Unstructured Road Segmentation Based on Road Boundary Enhancement Point-Cylinder Network Using LiDAR Sensor

The segmentation of unstructured roads, a key technology in self-driving technology, remains a challenging problem. At present, most unstructured road segmentation algorithms are based on cameras or use LiDAR for projection, which has considerable limitations that the camera will fail at night, and the projection method will lose one-dimensional information. Therefore, this paper proposes a road boundary enhancement Point-Cylinder Network, called BE-PCFCN, which uses Point-Cylinder in order to extract point cloud features directly and integrates the road enhancement module to achieve accurate unstructured road segmentation. Firstly, we use the improved RANSAC-Boundary algorithm to calculate the rough road boundary point set, training in the same parameters with the original point cloud as a submodule. The whole network adopts the encoder and decoder structure, using Point-Cylinder as the basic module, while considering the data locality and the algorithm complexity. Subsequently, we made an unstructured road data set for training and compared it with existing LiDAR(Light Detection And Ranging) semantic segmentation algorithms. Finally, the experiment verified the robustness of BE-PCFCN. The road intersection-over-union (IoU) was increased by 4% when compared with the best existing algorithm, reaching 95.6%. Even on unstructured roads with an extremely irregular shape, BE-PCFCN also currently has the best segmentation results.

Download Full-text

Road Segmentation using Semantic Segmentation Networks for ADAS

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.k1530.0981119 ◽

2019 ◽

Vol 8 (11) ◽

pp. 1740-1743

Keyword(s):

Autonomous Vehicles ◽

Autonomous Vehicle ◽

Warning System ◽

Semantic Segmentation ◽

Boundary Line ◽

Segmentation Result ◽

Safe Driving ◽

The Road ◽

Straight Line ◽

Road Segmentation

In this paper, we propose a method to automatically segment the road area from the input road images to support safe driving of autonomous vehicles. In the proposed method, the semantic segmentation network (SSN) is trained by using the deep learning method and the road area is segmented by utilizing the SSN. The SSN uses the weights initialized from the VGC-16 network to create the SegNet network. In order to fast the learning time and to obtain results, the class is simplified and learned so that it can be divided into two classes as the road area and the non-road area in the trained SegNet CNN network. In order to improve the accuracy of the road segmentation result, the boundary line of the road region with the straight-line component is detected through the Hough transform and the result is shown by dividing the accurate road region by combining with the segmentation result of the SSN. The proposed method can be applied to safe driving support by autonomously driving the autonomous vehicle by automatically classifying the road area during operation and applying it to the road area departure warning system

Download Full-text

Semantic Segmentation of Airborne LiDAR Data in Maya Archaeology

Remote Sensing ◽

10.3390/rs12223685 ◽

2020 ◽

Vol 12 (22) ◽

pp. 3685 ◽

Cited By ~ 1

Author(s):

Marek Bundzel ◽

Miroslav Jaščur ◽

Milan Kováč ◽

Tibor Lieskovský ◽

Peter Sinčák ◽

...

Keyword(s):

Semantic Segmentation ◽

Airborne Lidar ◽

Lidar Data ◽

Archaeological Research ◽

Ancient Maya ◽

Data Set ◽

The Road ◽

Road Map ◽

Construction Activity ◽

Airborne Lidar Data

Airborne LiDAR produced large amounts of data for archaeological research over the past decade. Labeling this type of archaeological data is a tedious process. We used a data set from Pacunam LiDAR Initiative survey of lowland Maya region in Guatemala. The data set contains ancient Maya structures that were manually labeled, and ground verified to a large extent. We have built and compared two deep learning-based models, U-Net and Mask R-CNN, for semantic segmentation. The segmentation models were used in two tasks: identification of areas of ancient construction activity, and identification of the remnants of ancient Maya buildings. The U-Net based model performed better in both tasks and was capable of correctly identifying 60–66% of all objects, and 74–81% of medium sized objects. The quality of the resulting prediction was evaluated using a variety of quantifiers. Furthermore, we discuss the problems of re-purposing the archaeological style labeling for production of valid machine learning training sets. Ultimately, we outline the value of these models for archaeological research and present the road map to produce a useful decision support system for recognition of ancient objects in LiDAR data.

