Abstract
Target detection and tracking can be widely used in military and civilian scenarios. Unmanned aerial vehicles (UAVs) have high maneuverability and strong concealment, thus they are very suitable for using as a platform for ground target detection and tracking. Most of the existing target detection and tracking algorithms are aimed at conventional targets. Because of the small scale and the incomplete details of the targets in the aerial image, it is difficult to apply the conventional algorithms to aerial photography from UAVs. This paper proposes a ground target image detection and tracking algorithm applied to UAVs using a revised deep learning technology. Aiming at the characteristics of ground targets in aerial images, target detection algorithms and target tracking algorithms are improved. The target detection algorithm is improved to detect small targets on the ground. The target tracking algorithm is designed to recover the target after the target is lost. The target detection and tracking algorithm is verified on the aerial dataset.
Highlights
Detection and Tracking for AerialIn recent years, Unmanned aerial vehicles (UAVs) have been widely used in military reconnaissance, agricultural planting, forest patrol and other fields
Faster Region CNN (R-CNN) [1] and YOLOv3 [2] are used as target detection algorithms respectively, and their convolutional layer is used as the deep features of the target tracking module
We use the convolution features extracted by target detection algorithm for the target tracking process
Summary
UAVs have been widely used in military reconnaissance, agricultural planting, forest patrol and other fields. The region occupied by the target has a small overall length and is occluded by the environment This puts forward higher requirements for the target detection and tracking process. Aiming at the small target in aerial images, we use the convolution feature to obtain better feature expression ability. This paper proposes a real-time detection-tracking framework for tracking a predetermined target in an aerial real-time picture or video sequence. Faster R-CNN [1] and YOLOv3 [2] are used as target detection algorithms respectively, and their convolutional layer is used as the deep features of the target tracking module. We use the convolution features extracted by target detection algorithm for the target tracking process. The feature map with low resolution extracted from a deep convolution layer expresses stronger sematic information. This criterion can be used to determine whether the tracking process has failed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
