Vehicle detection and masking in UAV images using YOLO to improve photogrammetric products

Abstract

Photogrammetric products obtained by processing data acquired with Unmanned Aerial Vehicles (UAVs) are used in many fields. Various structures are analysed, including roads. Many roads located in cities are characterised by heavy traffic. This makes it impossible to avoid the presence of cars in aerial photographs. However, they are not an integral part of the landscape, so their presence in the generated photogrammetric products is unnecessary. The occurrence of cars in the images may also lead to errors such as irregularities in digital elevation models (DEMs) in roadway areas and the blurring effect on orthophotomaps. The research aimed to improve the quality of photogrammetric products obtained with the Structure from Motion algorithm. To fulfil this objective, the Yolo v3 algorithm was used to automatically detect cars in the images. Neural network learning was performed using data from a different flight to ensure that the obtained detector could also be used in independent projects. The photogrammetric process was then carried out in two scenarios: with and without masks. The obtained results show that the automatic masking of cars in images is fast and allows for a significant increase in the quality of photogrammetric products such as DEMs and orthophotomaps.

A New Method for Lightweight Extracting Traffic Parameters from Drone Videos and Experimental Verification

“…With the rapid development of deep learning technology in recent years, in terms of vehicle target detection, researchers have proposed a variety of improved target detection neural networks for different scenarios and tasks. Among them [4][5][6], the yolo series of single-stage multi-target detection algorithms is widely used due to its obvious advantages. Makarov et al [7] used the yolo V2 network to realize the recognition of cars, large vehicles and other objects from the UAV perspective.…”