PhD Candidate

Lingfei Ma

Download CV (PDF)

Research interests

3D high-definition roadmaps promotes autonomous driving

A fully autonomous vehicle (AV), which aims to achieve the Level-4 full self-driving automation, has the capability to determine the best navigation routes, drive vehicle themselves on the most challenging road networks, and avoid collisions with other traffic participants without human interactions. AVs are increasingly developed to enhance quality and performance of modern transportation services with reduced costs and resources consumption. Moreover, in order to provide effective and precise localization services, the development of AV desiderates tremendous advances in 3D high-definition (HD) roadmaps. Such roadmaps are capable of providing 3D positioning information with cm-level accuracy. Therefore, establishing detailed and valuable 3D high-definition roadmaps has been regarded as a fundamental perspective of achieving autonomous driving.

Accordingly, mobile laser scanning (MLS) systems, consisting of advanced navigation and data acquisition devices, can be applied to acquire highly accurate, geo-referenced point clouds with highly sensitive information about road environments for the generation of 3D high-definition roadmaps.

My current research mainly focuses on autonomous driving, intelligent processing of point clouds, and 3D road scene modelling to promote the development of AVs and HD maps. In addition, combined with advanced computer vision techniques, I am looking forward that MLS technique can improve and achieve a wide application in the process of augmented reality.


  • MSc, Geography, University of Waterloo, 2017
  • BES, Geomatics, University of Waterloo, 2015
  • BSc, Geomatics, China University of Geosciences (Beijing), 2015


  • Ma L, Li Y, *Li J, Tan W, Yu Y, Chapman M, 2019. Multi-scale point-wise convolutional neural networks for 3D object segmentation from LiDAR point clouds in large-scale urban environments, IEEE Transactions on Intelligent Transportation Systems, under review.
  • Li Y, Ma L, Zhong Z, Cao D, *Li J, 2019. TGNet: Geometric Graph CNN on 3D Point Cloud Segmentation, IEEE Transactions on Geoscience and Remote Sensing, under review
  • Li Y, Ma L, Cao D, Chapman M, *Li J, 2019. Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review, IEEE Transactions on Neural Networks and Learning Systems, under review.
  • Ye C, Zhao H, Ma L, *Li J, Jiang H, Wang R, Chapman M, 2019. Curved lane extraction from MLS point clouds towards HD maps, IEEE Transactions on Intelligent Transportation Systems, under review.
  • *Yu Y, Guan H, Li D, Ma L, Li J, 2019. A hybrid capsule network for land cover classification using multispectral LiDAR data, IEEE Geoscience and Remote Sensing Letters, DOI:10.1109/LGRS.2019.2940505.
  • Chen Y, Wang S, Ma L, *Li J, Wu R, *Luo Z, Wang C, Chapman MA, 2019. Rapid urban roadside tree inventory using a mobile laser scanning system, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(9), 3690-3700.
  • Ye C, *Li J, Jiang H, Zhao H, Ma L, Chapman M, 2019. Semi-automated generation of road transition lines using mobile laser scanning data, IEEE Transactions on Intelligent Transportation Systems, doi:10.1109/TITS.2019.2904735.
  • Ma L, *Li J, Li Y, Zhong Z, Chapman M, 2019. Generation of horizontally curved driving lines in HD maps using mobile laser scanning point clouds, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, DOI:10.1109/JSTARS.2019.2904514.
  • Ma L, Wu T, Li Y, *Li J, Chen Y, Chapman M, 2019. Automated extraction of driving lines from mobile laser scanning point clouds, ICC 2019, Tokyo, Japan, 15-20 July 2019.
  • Ma L, Chen Z, Li Y, Zhang D, *Li J, Chapman M, 2019 Multispectral airborne laser scanning point-clouds for land cover classification using convolutional neural networks, ISPRS Achieve, 42(2/W13), 79-86, ISPRS Geospatial Week 2019, doi:10.5194/isprs-archives-XLII-2-W13-79-2019.
  • Ma L, Li Y, *Li J, Wang C, Wang R, Chapman MA, 2018. Mobile laser scanned point-clouds for road object detection and extraction: A review, Remote Sensing, 10(10), 1531; doi: 10.3390/rs10101531.
  • Li Y, Ma L, Huang Y, *Li J, 2018. Segment-based traffic sign detection from mobile laser scanning data, IGARSS 2018, July 23–27, Valencia, Spain, pp. 4611-4614.
  • Zhou M, Ma L, Li Y, *Li J, 2018. Extraction of building windows from mobile laser scanning point clouds, IGARSS 2018, July 23–27, Valencia, Spain, pp. 4308-4311.
  • Zhong Z, *Li J, Ma L, Jiang H, Zhao H, 2017. Deep residual networks for hyperspectral image classification, IGARSS 2017, Fort Worth, Taxes, USA, 23-28 July, pp. 1824-1827.
  • Ma L, Zhao H, *Li J, 2016. Examining urban expansion using multi-temporal Landsat imagery: a case study of the Montreal Census Metropolitan area from 1975 to 2015, Canada. ISPRS 2016, Prague, Czech Republic, pp. 965-972.
University of Waterloo