Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models
Unmanned aerial vehicle (UAV) detection in real-time is a challenging task despite the advances in computer vision and deep learning techniques. The increasing use of UAVs in numerous applications has generated worries about possible risks and misuse. Although vision-based UAV detection methods have...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/8/11/638 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850267498045243392 |
|---|---|
| author | Adnan Munir Abdul Jabbar Siddiqui Saeed Anwar Aiman El-Maleh Ayaz H. Khan Aqsa Rehman |
| author_facet | Adnan Munir Abdul Jabbar Siddiqui Saeed Anwar Aiman El-Maleh Ayaz H. Khan Aqsa Rehman |
| author_sort | Adnan Munir |
| collection | DOAJ |
| description | Unmanned aerial vehicle (UAV) detection in real-time is a challenging task despite the advances in computer vision and deep learning techniques. The increasing use of UAVs in numerous applications has generated worries about possible risks and misuse. Although vision-based UAV detection methods have been proposed in recent years, a standing open challenge and overlooked issue is that of adverse weather. This work is the first, to the best of our knowledge, to investigate the impact of adverse weather conditions and image distortions on vision-based UAV detection methods. To achieve this, a custom training dataset was curated with images containing a variety of UAVs in diverse complex backgrounds. In addition, this work develops a first-of-its-kind dataset, to the best of our knowledge, with UAV-containing images affected by adverse conditions. Based on the proposed datasets, a comprehensive benchmarking study is conducted to evaluate the impact of adverse weather and image distortions on the performance of popular object detection methods such as YOLOv5, YOLOv8, Faster-RCNN, RetinaNet, and YOLO-NAS. The experimental results reveal the weaknesses of the studied models and the performance degradation due to adverse weather, highlighting avenues for future improvement. The results show that even the best UAV detection model’s performance degrades in mean average precision (mAP) by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>−</mo><mn>50.62</mn></mrow></semantics></math></inline-formula> points in torrential rain conditions, by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>−</mo><mn>52.40</mn></mrow></semantics></math></inline-formula> points in high noise conditions, and by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>−</mo><mn>77.0</mn></mrow></semantics></math></inline-formula> points in high motion blur conditions. To increase the selected models’ resilience, we propose and evaluate a strategy to enhance the training of the selected models by introducing weather effects in the training images. For example, the YOLOv5 model with the proposed enhancement strategy gained <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>+</mo><mn>35.4</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>+</mo><mn>39.3</mn></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>+</mo><mn>44.9</mn></mrow></semantics></math></inline-formula> points higher mAP in severe rain, noise, and motion blur conditions respectively. The findings presented in this work highlight the advantages of considering adverse weather conditions during model training and underscore the significance of data enrichment for improving model generalization. The work also accentuates the need for further research into advanced techniques and architectures to ensure more reliable UAV detection under extreme weather conditions and image distortions. |
| format | Article |
| id | doaj-art-2e3047013e8446fe9c0a469189fc77db |
| institution | OA Journals |
| issn | 2504-446X |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-2e3047013e8446fe9c0a469189fc77db2025-08-20T01:53:45ZengMDPI AGDrones2504-446X2024-11-0181163810.3390/drones8110638Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning ModelsAdnan Munir0Abdul Jabbar Siddiqui1Saeed Anwar2Aiman El-Maleh3Ayaz H. Khan4Aqsa Rehman5Computer Engineering Department, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi ArabiaComputer Engineering Department, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi ArabiaSDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi ArabiaComputer Engineering Department, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi ArabiaComputer Engineering Department, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi ArabiaComputer Engineering Department, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi ArabiaUnmanned aerial vehicle (UAV) detection in real-time is a challenging task despite the advances in computer vision and deep learning techniques. The increasing use of UAVs in numerous applications has generated worries about possible risks and misuse. Although vision-based UAV detection methods have been proposed in recent years, a standing open challenge and overlooked issue is that of adverse weather. This work is the first, to the best of our knowledge, to investigate the impact of adverse weather conditions and image distortions on vision-based UAV detection methods. To achieve this, a custom training dataset was curated with images containing a variety of UAVs in diverse complex backgrounds. In addition, this work develops a first-of-its-kind dataset, to the best of our knowledge, with UAV-containing images affected by adverse conditions. Based on the proposed datasets, a comprehensive benchmarking study is conducted to evaluate the impact of adverse weather and image distortions on the performance of popular object detection methods such as YOLOv5, YOLOv8, Faster-RCNN, RetinaNet, and YOLO-NAS. The experimental results reveal the weaknesses of the studied models and the performance degradation due to adverse weather, highlighting avenues for future improvement. The results show that even the best UAV detection model’s performance degrades in mean average precision (mAP) by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>−</mo><mn>50.62</mn></mrow></semantics></math></inline-formula> points in torrential rain conditions, by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>−</mo><mn>52.40</mn></mrow></semantics></math></inline-formula> points in high noise conditions, and by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>−</mo><mn>77.0</mn></mrow></semantics></math></inline-formula> points in high motion blur conditions. To increase the selected models’ resilience, we propose and evaluate a strategy to enhance the training of the selected models by introducing weather effects in the training images. For example, the YOLOv5 model with the proposed enhancement strategy gained <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>+</mo><mn>35.4</mn></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>+</mo><mn>39.3</mn></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>+</mo><mn>44.9</mn></mrow></semantics></math></inline-formula> points higher mAP in severe rain, noise, and motion blur conditions respectively. The findings presented in this work highlight the advantages of considering adverse weather conditions during model training and underscore the significance of data enrichment for improving model generalization. The work also accentuates the need for further research into advanced techniques and architectures to ensure more reliable UAV detection under extreme weather conditions and image distortions.https://www.mdpi.com/2504-446X/8/11/638anti-droneUAV detectionadverse weather conditions |
| spellingShingle | Adnan Munir Abdul Jabbar Siddiqui Saeed Anwar Aiman El-Maleh Ayaz H. Khan Aqsa Rehman Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models Drones anti-drone UAV detection adverse weather conditions |
| title | Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models |
| title_full | Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models |
| title_fullStr | Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models |
| title_full_unstemmed | Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models |
| title_short | Impact of Adverse Weather and Image Distortions on Vision-Based UAV Detection: A Performance Evaluation of Deep Learning Models |
| title_sort | impact of adverse weather and image distortions on vision based uav detection a performance evaluation of deep learning models |
| topic | anti-drone UAV detection adverse weather conditions |
| url | https://www.mdpi.com/2504-446X/8/11/638 |
| work_keys_str_mv | AT adnanmunir impactofadverseweatherandimagedistortionsonvisionbaseduavdetectionaperformanceevaluationofdeeplearningmodels AT abduljabbarsiddiqui impactofadverseweatherandimagedistortionsonvisionbaseduavdetectionaperformanceevaluationofdeeplearningmodels AT saeedanwar impactofadverseweatherandimagedistortionsonvisionbaseduavdetectionaperformanceevaluationofdeeplearningmodels AT aimanelmaleh impactofadverseweatherandimagedistortionsonvisionbaseduavdetectionaperformanceevaluationofdeeplearningmodels AT ayazhkhan impactofadverseweatherandimagedistortionsonvisionbaseduavdetectionaperformanceevaluationofdeeplearningmodels AT aqsarehman impactofadverseweatherandimagedistortionsonvisionbaseduavdetectionaperformanceevaluationofdeeplearningmodels |