• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.12
• /
• pp.1061-1067
• /
• 2016

Position of the vehicle for driving is essential to autonomous navigation. However, there appears GPS position error due to multipath which is occurred by tall buildings in downtown area. In this paper, GPS position error is corrected by using camera sensor and highly accurate map made with 3D-Lidar. Input image through inverse perspective mapping is converted into top-view image, and it works out map matching with the map which has intensity of 3D-Lidar. Performance comparison was conducted between this method and traditional way which does map matching with input image after conversion of map to pinhole camera image. As a result, longitudinal error declined 49% and complexity declined 90%.

• Spatial Information Research
• /
• v.18 no.3
• /
• pp.23-32
• /
• 2010

LIDAR data are useful for forest applications such as bare-earth DEM generation for forest areas, and estimation of tree height and forest biomass. As a core preprocessing procedure for most forest applications, this study attempts to develop an efficient method to detect forest areas from LIDAR data. First, we suggest three perceptual cues based on multiple return characteristics, height deviation and spatial distribution, being expected as reliable perceptual cues for forest area detection from LIDAR data. We then classify the potential forest areas based on the individual cue and refine them with a bi-morphological process to eliminate falsely detected areas and smoothing the boundaries. The final refined forest areas have been compared with the reference data manually generated with an aerial image. All the methods based on three types of cues show the accuracy of more than 90%. Particularly, the method based on multiple returns is slightly better than other two cues in terms of the simplicity and accuracy. Also, it is shown that the combination of the individual results from each cue can enhance the classification accuracy.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.500-503
• /
• 2006

To adjust the discrepancy between Light Detection and Ranging (LIDAR) strips, previous researches generally have been conducted using conjugate features, which are called feature-based approaches. However, irrespective of the type of features used, the adjustment process relies upon the existence of suitable conjugate features within the overlapping area and the ability of employed methods to detect and extract the features. These limitations make the process complex and sometimes limit the applicability of developed methodologies because of a lack of suitable features in overlapping areas. To address these drawbacks, this paper presents a methodology using area-based algorithms. This approach is based on the scheme that discrepancies make complex the local height variations of LIDAR data whithin overlapping area. This scheme can be helpful to determine an appropriate transformation for adjustment in the way that minimizes the geographical complexity. During the process, the contour tree (CT) was used to represent the geological characteristics of LIDAR points in overlapping area and the Iterative Closest Points (ICP) algorithm was applied to automatically determine parameters of transformation. After transformation, discrepancies were measured again and the results were evaluated statistically. This research provides a robust methodology without restrictions involved in methods that employ conjugate features. Our method also makes the overall adjustment process generally applicable and automated.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1302-1308
• /
• 2019

This paper presents an approach for classifying image made by acquired position data from a 2D Lidar sensor with a convolutional neural network (CNN). Lidar sensor has been widely used for unmanned devices owing to advantages in term of data accuracy, robustness against geometry distortion and light variations. A CNN algorithm consists of one or more convolutional and pooling layers and has shown a satisfactory performance for image classification. In this paper, different types of CNN architectures based on training methods, Gradient Descent(GD) and Levenberg-arquardt(LM), are implemented. The LM method has two types based on the frequency of approximating Hessian matrix, one of the factors to update training parameters. Simulation results of the LM algorithms show better classification performance of the image data than that of the GD algorithm. In addition, the LM algorithm with more frequent Hessian matrix approximation shows a smaller error than the other type of LM algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.9-21
• /
• 2022

In this paper, we developed a 100% detection system for entering and leaving vehicles by improving the detection rate of existing detection cameras based on the LiDAR sensor, which is one of the core technologies of the 4th industrial revolution. Since the currently operating parking lot depends only on the recognition rate of the license plate number of about 98%, there are various problems such as inconsistency in the entry/exit count, inability to make a reservation in advance due to inaccurate information provision, and inconsistency in real-time parking information. Parking status information should be managed with 100% accuracy, and for this, we built a parking lot entrance/exit detection system using LIDAR. When a parking system is developed by applying the LIDAR sensor, which is mainly used to detect vehicles and objects in autonomous vehicles, it is possible to improve the accuracy of vehicle entry/exit information and the reliability of the entry/exit count with the detected sensing information. The resolution of LIDAR was guaranteed to be 100%, and it was possible to implement so that the sum of entering (+) and exiting (-) vehicles in the parking lot was 0. As a result of testing with 3,000 actual parking lot entrances and exits, the accuracy of entering and exiting parking vehicles was 100%.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.642-645
• /
• 2004

