WAY TO TRAIN DEEP LEARNING NEURAL MODEL USING IMAGES AND DATA FROM POINT CLOUDS AT SAME TIME
	SHARAFUTDINOV D R; PROTASOV S K; KUSKOV S A; SADOVSKOV K V
	2023-09-26
专利权人	EVOCARGO LLC (EVOC-Non-standard)
申请日期	2023-09-26
专利号	RU2832583-C1
成果简介	NOVELTY - Invention relates to the field of machine learning, in particular to image analysis using neural networks. The technical result is to reduce the cost of marking data and improve the accuracy of predicting the surface of the roadway with a neural network model, which will lead to an increase in the accuracy of automatic motion control systems for highly automated wheeled vehicles. The method includes: collecting data in the form of images obtained using cameras and clouds of points obtained using lidars, while manually annotating the clouds of points to highlight the road surface, after which the clouds of points are projected onto camera images using calibration data, then random noise is added in the areas in the image, If the projected points are not covered, the result is a mask that is used as the true position of the road surface in the image, which is necessary to calculate the loss function when training a model where the loss function is a masked version of the cross entropy. USE - Machine learning. ADVANTAGE - Technical result is to reduce the cost of marking data and improve the accuracy of predicting the surface of the roadway with a neural network model, which will lead to an increase in the accuracy of automatic motion control systems for highly automated wheeled vehicles. 1 cl, 6 dwg
IPC 分类号	G01C-021/30 ; G06V-020/58
国家	俄罗斯
专业领域	信息技术
语种	英语
成果类型	专利
文献类型	科技成果
条目标识符	http://119.78.100.226:8889/handle/3KE4DYBR/20226
专题	中国科学院新疆生态与地理研究所
作者单位	EVOCARGO LLC (EVOC-Non-standard)
推荐引用方式 GB/T 7714	SHARAFUTDINOV D R,PROTASOV S K,KUSKOV S A,et al. WAY TO TRAIN DEEP LEARNING NEURAL MODEL USING IMAGES AND DATA FROM POINT CLOUDS AT SAME TIME. RU2832583-C1[P]. 2023.

条目包含的文件
条目无相关文件。

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。