Vehicle detection from airborne LiDAR point clouds based on a decision tree algorithm with horizontal and vertical features

Eum, Junho; Bae, Minho; Jeon, Junbeom; Lee, Heezin; Oh, Sangyoon; Lee, Minsu

doi:10.1080/2150704x.2016.1278310

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the data passed the inspection and correlation analysis, all calibration data sets were divided into the training set and the test set at the ratio of 7:3 with factors such as intensity and color as independent variables, and the R L as the dependent variable. A decision tree algorithm was used to fit and regress the data ( 46 ). By choosing splitting conditions and pruning rules to constrain the decision tree, we found the relationship between reflection intensity, color, and retroreflection of road traffic markings, and built a decision tree-based calibration prediction model.…”

Section: Road Marking Calibration and Evaluation Methods Based On Veh...mentioning

confidence: 99%

LiDAR Perception and Evaluation Method for Road Traffic Marking Retroreflection

Huang

Han

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

To solve the problem of low efficiency in retroreflection maintenance of road traffic markings, in this study a vehicle-mounted LiDAR-based perception and evaluation method of retroreflection of markings is proposed. First, this method establishes a calibration prediction model for LiDAR based on a regression decision tree. Then, a marking maintenance evaluation model is constructed in combination with the decision threshold proposed by China’s national standard, and the accuracy of the maintenance evaluation model is analyzed using F1-score, recall, and precision. In this study, four marking lines were used as the calibration data source, and a dataset of an independent 1,300 m road section was used to verify the established models. The results show that the coefficient of the retroreflected luminance ( RL) and the reflection intensity of the markings are positively correlated. During the construction of the calibration prediction model, the multiple linear regression functions, the second-order polynomial functions, and the decision tree are compared, and the result indicates that decision tree has the best fit to the data with the coefficient of determination for the established calibration prediction model better than 0.95. The agreement between the maintenance decision obtained from the maintenance evaluation model and the traditional method is more than 85%. The time cost is reduced by at least 90%. The proposed calibration prediction model can accurately predict the RL, and can quickly collect the RL values of the in-service road traffic markings. The proposed maintenance evaluation model is highly efficient and can replace the traditional evaluation method for markings.

show abstract

Section: Road Marking Calibration and Evaluation Methods Based On Veh...mentioning

confidence: 99%

LiDAR Perception and Evaluation Method for Road Traffic Marking Retroreflection

Huang

Han

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…The device can obtain better real-time performance and accuracy. Junho [33] extracted the features such as area and rectangle in the horizontal and vertical directions of the obtained point cloud, established a vehicle recognition model and used the decision tree algorithm to train a classifier for vehicle target recognition. Moreover, using the SVM classifier for training, Himmelsbach extracted more specific features including object reflectivity, volume and local points.…”

Section: Related Researchmentioning

confidence: 99%

Robust LiDAR-Based Vehicle Detection for On-Road Autonomous Driving

Jin

Yang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The stable detection and tracking of high-speed vehicles on the road by using LiDAR can input accurate information for the decision-making module and improve the driving safety of smart cars. This paper proposed a novel LiDAR-based robust vehicle detection method including three parts: point cloud clustering, bounding box fitting and point cloud recognition. Firstly, aiming at the problem of clustering quality degradation caused by the uneven distribution of LiDAR point clouds and the difference in clustering radius between point cloud clusters in traditional DBSCAN (TDBSCAN) obstacle clustering algorithms, an improved DBSCAN algorithm based on distance-adaptive clustering radius (ADBSCAN) is designed, and a point cloud KD-Tree data structure is constructed to speed up the traversal of the algorithm; meanwhile, the OPTICS algorithm is introduced to enhance the performance of the proposed algorithm. Then, by adopting different fitting strategies for vehicle contour points in various states, the adaptability of the bounding box fitting algorithm is improved; Moreover, in view of the shortcomings of the poor robustness of the L-shape algorithm, the principal component analysis method (PCA) is introduced to obtain stable bounding box fitting results. Finally, considering the time-consuming and low-accuracy training of traditional machine learning algorithms, advanced PointNet in deep learning technique is built to send the point cloud within the bounding box of a high-confidence vehicle into PointNet to complete vehicle recognition. Experiments based on our autonomous driving perception platform and the KITTI dataset prove that the proposed method can stably complete vehicle target recognition and achieve a good balance between time-consuming and accuracy.

show abstract

“…The traditional methods of point cloud feature extraction mainly have two directions: the first is feature extraction based on a triangular network model, and the other is feature extraction based on scattered point clouds. − Among them, the point cloud is triangulated on the basis of a triangular mesh for feature extraction. This method establishes the topological relationship of point cloud data, and it takes the edge of a triangular patch as the feature line, which simplifies the process of feature point extraction.…”

Section: Introductionmentioning

confidence: 99%

Geometric Feature Extraction of Point Cloud of Chemical Reactor Based on Dynamic Graph Convolution Neural Network

Zhao

Guo

2021

ACS Omega

View full text Add to dashboard Cite

Geometric features are an important factor for the classification of drugs and other transport objects in chemical reactors. The moving speed of drugs and other transport objects in chemical reactors is fast, and it is difficult to obtain their features by imaging and other methods. In order to avoid the mistaken and missed distribution of drugs and other objects, a method of extracting geometric features of the drug’s point cloud in a chemical reactor based on a dynamic graph convolution neural network (DGCNN) is proposed. In this study, we first use MATLAB R2019a to add a random number of noise points in each point cloud file and label the point cloud. Second, k -nearest neighbor (KNN) is used to construct the adjacency relationship of all nodes, and the effect of DGCNN under different k values and the confusion matrix under the optimal k value are analyzed. Finally, we compare the effect of DGCNN with PointNet and PointNet++. The experimental results show that when k is 20, the accuracy, precision, recall, and F1 score of DGCNN are higher than those of other k values, while the training time is much shorter than that of k = 25, 30, and 35; in addition, the effect of DGCNN in extracting geometric features of the point cloud is better than that of PointNet and PointNet++. The results show that it is feasible to use DGCNN to analyze the geometric characteristics of drug point clouds in a chemical reactor. This study fills the gap of the end-to-end extraction method for a point cloud’s corresponding geometric features without a data set. In addition, this study promotes the institutionalization, standardization, and intelligent design of safe production and management of drugs and other objects in the chemical reactor, and it has positive significance for the production cost and resource utilization of the whole pharmaceutical process. At the same time, it provides a new method for the intelligent processing of point cloud data.

show abstract

Vehicle detection from airborne LiDAR point clouds based on a decision tree algorithm with horizontal and vertical features

Cited by 9 publications

References 12 publications

LiDAR Perception and Evaluation Method for Road Traffic Marking Retroreflection

LiDAR Perception and Evaluation Method for Road Traffic Marking Retroreflection

Robust LiDAR-Based Vehicle Detection for On-Road Autonomous Driving

Geometric Feature Extraction of Point Cloud of Chemical Reactor Based on Dynamic Graph Convolution Neural Network

Contact Info

Product

Resources

About