• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.51-56
• /
• 2022

This paper presents an Ground Segmentation algorithm to eliminate unnecessary Lidar Point Cloud Data (PCD) in an autonomous driving system. We consider Random Sample Consensus (Ransac) Algorithm to process lidar ground data. Ransac designates inlier and outlier to erase ground point cloud and classified PCD into two parts. Test results show removal of PCD from ground area by distinguishing inlier and outlier. The paper validates ground rejection algorithm in real time calculating the number of objects recognized by ground data compared to lidar raw data and ground segmented data based on the z-axis. Ground Segmentation is simulated by Robot Operating System (ROS) and an analysis of autonomous driving data is constructed by Matlab. The proposed algorithm can enhance performance of autonomous driving as misrecognizing circumstances are reduced.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.482-483
• /
• 2024

Real-time Point Cloud Ground Segmentation은 자율주행에서 판단 및 객체 탐지/추적 등 다양한 분야에 도움을 준다. 이에 따라, Real-time Point Cloud Ground Segmentation을 했으며, 센서로는 라이다, 알고리즘으로는 TRAVEL논문을 인용했다. 또한 Real-time Point Cloud Ground Segmentation뿐 만 아니라 이동가능지형 판단(Traversability)을 하였다. 그리고 최종적으로, 위와 같은 알고리즘들을 회사 로봇(Scout Mini Robot)에 접목시켰으며 그 과정에서 TRAVEL 알고리즘내에 내제된 파라미터 값들을 최적화시키는 과정이 필요하였다. 그래서 3가지의 방법을 통해 파라미터 값을 선정한 후, 결과값을 비교 분석하였다. 연구 결과, Rellis-3D와 베이지안 최적화를 사용한 베이지안 파라미터가 최적의 파라미터임을 확인할 수 있었다.

• Journal of Information Processing Systems
• /
• v.13 no.3
• /
• pp.491-499
• /
• 2017

In this study, we proposed a new approach to segment ground and nonground points gained from a 3D laser range sensor. The primary aim of this research was to provide a fast and effective method for ground segmentation. In each frame, we divide the point cloud into small groups. All threshold points and start-ground points in each group are then analyzed. To determine threshold points we depend on three features: gradient, lost threshold points, and abnormalities in the distance between the sensor and a particular threshold point. After a threshold point is determined, a start-ground point is then identified by considering the height difference between two consecutive points. All points from a start-ground point to the next threshold point are ground points. Other points are nonground. This process is then repeated until all points are labelled.

• Journal of Korea Game Society
• /
• v.17 no.6
• /
• pp.139-152
• /
• 2017

In this paper, we propose a ground area detection technique based on region segmentation in the spherical image. We modified the Watershed planar image segmentation method to segment spherical images. After regions are segmented, the ground area is detected by comparing colors and textures of pixels of the assumed ground region with the pixels of other regions. The ground detection technique for planar images cannot be used for spherical images due to the spherical distortion. Considering the spherical distortion, we designed the ground shape detection algorithm to detect the ground area in the spherical images. Our experimental results show that the proposed technique properly detects ground areas both for the flat ground and the obstacle-filled ground environments.

• Journal of information and communication convergence engineering
• /
• v.13 no.3
• /
• pp.205-214
• /
• 2015

In this paper, we propose a new approach to learning a discriminative model for figure/ground segmentation by incorporating the bag-of-features and conditional random field (CRF) techniques. We advocate the use of image patches instead of superpixels as the basic processing unit. The latter has a homogeneous appearance and adheres to object boundaries, while an image patch often contains more discriminative information (e.g., local image structure) to distinguish its categories. We use pixel-level sparse coding to represent an image patch. With the proposed feature representation, the unary classifier achieves a considerable binary segmentation performance. Further, we integrate unary and pairwise potentials into the CRF model to refine the segmentation results. The pairwise potentials include color and texture potentials with neighborhood interactions, and an edge potential. High segmentation accuracy is demonstrated on three benchmark datasets: the Weizmann horse dataset, the VOC2006 cow dataset, and the MSRC multiclass dataset. Extensive experiments show that the proposed approach performs favorably against the state-of-the-art approaches.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.134-141
• /
• 2023

We present a novel method aimed at refining ground truth data through regularization and modification, particularly applicable when working with the original ground truth set. Enhancing the performance of deep neural networks is achieved by applying regularization techniques to the existing ground truth data. In many machine learning tasks requiring pixel-level segmentation sets, accurately delineating objects is vital. However, it proves challenging for thin and elongated objects such as blood vessels in X-ray coronary angiography, often resulting in inconsistent generation of ground truth data. This method involves an analysis of the quality of training set pairs - comprising images and ground truth data - to automatically regulate and modify the boundaries of ground truth segmentation. Employing the active contour model and a recursive ground truth generation approach results in stable and precisely defined boundary contours. Following the regularization and adjustment of the ground truth set, there is a substantial improvement in the performance of deep neural networks.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.681-682
• /
• 2016

In this study we propose a novel approach to segment a terrain in two parts: ground and none-ground. The terrain is gained by a multi-channel 3D laser range sensor. We process each vertical line in each frame data. The vertical line is bounded by the sensor's position and a point in the largest circle of the frame. We consider each pair of two consecutive points in each line to find begin-ground and end-ground points. All points placed between a begin-ground point and an end-ground point are ground ones. The other points are none-ground. After examining all vertical lines in the frame, we obtain the terrain segmentation result.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• Tunnel and Underground Space
• /
• v.29 no.6
• /
• pp.508-522
• /
• 2019

Because of the slope failure, not only property damage but also human damage can occur, slope stability analysis should be conducted to predict and reinforce of the slope. This paper, defines the ground areas that can be characterized in terms of slope failure such as Rockmass jointset, Rockmass fault, Soil, Leakage water and Crush zone in sloped images. As a result, it was shown that the deep learning instance segmentation network can be used to recognize and automatically segment the precise shape of the ground region with different characteristics shown in the image. It showed the possibility of supporting the slope mapping work and automatically calculating the ground characteristics information of slopes necessary for decision making such as slope reinforcement.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.733-734
• /
• 2016

This study proposes a novel approach for ground segmentation of 3D point cloud. We combine two techniques: gradient threshold segmentation, and mean height evaluation. Acquired 3D point cloud is represented as a graph data structures by exploiting the structure of 2D reference image. The ground parts nearing the position of the sensor are segmented based on gradient threshold technique. For sparse regions, we separate the ground and nonground by using a technique called mean height evaluation. The main contribution of this study is a new ground segmentation algorithm which works well with 3D point clouds from various environments. The processing time is acceptable and it allows the algorithm running in real time.