• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.422-424
• /
• 2021

In this paper, it leads the approach of fusing multiple RGB cameras for visual objects recognition based on deep learning with convolution neural network and 3D Light Detection and Ranging (LiDAR) to observe the environment and match into a 3D world in estimating the distance and position in a form of point cloud map. The goal of perception in multiple cameras are to extract the crucial static and dynamic objects around the autonomous vehicle, especially the blind spot which assists the AV to navigate according to the goal. Numerous cameras with object detection might tend slow-going the computer process in real-time. The computer vision convolution neural network algorithm to use for eradicating this problem use must suitable also to the capacity of the hardware. The localization of classified detected objects comes from the bases of a 3D point cloud environment. But first, the LiDAR point cloud data undergo parsing, and the used algorithm is based on the 3D Euclidean clustering method which gives an accurate on localizing the objects. We evaluated the method using our dataset that comes from VLP-16 and multiple cameras and the results show the completion of the method and multi-sensor fusion strategy.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.389-393
• /
• 2007

There has been many researches using LiDAR(Light Detection And Ranging) data. There has been many other researches through out the world using the 3 dimensional spatial data in various fields. In this research, Using lidar data and digital images, we have extracted the position of the power-transmission line and created 3 dimensional models. The presented method is more efficient than field surveying and it can also be used lot monitoring change in the environment

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.4
• /
• pp.259-266
• /
• 2015

Change detection using the heterogeneous data such as aerial images, aerial LiDAR (Light Detection And Ranging), and satellite images needs to be developed to efficiently monitor the complicating land use change. We approached this problem not relying on the intensity value of the geospatial image, but by using RECC(Relative Edge Cross Correlation) which is based on the edge information over the urban and suburban area. The experiment was carried out for the aerial LiDAR data with high-resolution Kompsat-2 and −3 images. We derived the optimal window size and threshold value for RECC-based change detection, and then we observed the overall change detection accuracy of 80% by comparing the results to the manually acquired reference data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_2
• /
• pp.611-623
• /
• 2013

Point cloud data (i.e., LiDAR; Light Detection and Ranging) collected by Airborne Laser Scanner (ALS) system is one of the major sources for surface reconstruction including DEM generation, topographic mapping and object modeling. Recently, demand and requirement of the accurate and realistic Digital Building Model (DBM) increase for geospatial platforms and spatial data infrastructure. The main issues in the object modeling such as building and city modeling are efficiency of the methodology and quality of the final products. Efficiency and quality are associated with automation and accuracy, respectively. However, these two factors are often opposite each other. This paper aims to introduce correction scheme of incorrectly determined Model Key Points (MKPs) regardless of the segmentation method. Planimetric and height locations of the MKPs were refined by surface patch fitting based on the Least-Squares Solution (LESS). The proposed methods were applied to the synthetic and real LiDAR data. Finally, the results were analyzed by comparing adjusted MKPs with the true building model data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.635-644
• /
• 2020

Object recognition, detection and instance segmentation based on DL (Deep Learning) have being used in various practices, and mainly optical images are used as training data for DL models. The major objective of this paper is object segmentation and building detection by utilizing multimodal datasets as well as optical images for training Detectron2 model that is one of the improved R-CNN (Region-based Convolutional Neural Network). For the implementation, infrared aerial images, LiDAR data, and edges from the images, and Haralick features, that are representing statistical texture information, from LiDAR (Light Detection And Ranging) data were generated. The performance of the DL models depends on not only on the amount and characteristics of the training data, but also on the fusion method especially for the multimodal data. The results of segmenting objects and detecting buildings by applying hybrid fusion - which is a mixed method of early fusion and late fusion - results in a 32.65% improvement in building detection rate compared to training by optical image only. The experiments demonstrated complementary effect of the training multimodal data having unique characteristics and fusion strategy.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.5
• /
• pp.453-464
• /
• 2012

This is a research of an adaptive longitudinal control system for situated cognition in wide range, traffic accidents reduction and safety driving environment by integrated system which graft a road infrastructure's information based on IT onto the intelligent vehicle combined automobile and IT technology. The road infrastructure installed by laser scanner in intersection, speed limited area and sharp curve area where is many risk of traffic accident. The road infra conducts objects recognition, segmentation, and tracking for determining dangerous situation and communicates real-time information by Ethernet with vehicle. Also, the data which transmitted from infrastructure supports safety driving by integrated with laser scanner's data on vehicle bumper.

• Tunnel and Underground Space
• /
• v.30 no.1
• /
• pp.76-86
• /
• 2020

In this study, a small autonomous driving robot was developed for underground mines using the Light Detection and Ranging (LiDAR) sensor. The developed robot measures the distances to the left and right wall surfaces using the LiDAR sensor, and automatically controls its steering to drive along the centerline of mine tunnel. A field experiment was conducted in an underground amethyst mine to test the driving performance of developed robot. During five repeated driving tests, the robot showed stable driving performance overall. There were no collision accidents with the wall of mine tunnel.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1009-1024
• /
• 2018

With the increased use of LiDAR (Light Detection and Ranging) that can obtain over millions of point dataset, methodologies for efficient search and dimensionality reduction for the point cloud became a crucial technique. The existing octree-based "parametric algorithm" has proved its efficiency and contributed as a part of PCL (Point Cloud Library). However, the implementation of the algorithm on GPU (Graphics Processing Unit) is considered very difficult because of structural constraints of the octree implemented in PCL. In this paper, we present a method for the parametric algorithm on GPU environment and implement a projection of the queried points on four directions with an improved noise reduction.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.3
• /
• pp.1-14
• /
• 2024

Gaining an accurate 3D stream geometry has become feasible with Unmanned Aerial Vehicle (UAV), which is crucial for better understanding stream hydrodynamic processes. The objective of this study was to investigate series of filters to remove stream vegetation and propose the best method for generating Digital Terrain Models (DTMs) using UAV-based point clouds. A stream reach approximately 500 m of the Bokha stream in Icheon city was selected as the study area. Point clouds were obtained in August 1st, 2023, using Phantom 4 multispectral and Zenmuse L1 for Structure from Motion (SfM) and Light Detection And Ranging (LiDAR) respectively. Three vegetation filters, two morphological filters, and six composite filters which combined vegetation and morphological filters were applied in this study. The Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were used to assess each filters comparing with the two cross-sections measured by leveling survey. The vegetation filters performed better in SfM, especially for short vegetation areas, while the morphological filters demonstrated superior performance on LiDAR, particularly for taller vegetation areas. Overall, the composite filters combining advantages of two types of filters performed better than single filter application. The best method was the combination of Progressive TIN (PTIN) and Color Indicies of Vegetation Extraction (CIVE) for SfM, showing the smallest MAE of 0.169 m. The proposed method in this study can be utilized for constructing DTMs of stream and thus contribute to improving the accuracy of stream hydrodynamic simulations.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.3
• /
• pp.22-30
• /
• 2007

It is difficult to generate DTM using aerial photographs because trees usually cover disaster occurred areas. So, this study proposed how to filter by moving window using digital aerial photographs and generate accurate DTM. The results were compared with those of adaptive filtering by commercial digital photogrammetry software (Socet set) to find out the effect of tree removal by window size in forest soil sediment disaster. And then they were compared with DTM generated from LiDAR data. As a result, it was showed that the accuracy of moving filtering DTM was lower than that of LiDAR DTM while it was higher by 6m than that of Adaptive filtering.