Download Full-text

Review of Road Segmentation for SAR Images

Remote Sensing ◽

10.3390/rs13051011 ◽

2021 ◽

Vol 13 (5) ◽

pp. 1011

Author(s):

Zengguo Sun ◽

Hui Geng ◽

Zheng Lu ◽

Rafał Scherer ◽

Marcin Woźniak

Keyword(s):

Rapid Development ◽

Synthetic Aperture ◽

Practical Significance ◽

Future Research ◽

Sar Images ◽

The Road ◽

Advantages And Disadvantages ◽

Segmentation Methods ◽

Segmentation Algorithms ◽

Road Segmentation

Road segmentation for synthetic aperture radar (SAR) images is of great practical significance. With the rapid development and wide application of SAR imaging technology, this problem has attracted much attention. At present, there are numerous road segmentation methods. This paper analyzes and summarizes the road segmentation methods for SAR images over the years. Firstly, the traditional road segmentation algorithms are classified according to the degree of automation and the principle. Advantages and disadvantages are introduced successively for each traditional method. Then, the popular segmentation methods based on deep learning in recent years are systematically introduced. Finally, novel deep segmentation neural networks based on the capsule paradigm and the self-attention mechanism are forecasted as future research for SAR images.

Download Full-text

Panicle-3D: Efficient Phenotyping Tool for Precise Semantic Segmentation of Rice Panicle Point Cloud

Plant Phenomics ◽

10.34133/2021/9838929 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Liang Gong ◽

Xiaofeng Du ◽

Kai Zhu ◽

Ke Lin ◽

Qiaojun Lou ◽

...

Keyword(s):

Point Cloud ◽

Network Models ◽

Semantic Segmentation ◽

Spatial Location ◽

Point Clouds ◽

Utilization Efficiency ◽

Data Set ◽

Cloud Data ◽

Point Cloud Segmentation ◽

Segmentation Accuracy

The automated measurement of crop phenotypic parameters is of great significance to the quantitative study of crop growth. The segmentation and classification of crop point cloud help to realize the automation of crop phenotypic parameter measurement. At present, crop spike-shaped point cloud segmentation has problems such as fewer samples, uneven distribution of point clouds, occlusion of stem and spike, disorderly arrangement of point clouds, and lack of targeted network models. The traditional clustering method can realize the segmentation of the plant organ point cloud with relatively independent spatial location, but the accuracy is not acceptable. This paper first builds a desktop-level point cloud scanning apparatus based on a structured-light projection module to facilitate the point cloud acquisition process. Then, the rice ear point cloud was collected, and the rice ear point cloud data set was made. In addition, data argumentation is used to improve sample utilization efficiency and training accuracy. Finally, a 3D point cloud convolutional neural network model called Panicle-3D was designed to achieve better segmentation accuracy. Specifically, the design of Panicle-3D is aimed at the multiscale characteristics of plant organs, combined with the structure of PointConv and long and short jumps, which accelerates the convergence speed of the network and reduces the loss of features in the process of point cloud downsampling. After comparison experiments, the segmentation accuracy of Panicle-3D reaches 93.4%, which is higher than PointNet. Panicle-3D is suitable for other similar crop point cloud segmentation tasks.

Download Full-text

Extraction of Newly-built Roads Using Probe Data

Abstracts of the ICA ◽

10.5194/ica-abs-1-354-2019 ◽

2019 ◽

Vol 1 ◽

pp. 1-2

Author(s):

Shuto Sugai ◽

Sho Takahashi ◽

Mayumi Noguchi ◽

Akira Sasagawa

Keyword(s):

