A review of road extraction from remote sensing images

Wang, Weixing; Yang, Nan; Zhang, Yi; Wang, Fengping; Cao, Ting; Eklund, Patrik

doi:10.1016/j.jtte.2016.05.005

Cited by 230 publications

(164 citation statements)

References 22 publications

Supporting

Mentioning

160

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, they did not use a learning feature approach to detect lane markings as we have done in this work. More complete overviews about the extraction of roads and road features from airborne images can be found in Mayer et al [38] and Wang et al [50]. As discussed, no previous work has tried to learn the features of the lane marking through an end-to-end feature learning mechanism e.g., deep learning methods, to the best of knowledge of these authors.…”

Section: B Related Workmentioning

confidence: 99%

Aerial LaneNet: Lane-Marking Semantic Segmentation in Aerial Imagery Using Wavelet-Enhanced Cost-Sensitive Symmetric Fully Convolutional Neural Networks

Azimi

Fischer

Körner

et al. 2019

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

The knowledge about the placement and appearance of lane markings is a prerequisite for the creation of maps with high precision, necessary for autonomous driving, infrastructure monitoring, lane-wise traffic management, and urban planning. Lane markings are one of the important components of such maps. Lane markings convey the rules of roads to drivers. While these rules are learned by humans, an autonomous driving vehicle should be taught to learn them to localize itself. Therefore, accurate and reliable lane marking semantic segmentation in the imagery of roads and highways is needed to achieve such goals. We use airborne imagery which can capture a large area in a short period of time by introducing an aerial lane marking dataset. In this work, we propose a Symmetric Fully Convolutional Neural Network enhanced by Wavelet Transform in order to automatically carry out lane marking segmentation in aerial imagery. Due to a heavily unbalanced problem in terms of number of lane marking pixels compared with background pixels, we use a customized loss function as well as a new type of data augmentation step. We achieve a high accuracy in pixelwise localization of lane markings compared with the state-ofthe-art methods without using 3rd-party information. In this work, we introduce the first high-quality dataset used within our experiments which contains a broad range of situations and classes of lane markings representative of today's transportation systems. This dataset will be publicly available and hence, it can be used as the benchmark dataset for future algorithms within this domain.

show abstract

Section: B Related Workmentioning

confidence: 99%

Aerial LaneNet: Lane-Marking Semantic Segmentation in Aerial Imagery Using Wavelet-Enhanced Cost-Sensitive Symmetric Fully Convolutional Neural Networks

Azimi

Fischer

Körner

et al. 2019

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The encoder of low level features encodes multi-scale contextual information from the initial 2-band lidar images by a DDCM module with 6 different dilation rates [1,2,3,5,7,9]. The decoder of high level features decodes highly abstract representations learned from ResNet by 2 DDCM modules with rates [1,2,3,4] and [1] separately. The transformed low-level and high-level feature maps by DDCMs are then fused together to infer pixel-wise full-class probabilities.…”

Section: B Train and Test Time Augmentationmentioning

confidence: 99%

Road Mapping in Lidar Images Using a Joint-Task Dense Dilated Convolutions Merging Network

Liu

Kampffmeyer

Jenssen

et al. 2019

IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

It is important, but challenging, for the forest industry to accurately map roads which are used for timber transport by trucks. In this work, we propose a Dense Dilated Convolutions Merging Network (DDCM-Net) to detect these roads in lidar images. The DDCM-Net can effectively recognize multi-scale and complex shaped roads with similar texture and colors, and also is shown to have superior performance over existing methods. To further improve its ability to accurately infer categories of roads, we propose the use of a joint-task learning strategy that utilizes two auxiliary output branches, i.e, multi-class classification and binary segmentation, joined with the main output of full-class segmentation. This pushes the network towards learning more robust representations that are expected to boost the ultimate performance of the main task. In addition, we introduce an iterative-random-weighting method to automatically weigh the joint losses for auxiliary tasks. This can avoid the difficult and expensive process of tuning the weights of each task's loss by hand. The experiments demonstrate that our proposed jointtask DDCM-Net can achieve better performance with fewer parameters and higher computational efficiency than previous state-of-the-art approaches.

show abstract

“…Remote sensing images have the unique advantages of providing large scale information, which is very suitable for analyzing road networks efficiently [1,2]. Accurate road information, from high spatial-resolution images, has become urgently required in recent years.…”

Section: Introductionmentioning

confidence: 99%

Road Extraction from High Resolution Image with Deep Convolution Network—A Case Study of GF-2 Image

Wei

Zhang

Liu

et al. 2018

The 2nd International Electronic Conference on Remote Sensing

View full text Add to dashboard Cite

Recently, with the development of remote sensing and computer techniques, automatic and accurate road extraction is becoming feasible for practical usage. Nowadays, accurate extraction of road information from satellite data has become one of the most popular topics in both remote sensing and transportation fields. It is very useful for applying this technique to fast map updating, construction supervision, and so on. However, as there is usually a huge volume of information provided by remote sensing data, an efficient method to refine the big volume of data is important in corresponding applications. We apply deep convolution network to perform an image segmentation approach, as a solution for extracting road networks from high resolution images. In order to take advantage of deep learning, we study the methods of generating representative training and testing datasets, and develop semi-supervised leaning skills to enhance the data scale. The extraction of the satellite images that are affected by color distortion is also studied, in order to make the method more robust for more applicational fields. The GF-2 satellite data is used for experiments, as its images may show optical distortion in small pieces. Experiments in this paper showed that, the proposed solution successfully identifies road networks from complex situations with a total accuracy of more than 80% in discriminable areas.

show abstract

A review of road extraction from remote sensing images

Cited by 230 publications

References 22 publications

Aerial LaneNet: Lane-Marking Semantic Segmentation in Aerial Imagery Using Wavelet-Enhanced Cost-Sensitive Symmetric Fully Convolutional Neural Networks

Aerial LaneNet: Lane-Marking Semantic Segmentation in Aerial Imagery Using Wavelet-Enhanced Cost-Sensitive Symmetric Fully Convolutional Neural Networks

Road Mapping in Lidar Images Using a Joint-Task Dense Dilated Convolutions Merging Network

Road Extraction from High Resolution Image with Deep Convolution Network—A Case Study of GF-2 Image

Contact Info

Product

Resources

About