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle
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 so...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/5/965 |
| _version_ | 1797414459984052224 |
|---|---|
| author | Marek Kraft Mateusz Piechocki Bartosz Ptak Krzysztof Walas |
| author_facet | Marek Kraft Mateusz Piechocki Bartosz Ptak Krzysztof Walas |
| author_sort | Marek Kraft |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T05:33:20Z |
| format | Article |
| id | doaj.art-84d38d75156643f0a0292ced69366edc |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:33:20Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-84d38d75156643f0a0292ced69366edc2023-12-03T12:30:55ZengMDPI AGRemote Sensing2072-42922021-03-0113596510.3390/rs13050965Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial VehicleMarek Kraft0Mateusz Piechocki1Bartosz Ptak2Krzysztof Walas3Faculty of Control, Robotics and Electrical, Engineering, Institute of Robotics and Machine Intelligence, Poznań University of Technology, 60-965 Poznań, PolandFaculty of Control, Robotics and Electrical, Engineering, Institute of Robotics and Machine Intelligence, Poznań University of Technology, 60-965 Poznań, PolandFaculty of Control, Robotics and Electrical, Engineering, Institute of Robotics and Machine Intelligence, Poznań University of Technology, 60-965 Poznań, PolandFaculty of Control, Robotics and Electrical, Engineering, Institute of Robotics and Machine Intelligence, Poznań University of Technology, 60-965 Poznań, PolandPublic 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.https://www.mdpi.com/2072-4292/13/5/965deep learningobject detectionimage processingtrashlitterUAV |
| spellingShingle | Marek Kraft Mateusz Piechocki Bartosz Ptak Krzysztof Walas Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle Remote Sensing deep learning object detection image processing trash litter UAV |
| title | Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle |
| title_full | Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle |
| title_fullStr | Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle |
| title_full_unstemmed | Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle |
| title_short | Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle |
| title_sort | autonomous onboard vision based trash and litter detection in low altitude aerial images collected by an unmanned aerial vehicle |
| topic | deep learning object detection image processing trash litter UAV |
| url | https://www.mdpi.com/2072-4292/13/5/965 |
| work_keys_str_mv | AT marekkraft autonomousonboardvisionbasedtrashandlitterdetectioninlowaltitudeaerialimagescollectedbyanunmannedaerialvehicle AT mateuszpiechocki autonomousonboardvisionbasedtrashandlitterdetectioninlowaltitudeaerialimagescollectedbyanunmannedaerialvehicle AT bartoszptak autonomousonboardvisionbasedtrashandlitterdetectioninlowaltitudeaerialimagescollectedbyanunmannedaerialvehicle AT krzysztofwalas autonomousonboardvisionbasedtrashandlitterdetectioninlowaltitudeaerialimagescollectedbyanunmannedaerialvehicle |