• Journal of Korea Multimedia Society
• /
• v.19 no.9
• /
• pp.1647-1658
• /
• 2016

RGB+D database has been widely used in object recognition, object tracking, robot control, to name a few. While rapid advance of active depth sensing technologies allows for the widespread of indoor RGB+D databases, there are only few outdoor RGB+D databases largely due to an inherent limitation of active depth cameras. In this paper, we propose a novel method used to build outdoor RGB+D databases. Instead of using active depth cameras such as Kinect or LIDAR, we acquire a pair of stereo image using high-resolution stereo camera and then obtain a depth map by applying stereo matching algorithm. To deal with estimation errors that inevitably exist in the depth map obtained from stereo matching methods, we develop an approach that estimates confidence of depth maps based on unsupervised learning. Unlike existing confidence estimation approaches, we explicitly consider a spatial correlation that may exist in the confidence map. Specifically, we focus on refining confidence feature with the assumption that the confidence feature and resultant confidence map are smoothly-varying in spatial domain and are highly correlated to each other. Experimental result shows that the proposed method outperforms existing confidence measure based approaches in various benchmark dataset.

• The Journal of Korea Robotics Society
• /
• v.14 no.4
• /
• pp.357-362
• /
• 2019

This paper proposes a model and train method that can real-time detect objects and distances estimation based on a monocular camera by applying deep learning. It used YOLOv2 model which is applied to autonomous or robot due to the fast image processing speed. We have changed and learned the loss function so that the YOLOv2 model can detect objects and distances at the same time. The YOLOv2 loss function added a term for learning bounding box values x, y, w, h, and distance values z as 클래스ification losses. In addition, the learning was carried out by multiplying the distance term with parameters for the balance of learning. we trained the model location, recognition by camera and distance data measured by lidar so that we enable the model to estimate distance and objects from a monocular camera, even when the vehicle is going up or down hill. To evaluate the performance of object detection and distance estimation, MAP (Mean Average Precision) and Adjust R square were used and performance was compared with previous research papers. In addition, we compared the original YOLOv2 model FPS (Frame Per Second) for speed measurement with FPS of our model.

• 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.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.130-138
• /
• 2024

High-precision 3D Object Detection is a crucial component within autonomous driving systems, with far-reaching implications for subsequent tasks like multi-object tracking and path planning. In this paper, we propose a novel approach designed to enhance the performance of 3D Object Detection, especially in heading angle estimation by employing a moving object segmentation technique. Our method starts with extracting point-wise moving labels via a process of moving object segmentation. Subsequently, these labels are integrated into the LiDAR Pointcloud data and integrated data is used as inputs for 3D Object Detection. We conducted an extensive evaluation of our approach using the KITTI-road dataset and achieved notably superior performance, particularly in terms of AOS, a pivotal metric for assessing the precision of 3D Object Detection. Our findings not only underscore the positive impact of our proposed method on the advancement of detection performance in lidar-based 3D Object Detection methods, but also suggest substantial potential in augmenting the overall perception task capabilities of autonomous driving systems.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.39-44
• /
• 2022

This paper presents LiDAR static obstacle map based vehicle position correction algorithm for urban autonomous driving. Real Time Kinematic (RTK) GPS is commonly used in highway automated vehicle systems. For urban automated vehicle systems, RTK GPS have some trouble in shaded area. Therefore, this paper represents a method to estimate the position of the host vehicle using AVM camera, front camera, LiDAR and low-cost GPS based on Extended Kalman Filter (EKF). Static obstacle map (STOM) is constructed only with static object based on Bayesian rule. To run the algorithm, HD map and Static obstacle reference map (STORM) must be prepared in advance. STORM is constructed by accumulating and voxelizing the static obstacle map (STOM). The algorithm consists of three main process. The first process is to acquire sensor data from low-cost GPS, AVM camera, front camera, and LiDAR. Second, low-cost GPS data is used to define initial point. Third, AVM camera, front camera, LiDAR point cloud matching to HD map and STORM is conducted using Normal Distribution Transformation (NDT) method. Third, position of the host vehicle position is corrected based on the Extended Kalman Filter (EKF).The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment and showed better performance than only lane-detection algorithm. It is expected to be more robust and accurate than raw lidar point cloud matching algorithm in autonomous driving.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.5
• /
• pp.379-387
• /
• 2006

