Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Andi Zang

Lane Boundary Geometry Extraction from Satellite Imagery

Feb 06, 2020
Andi Zang, Runsheng Xu, Zichen Li, David Doria

Figure 1 for Lane Boundary Geometry Extraction from Satellite Imagery

Figure 2 for Lane Boundary Geometry Extraction from Satellite Imagery

Figure 3 for Lane Boundary Geometry Extraction from Satellite Imagery

Figure 4 for Lane Boundary Geometry Extraction from Satellite Imagery

Autonomous driving car is becoming more of a reality, as a key component,high-definition(HD) maps shows its value in both market place and industry. Even though HD maps generation from LiDAR or stereo/perspective imagery has achieved impressive success, its inherent defects cannot be ignored. In this paper, we proposal a novel method for Highway HD maps modeling using pixel-wise segmentation on satellite imagery and formalized hypotheses linking, which is cheaper and faster than current HD maps modeling approaches from LiDAR point cloud and perspective view imagery, and let it becomes an ideal complementary of state of the art. We also manual code/label an HD road model dataset as ground truth, aligned with Bing tile image server, to train, test and evaluate our methodology. This dataset will be publish at same time to contribute research in HD maps modeling from aerial imagery.

* In Proceedings of the 1st ACM SIGSPATIAL Workshop on High-Precision Maps and Intelligent Applications for Autonomous Vehicles, page 1. ACM, 2017

Via

Access Paper or Ask Questions

Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder

Mar 11, 2015
Xi Zhang, Yanwei Fu, Andi Zang, Leonid Sigal, Gady Agam

Figure 1 for Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder

Figure 2 for Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder

Figure 3 for Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder

Figure 4 for Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder

We propose a method for using synthetic data to help learning classifiers. Synthetic data, even is generated based on real data, normally results in a shift from the distribution of real data in feature space. To bridge the gap between the real and synthetic data, and jointly learn from synthetic and real data, this paper proposes a Multichannel Autoencoder(MCAE). We show that by suing MCAE, it is possible to learn a better feature representation for classification. To evaluate the proposed approach, we conduct experiments on two types of datasets. Experimental results on two datasets validate the efficiency of our MCAE model and our methodology of generating synthetic data.

* 10 pages

Via

Access Paper or Ask Questions