This paper focuses on recovering systematic biases during LIDAR calibration, particularly using natural surfaces as control features. Many previous approaches have utilized all the points overlapping with the control features and often experienced with an inaccurate value converged with a poor rate due to wrong correspondence in pairing a point and the corresponding control features. To overcome these shortcomings, we establish a preventive scheme to select the pairs of high confidence, where the confidence value is based on the error budget associated with the point measurement and the linearity and roughness of the control feature. This approach was then applied to calibraring the LIDAR data simulated with the given systematic biases. The parameters were successfully recovered using the proposed approach with the accuracy and convergence rate superior to those using the previous approaches.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.5
• /
• pp.451-459
• /
• 2011

Fundamentally, there are 5 systems are needed for autonomous navigation of unmanned ground vehicle: Localization, environment perception, path planning, motion planning and vehicle control. Path planning and motion planning are accomplished based on result of the environment perception process. Thus, high reliability of localization and the environment perception will be a criterion that makes a judgment overall autonomous navigation. In this paper, via map matching using vehicle dynamic model and LIDAR sensors, replace high price localization system to new one, and have researched an algorithm that lead to robust autonomous navigation. Finally, all results are verified via actual unmanned ground vehicle tests.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.519-521
• /
• 2003

Within the paper an approach for the automatic extraction and reconstruction of buildings in urban built-up areas base on fusion of high-resolution satellite image and LIDAR data is presented. The presented data fusion scheme is essentially motivated by the fact that image and range data are quite complementary. Raised urban objects are first segmented from the terrain surface in the LIDAR data by making use of the spectral signature derived from satellite image, afterwards building potential regions are initially detected in a hierarchical scheme. A novel 3D building reconstruction model is also presented based on the assumption that most buildings can be approximately decomposed into polyhedral patches. With the constraints of presented building model, 3D edges are used to generate the hypothesis and follow the verification processes and a subsequent logical processing of the primitive geometric patches leads to 3D reconstruction of buildings with good details of shape. The approach is applied on the test sites and shows a good performance, an evaluation is described as well in the paper.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1309-1312
• /
• 2015

본 논문에서는 현대 자율 주행 차량 경진대회에 적용되었던 LIDAR 기반의 다중 물체 추적 알고리즘을 소개한다. 물체 추적은 자율 주행 차량이 외부 환경을 인지하는데 중요한 역할을 한다. 본 논문의 물체 추적 알고리즘은 동시에 여러 개의 물체를 추적할 수 있도록 Multiple Data Association 방식을 사용하였고 순수하게 LIDAR만으로 동작하기 때문에 밤과 낮 모든 경우에 적용 가능하다. 알고리즘은 Clustering, Data Association, State Estimation, Data Arrangement 총 4단계로 이루어져 있으며 본 논문에서는 각 단계별로 알고리즘의 동작 방식을 소개한다. 실제 구현에는 Velodyne사의 HDL-32e이 사용되었고 실제 주행에서 교차로 내의 차량 추적 및 선행 차량의 동향을 추적하는데 적용되었다.

• Korean Journal of Remote Sensing
• /
• v.23 no.3
• /
• pp.199-209
• /
• 2007

Traditionally, aerial images have been used as main sources for compiling topographic maps. In recent years, lidar data has been exploited as another type of mapping data. Regarding their performances, aerial imagery has the ability to delineate object boundaries but omits much of these boundaries during feature extraction. Lidar provides direct information about heights of object surfaces but have limitations with respect to boundary localization. Considering the characteristics of the sensors, this paper proposes an approach to extracting buildings from lidar and aerial imagery, which is based on the complementary characteristics of optical and range sensors. For detecting building regions, relationships among elevation contours are represented into directional graphs and searched for the contours corresponding to external boundaries of buildings. For generating building models, a wing model is proposed to assemble roof surface patches into a complete building model. Then, building models are projected and checked with features in aerial images. Experimental results show that the proposed approach provides an efficient and accurate way to extract building models.