Title: Using images rendered by PBRT to train faster R-CNN for UAV detection
Authors: Peng, Junkai
Zheng, Changwen
Lv, Pin
Cui, Tianyu
Cheng, Ye
Lingyu, Si
Citation: WSCG '2018: short communications proceedings: The 26th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2016 in co-operation with EUROGRAPHICS: University of West Bohemia, Plzen, Czech Republic May 28 - June 1 2018, p. 13-18.
Issue Date: 2018
Publisher: Václav Skala - UNION Agency
Document type: konferenční příspěvek
URI: wscg.zcu.cz/WSCG2018/!!_CSRN-2802.pdf
ISBN: 978-80-86943-41-1
ISSN: 2464-4617
Keywords: detekce objektů;hluboké učení;Faster R-CNN;PBRT;UAV
Keywords in different language: object detection;deep learning;faster R-CNN;PBRT;UAV
Abstract: Deep neural networks, such as Faster R-CNN, have been widely used in object detection. However, deep neural networks usually require a large-scale dataset to achieve desirable performance. For the specific application, UAV detection, training data is extremely limited in practice. Since annotating plenty of UAV images manually can be very resource intensive and time consuming, instead, we use PBRT to render a large number of photorealistic UAV images of high variation within a reasonable time. Using PBRT ensures the realism of rendered images, which means they are indistinguishable from real photographs to some extent. Trained with our rendered images, the Faster R-CNN has an AP of 80.69% on manually annotated UAV images test set, much higher than the one only trained with COCO 2014 dataset and PASCAL VOC 2012 dataset (43.36%). Moreover, our rendered image dataset contains not only bounding boxes of all UAVs, but also locations of some important parts of UAVs and locations of all pixels covered by UAVs, which can be used for more complicated application, such as mask detection or keypoint detection.
Rights: © Václav Skala - UNION Agency
Appears in Collections:WSCG '2018: Short Papers Proceedings

Files in This Item:
File Description SizeFormat 
Peng.pdfPlný text10,4 MBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/34647

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.