Open AccessAn experimental study of vehicle detection on aerial imagery using deep learning-based detection approaches
Author(s) -
Xiaofeng Liao,
Shahnorbanun Sahran,
Syaimak Abdul Shukor
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1550/3/032005
Subject(s) - artificial intelligence , computer science , benchmark (surveying) , deep learning , aerial imagery , convolutional neural network , object detection , metric (unit) , aerial image , computer vision , pattern recognition (psychology) , machine learning , image (mathematics) , cartography , engineering , geography , operations management
Deep convolutional neural network technology is widely used to deal with general object detection in computer vision, and it achieved remarkable progress. Unmanned aerial vehicles provide large numbers of aerial imagery that significantly facilitate several applications including traffic monitoring, surveillance, tracking, rescue, and safe military tasks. This paper presents an experimental study to evaluate the performances of several state-of-the-art deep learning-based detection approaches on vehicle detection from aerial imagery. The pre-trained models, including Faster R-CNN, R-FCN, and SSD, are adopted from the TensorFlow model zoo, and the VEDAI dataset is used as the benchmark. The results show that Faster R-CNN combined with Resnet101 backbone achieved the highest mAP, which is 39.73% on the COCO metric. This experimental study expects to be a guideline to choose suitable approaches for particular applications.