Abstract
Unmanned air vehicles (UAVs) popularity is on the rise as it enables the
services like traffic monitoring, emergency communications, deliveries,
and surveillance. However, the unauthorized usage of UAVs (a.k.a drone)
may violate security and privacy protocols for security-sensitive
national and international institutions. The presented challenges
require fast, efficient, and precise detection of UAVs irrespective of
harsh weather conditions, the presence of different objects, and their
size to enable SafeSpace. Recently, there has been significant progress
in using the latest deep learning models, but those models have
shortcomings in terms of computational complexity, precision, and
non-scalability. To overcome these limitations, we propose a precise and
efficient multiscale and multifeature UAV detection network for
SafeSpace, i.e., \textit{MultiFeatureNet}
(\textit{MFNet}), an improved version of the popular
object detection algorithm YOLOv5s. In \textit{MFNet},
we perform multiple changes in the backbone and neck of the YOLOv5s
network to focus on the various small and ignored features required for
accurate and fast UAV detection. To further improve the accuracy and
focus on the specific situation and multiscale UAVs, we classify the
\textit{MFNet} into small (S), medium (M), and large
(L): these are the combinations of various size filters in the
convolution and the bottleneckCSP layers, reside in the backbone and
neck of the architecture. This classification helps to overcome the
computational cost by training the model on a specific feature map
rather than all the features. The results show significant performance
gain even for unseen feature maps with minimal loss in accuracy. Results
show a significant reduction in training parameters, inference, and
increased pattern in FPS and GFLOPs for \textit{MFNet}
compared to YOLOv5s. \textit{MFNet-M} performance
evaluation in terms of precision, recall, mean average-precision (mAP),
and IOU increased around 1.8\%, 2.2\%,
0.9\%, 1.7\% compared to YOLOv5s.
Furthermore, \textit{MFNet-M} achieves the best
performance with 96.8\% precision,
88.4\% recall, 95.9\% mAP, and
51.1\% IoU for UAV detection. The dataset and code are
available as an open source: github.com/ZeeshanKaleem/MultiFeatureNet.