Geometric Accuracy ◽

Geospatial Information ◽

Data Set ◽

The Road ◽

Personally Identifiable Information ◽

Point Data ◽

On The Road ◽

Map Data ◽

Road Data ◽

Set Of Points

Abstract. Geospatial Information Authority of Japan has been providing the Digital Japan Basic Map as fundamental geospatial information of Japan. In order to keep the map data up-to-date efficiently, we considered the method to extract newly-built roads from probe data which represent various moving trajectories of smartphone users.We used the probe data from NAVITIME JAPAN Co., Ltd., obtained from the GPS navigation application for smartphones the company provided. The probe data are recorded while the application is active, and are provided as a data set of points indicating the moving trajectories. The provided data do not include personally identifiable information. The positioning data are basically matched on the road data in the application; but if the application estimates that the users are not on the road, the raw positioning data are recorded. Note that it is difficult to utilize the data for map update directly, because geometric accuracy of the data may not be enough for map update in detail; thus we have focused on extraction of newly-built roads.The workflow of the extraction is shown in Figure 1. Considering the geometric accuracy of the update sources in the Digital Japan Basic Map, 17.5&thinsp;m wide buffers from the road center lines are generated for the following classification. The points within the buffers indicate that the users moved on existing roads in the Digital Japan Basic Map. The points outside the buffers can be the candidates of newly-built roads. After this classification, we examined all the candidate points and evaluated whether each candidate point represented a newly-built road or not.In this study, we used one-week probe data in August 2017 in Fukuoka prefecture, Japan. By the classification described above, we extracted 37,776 candidate points from 871,129 point data. Some examples of the candidate points are shown in Figure 2. In some cases, we succeeded in extracting newly-built roads; in other cases, however, some data were considered to represent movements in buildings or of airplanes. These unnecessary data increase the number of inappropriate candidate points. In order to reduce the number of such inappropriate points, we have tried to introduce a filtering process using the user’s velocity. In the conference, the result of this filtering will be reported.

Download Full-text

The road surveying system of the federal highway research institute – a performance evaluation of road segmentation algorithms

Advances in Radio Science ◽

10.5194/ars-11-81-2013 ◽

2013 ◽

Vol 11 ◽

pp. 81-85 ◽

Cited By ~ 1

Author(s):

R. Streiter ◽

G. Wanielik

Keyword(s):

Measurement System ◽

Road Construction ◽

The Road ◽

Federal Highway ◽

Driving Assistance ◽

Parametric Description ◽

Sensor Configuration ◽

Road Segmentation ◽

Road Data ◽

Processing Platform

Abstract. The construction of highways and federal roadways is subject to many restrictions and designing rules. The focus is on safety, comfort and smooth driving. Unfortunately, the planning information for roadways and their real constitution, course and their number of lanes and lane widths is often unsure or not available. Due to digital map databases of roads raised much interest during the last years and became one major cornerstone of innovative Advanced Driving Assistance Systems (ADASs), the demand for accurate and detailed road information increases considerably. Within this project a measurement system for collecting high accurate road data was developed. This paper gives an overview about the sensor configuration within the measurement vehicle, introduces the implemented algorithms and shows some applications implemented in the post processing platform. The aim is to recover the origin parametric description of the roadway and the performance of the measurement system is being evaluated against several original road construction information.

Download Full-text

A GF-3 SAR Image Dataset of Road Segmentation

Information Technology And Control ◽

10.5755/j01.itc.50.1.27987 ◽

2021 ◽

Vol 50 (1) ◽

pp. 89-101

Author(s):

Zengguo Sun ◽

Mingmin Zhao ◽

Bai Jia

Keyword(s):

Semantic Segmentation ◽

Synthetic Aperture ◽

Experimental Result ◽

Sar Image ◽

Average Precision ◽

Sar Images ◽

Segmentation Accuracy ◽

Segmentation Algorithms ◽

Image Dataset ◽

Road Segmentation

We constructed a GF-3 SAR image dataset based on road segmentation to boost the development of GF-3 synthetic aperture radar (SAR) image road segmentation technology and make GF-3 SAR images be applied to practice better. We selected 23 scenes of GF-3 SAR images in Shaanxi, China, cut them into road chips with 512 × 512 pixels, and then labeled the dataset using LabelMe labeling tool. The dataset consists of 10026 road chips, and these road images are from different GF-3 imaging modes, so there is diversity in resolution and polarization. Three segmentation algorithms such as Multi-task Network Cascades (MNC), Fully Convolutional Instance-aware Semantic Segmentation (FCIS), and Mask Region Convolutional Neural Networks (Mask R-CNN) are trained by using the dataset. The experimental result measures including Average Precision (AP) and Intersection over Union (IoU) show that segmentation algorithms work well with this dataset, and the segmentation accuracy of Mask R-CNN is the best, which demonstrates the validity of the dataset we constructed.

