id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
brj-22232	Li, Zeqing; Zhang, Xiaowei; Li, Haibin; Wang, Zepeng; Wen, Jian	Training Data Augmentations for Improving Hyperbola Recognition in Ground Penetrating Radar B-Scan Image for Tree Roots Detection	2022	21	.pdf	application/pdf	7845	404	57	Zhang et al. (2021) used the Faster R-CNN to train 1442 GPR B-scan images (282 for real images and 1160 for simulation images) to achieve automatic recognition and localization of hyperbolas in GPR images. Dataset Construction The composition of GPR image dataset consisted of four parts: acquisition of real data, simulated data generation, enhanced data generation, and data combination.	cache/brj-22232.pdf	txt/brj-22232.txt