activity
20182025
most citedLearning Sequence Descriptor based on Spatio-Temporal Attention for Visual Place Recognition

12 citations · 35 across the 26 of their papers we have counts for

collaborators
Showing 2018Show all

6 papers · 1 filter

cs.CV2018

Vision-based Semantic Mapping and Localization for Autonomous Indoor Parking

Yewei Huang, Junqiao Zhao, Xudong He +2

In this paper, we proposed a novel and practical solution for the real-time indoor localization of autonomous driving in parking lots. High-level landmarks, the parking slots, are…

cs.CV2018★ 1 cited

DLO: Direct LiDAR Odometry for 2.5D Outdoor Environment

Lu Sun, Junqiao Zhao, Xudong He +1

For autonomous vehicles, high-precision real-time localization is the guarantee of stable driving. Compared with the visual odometry (VO), the LiDAR odometry (LO) has the advantage…

cs.CV2018★ 1 cited

VH-HFCN based Parking Slot and Lane Markings Segmentation on Panoramic Surround View

Yan Wu, Tao Yang, Junqiao Zhao +2

The automatic parking is being massively developed by car manufacturers and providers. Until now, there are two problems with the automatic parking. First, there is no openly-avail…

cs.RO2018★ 1 cited

TiEV: The Tongji Intelligent Electric Vehicle in the Intelligent Vehicle Future Challenge of China

Junqiao Zhao, Chen Ye, Yan Wu +16

TiEV is an autonomous driving platform implemented by Tongji University of China. The vehicle is drive-by-wire and is fully powered by electricity. We devised the software system o…

cs.RO2018

Automatic Vector-based Road Structure Mapping Using Multi-beam LiDAR

Xudong He, Junqiao Zhao, Lu Sun +4

In this paper, we studied a SLAM method for vector-based road structure mapping using multi-beam LiDAR. We propose to use the polyline as the primary mapping element instead of gri…

cs.CV2018★ 1 cited

Semantic Segmentation via Highly Fused Convolutional Network with Multiple Soft Cost Functions

Tao Yang, Yan Wu, Junqiao Zhao +1

Semantic image segmentation is one of the most challenged tasks in computer vision. In this paper, we propose a highly fused convolutional network, which consists of three parts: f…