Efficient Road Detection and Tracking for Unmanned Aerial Vehicle

Zhou, Hongyuan; Kong, Hui; Wei, Lei; Creighton, Douglas; Nahavandi, Saeid

doi:10.1109/tits.2014.2331353

Cited by 204 publications

(76 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although there exist some approaches to road detection from an aerial viewpoint, they are based on classical methods such as snakes (Laptev et al, 2000), histogram based thresholding and lines detection using the Hough transform (Lin and Saripalli, 2012) or homography-alignment-based tracking and graph cuts detection (Zhou et al, 2015). The main contributions of this paper are to extend the current approaches of road segmentation to aerial imagery using convolutional neural networks and to provide a database to do so, as well as a tool for automatically labeling a video sequence using only the manual segmentation of the first frame.…”

Section: State Of the Artmentioning

confidence: 99%

Spatio-temporal Road Detection from Aerial Imagery using CNNs

Luque¹,

Rubió²,

Ruiz-Hidalgo³

2017

Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

Abstract:The main goal of this paper is to detect roads from aerial imagery recorded by drones. To achieve this, we propose a modification of SegNet, a deep fully convolutional neural network for image segmentation. In order to train this neural network, we have put together a database containing videos of roads from the point of view of a small commercial drone. Additionally, we have developed an image annotation tool based on the watershed technique, in order to perform a semi-automatic labeling of the videos in this database. The experimental results using our modified version of SegNet show a big improvement on the performance of the neural network when using aerial imagery, obtaining over 90% accuracy.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Spatio-temporal Road Detection from Aerial Imagery using CNNs

Luque¹,

Rubió²,

Ruiz-Hidalgo³

2017

Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

show abstract

“…Hailing Zhou et al [24] presented proficient road detection and tracking framework in UAV videos. This road detection and tracking was done by two approaches they are graph-cut-baseddetection and homography-based road tracking.…”

Section: Recent Related Researches: a Reviewmentioning

confidence: 99%

An Innovative Moving Object Detection and Tracking System by Using Modified Region Growing Algorithm

Sujatha¹,

Kumari²

2016

SIPIJ

View full text Add to dashboard Cite

show abstract

“…Currently unmanned aerial vehicles are widely used in many areas, particularly in transport. Principal uses encompass the supervision of safety, monitoring of the strain of movement, monitoring of construction of roads and of connected research with the course of communication nets [2]. Unmanned aerial vehicles are usually equipped with single-frequency GPS receivers.…”

Section: Introductionmentioning

confidence: 99%

“…In the course of the conducted research [2], it was observed that the matching and segmentation of an object DOI: 10.22616/ERDev2018.17.N199 is one of the main issues, when it comes to tracking objects in video sequences. In other studies, an object tracking algorithm based on subtraction of the image background and image adjustment using a critical point filter (multiresolution) has been proposed.…”

Section: Introductionmentioning

confidence: 99%

Application of unmanned aerial vehicles in monitoring of communication routes on country areas

Wierzbicki

2018

Engineering for Rural Development

View full text Add to dashboard Cite

Abstract. Along with intensive development of automotive transport there is a real need of assurance of monitoring for the purpose of the improvement of safety of traffic and to increase the flow of traffic, particularly in the case of large routes. Applying unmanned aerial vehicles (UAVs) equipped with compact digital cameras is an outstanding solution. Currently UAVs are widely used in many areas, particularly in transport. Principal uses encompass the supervision of safety, monitoring of the strain of movement, monitoring of construction of roads and of connected research with the course of communication nets. Selected aspects of applying UAV equipped with compact digital camera for the monitoring traffic flow routes are described in the article. Imagery data were obtained with the fixed-wing Trimble UX-5 platform, which was equipped with the compact digital camera. Analysis of the usefulness of images for the monitoring of the traffic intensity was performed on the selected traffic routes. Detection of vehicles on the video was based on the method of Haar Feature-based Cascade Classifier from the OpenCV collection of a library. The training of the classifier consisted in preparing several dozen different samples containing cars and trucks. After the operation of training the classifier analyzing the chosen sequences of images was possible. The effectiveness of the detection of vehicles at the images deprived of the smear equals 64 %. It is a satisfying result. Considering the fact that images were not made in the nadir they were only obliques. In addition, wooded and urban areas were registered on the images besides the road and vehicles. For that reason the classifier in many cases recognized the crowns of trees as individual vehicles.Research methods applied at the work can be used and tested for the detection of vehicles on roads, like motorways or dual carriageways.

show abstract

Efficient Road Detection and Tracking for Unmanned Aerial Vehicle

Cited by 204 publications

References 32 publications

Spatio-temporal Road Detection from Aerial Imagery using CNNs

Spatio-temporal Road Detection from Aerial Imagery using CNNs

An Innovative Moving Object Detection and Tracking System by Using Modified Region Growing Algorithm

Application of unmanned aerial vehicles in monitoring of communication routes on country areas

Contact Info

Product

Resources

About