TY - GEN
T1 - Multi-scale Aerial Object Detection Using Feature Pyramid Networks
AU - Johnson, Dennis George
AU - Bhat, Nandan
AU - Akshatha, K. R.
AU - Karunakar, A. K.
AU - Satish Shenoy, B.
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2023
Y1 - 2023
N2 - Aerial object detection on an UAV or embedded vision platform requires accurate detection of objects with various spatial scales and has numerous applications in surveillance, traffic monitoring, search, and rescue, etc. The task of small-object detection becomes harder while using standard convolutional neural network architectures due to the reduction in spatial resolution. This work evaluates the effectiveness of using feature pyramid hierarchies with the Faster R-CNN algorithm for aerial object detection. The VisDrone aerial object detection dataset with ten object classes has been utilized to develop a Faster R-CNN ResNet model with C4 and FPN architectures to compare the performance. Significant improvement in the performance obtained by using feature pyramid networks for all object categories highlights their importance in the multi-scale aerial object detection task.
AB - Aerial object detection on an UAV or embedded vision platform requires accurate detection of objects with various spatial scales and has numerous applications in surveillance, traffic monitoring, search, and rescue, etc. The task of small-object detection becomes harder while using standard convolutional neural network architectures due to the reduction in spatial resolution. This work evaluates the effectiveness of using feature pyramid hierarchies with the Faster R-CNN algorithm for aerial object detection. The VisDrone aerial object detection dataset with ten object classes has been utilized to develop a Faster R-CNN ResNet model with C4 and FPN architectures to compare the performance. Significant improvement in the performance obtained by using feature pyramid networks for all object categories highlights their importance in the multi-scale aerial object detection task.
UR - http://www.scopus.com/inward/record.url?scp=85134317464&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85134317464&partnerID=8YFLogxK
U2 - 10.1007/978-981-19-0095-2_31
DO - 10.1007/978-981-19-0095-2_31
M3 - Conference contribution
AN - SCOPUS:85134317464
SN - 9789811900945
T3 - Lecture Notes in Networks and Systems
SP - 303
EP - 313
BT - Information and Communication Technology for Competitive Strategies, ICTCS 2021- ICT
A2 - Joshi, Amit
A2 - Mahmud, Mufti
A2 - Ragel, Roshan G.
PB - Springer Science and Business Media Deutschland GmbH
T2 - 6th International Conference on Information and Communication Technology for Competitive Strategies, ICTCS 2021
Y2 - 17 December 2021 through 18 December 2021
ER -