Download Full-text

PCT: Point cloud transformer

Computational Visual Media ◽

10.1007/s41095-021-0229-5 ◽

2021 ◽

Vol 7 (2) ◽

pp. 187-199

Author(s):

Meng-Hao Guo ◽

Jun-Xiong Cai ◽

Zheng-Ning Liu ◽

Tai-Jiang Mu ◽

Ralph R. Martin ◽

...

Keyword(s):

Language Processing ◽

Point Cloud ◽

Nearest Neighbor ◽

Semantic Segmentation ◽

Nearest Neighbor Search ◽

Local Context ◽

Irregular Domain ◽

Cloud Processing ◽

Neighbor Search ◽

Farthest Point

AbstractThe irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer (PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning. To better capture local context within the point cloud, we enhance input embedding with the support of farthest point sampling and nearest neighbor search. Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.

Download Full-text

Real-time 2D–3D door detection and state classification on a low-power device

SN Applied Sciences ◽

10.1007/s42452-021-04588-3 ◽

2021 ◽

Vol 3 (5) ◽

Author(s):

João Gaspar Ramôa ◽

Vasco Lopes ◽

Luís A. Alexandre ◽

S. Mogo

Keyword(s):

Low Power ◽

Real Time ◽

Object Classification ◽

Semantic Segmentation ◽

Detection Algorithm ◽

Power Device ◽

Indoor Environments ◽

State Classification ◽

Segmentation Algorithms ◽

Indoor Spaces

AbstractIn this paper, we propose three methods for door state classification with the goal to improve robot navigation in indoor spaces. These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are. Our methods work offline, in low-powered computers as the Jetson Nano, in real-time with the ability to differentiate between open, closed and semi-open doors. We use the 3D object classification, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classification networks, AlexNet and GoogleNet. We built a 3D and RGB door dataset with images from several indoor environments using a 3D Realsense camera D435. This dataset is freely available online. All methods are analysed taking into account their accuracy and the speed of the algorithm in a low powered computer. We conclude that it is possible to have a door classification algorithm running in real-time on a low-power device.

Download Full-text

CNN-Based Road-Surface Crack Detection Model That Responds to Brightness Changes

Electronics ◽

10.3390/electronics10121402 ◽

2021 ◽

Vol 10 (12) ◽

pp. 1402

Author(s):

Taehee Lee ◽

Yeohwan Yoon ◽

Chanjun Chun ◽

Seungki Ryu

Keyword(s):

Surface Crack ◽

Autonomous Vehicles ◽

Crack Detection ◽

Model Performance ◽

Semantic Segmentation ◽

Road Surface ◽

Image Brightness ◽

The Road ◽

Detection Model ◽

Artificial Intelligence Models

Poor road-surface conditions pose a significant safety risk to vehicle operation, especially in the case of autonomous vehicles. Hence, maintenance of road surfaces will become even more important in the future. With the development of deep learning-based computer image processing technology, artificial intelligence models that evaluate road conditions are being actively researched. However, as the lighting conditions of the road surface vary depending on the weather, the model performance may degrade for an image whose brightness falls outside the range of the learned image, even for the same road. In this study, a semantic segmentation model with an autoencoder structure was developed for detecting road surface along with a CNN-based image preprocessing model. This setup ensures better road-surface crack detection by adjusting the image brightness before it is input into the road-crack detection model. When the preprocessing model was applied, the road-crack segmentation model exhibited consistent performance even under varying brightness values.

Download Full-text