The real world is spatially modelled conceptually either as discrete objects or earth surface. The generated data models are then usually represented as vector and raster respectively. Although there are limited cases where only one data model is sufficient to solve the spatial problem at hand, it is now generally accepted that GIS should be able to handle various types of data model. Recent advances in spatial technology introduced even more variety of heterogeneous data models and the need is ever growing to handle and manage efficiently these large variety of spatial data. The OGC (Open GIS Consortium), an international organization pursuing standardization in the geospatial industry. recently introduced the GMLJP2 (Geographic Mark-Up Language JP2) format which enables store and handle heterogeneous spatial data. The GMLJP2 format, which is based on the JP2 format which is an abbreviation for JPEG2000 wavelet image compression format, takes advantage of the versatility of the GML capabilities to add extra data on top of the compressed image. This study takes a close look into the GMLJP2 format to analyse and exploit its potential to handle and mange hetergeneous spatial data. Aerial image, digital map and LIDAR data were successfully transformed end archived into a single GMLJP2 file. A simple viewing program was made to view the heterogeneous spatial data from this single file.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.4
• /
• pp.359-365
• /
• 2011

This study aims at filtering ALS points into ground and non-ground effectively through labeling and window based algorithm by utilizing 2D adjacency based on scan line. Firstly, points adjacency is constructed through minimal search based on scan line. Connected component labeling algorithm is applied to classify raw ALS points into ground and non-ground by utilizing the adjacency structure. Then, some small objects are removed by morphology filtering, and isolated ground points are restored by IDW estimation. The experimental results shows that the method provides good filtering performance( about 97% accuracy) for diverse sites, and the overall processing takes less time than converting raw data into TIN or raster grid.

• Smart Media Journal
• /
• v.12 no.4
• /
• pp.41-46
• /
• 2023

UWB is a type of technology used for indoor positioning and is characterized by higher accuracy than RSSI-based schemes. Mobile equipment operating based on ROS can monitor the environment around the equipment using lidar and cameras. When applying the loop closing technique to determine the starting position in this monitoring process, the existing method has a problem of low accuracy because the closing operation occurs only when there are feature points on the image. In this paper, to solve this problem, we designed a system that increases the accuracy of loop closing work by providing location information by mounting a UWB tag on a mobile device. In addition, the accuracy of the UWB-based indoor positioning system was evaluated through experiments, and it was verified that it could be used for loop closing techniques.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.175-189
• /
• 2023

Fault detection and diagnosis (FDI) algorithms are actively being researched for ensuring the integrity and reliability of environment perception sensors in autonomous vehicles. In this paper, a fault detection algorithm based on a multi-sensor perception system composed of radar, camera, and lidar is proposed to guarantee the safety of an autonomous vehicle's perception system. The algorithm utilizes reference generation filters and residual generation filters based on finite impulse response (FIR) filter estimates. By analyzing the residuals generated from the filtered sensor observations and the estimated state errors of individual objects, the algorithm detects faults in the environment perception sensors. The proposed algorithm was evaluated by comparing its performance with a Kalman filter-based algorithm through numerical simulations in a virtual environment. This research could help to ensure the safety and reliability of autonomous vehicles and to enhance the integrity of their environment perception sensors.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.240-251
• /
• 2016

This paper presents a real-time indoor location and pose estimation method that utilizes simple artificial markers and image analysis techniques for the purpose of warehouse automation. The conventional indoor localization methods cannot work robustly in warehouses where severe environmental changes usually occur due to the movement of stocked goods. To overcome this problem, the proposed framework places artificial markers having different interior pattern on the predefined position of the warehouse floor. The proposed algorithm obtains marker candidate regions from a captured image by a simple binarization and labeling procedure. Then it extracts maker interior pattern information from each candidate region in order to decide whether the candidate region is a true marker or not. The extracted interior pattern information and the outer boundary of the marker are used to estimate location and heading angle of the localization system. Experimental results show that the proposed localization method can provide high performance which is almost equivalent to that of the conventional method using an expensive LIDAR sensor and AMCL algorithm.