• 전기학회논문지
• /
• 제65권2호
• /
• pp.342-348
• /
• 2016

We propose an obstacle detection algorithm for unmanned ground vehicle on uneven terrain. The key ideas of the proposed algorithm are the use of two-layer laser range data to calculate the gradient of a target, which is characterized as either ground or obstacles. The proposed obstacle detection algorithm includes 4-steps: 1) Obtain the distance data for each angle from multiple lidars or a multi-layer scan lidar. 2) Calcualate the gradient for each angle of the uneven terrain. 3) Determine ground or obstacle for each angle on the basis of reference gradient. 4) Generate a new distance data for each angle for a virtual laser scanner. The proposed algorithm is verified by various experiments.

• Smart Structures and Systems
• /
• 제30권1호
• /
• pp.17-34
• /
• 2022

For steel structures, fatigue cracks are critical damage induced by long-term cycle loading and distortion effects. Vision-based crack detection can be a solution to ensure structural integrity and performance by continuous monitoring and non-destructive assessment. A critical issue is to distinguish cracks from other features in captured images which possibly consist of complex backgrounds such as handwritings and marks, which were made to record crack patterns and lengths during periodic visual inspections. This study presents a parametric study on image-based crack identification for orthotropic steel bridge decks using captured images with complicated backgrounds. Firstly, a framework for vision-based crack segmentation using the atrous convolution-based Deeplapv3+ network (ACDN) is designed. Secondly, features on crack images are labeled to build three databanks by consideration of objects in the backgrounds. Thirdly, evaluation metrics computed from the trained ACDN models are utilized to evaluate the effects of obstacles on crack detection results. Finally, various training parameters, including image sizes, hyper-parameters, and the number of training images, are optimized for the ACDN model of crack detection. The result demonstrated that fatigue cracks could be identified by the trained ACDN models, and the accuracy of the crack-detection result was improved by optimizing the training parameters. It enables the applicability of the vision-based technique for early detecting tiny fatigue cracks in steel structures.

• 대한임베디드공학회논문지
• /
• 제19권2호
• /
• pp.91-99
• /
• 2024

Collision avoidance system is important to improve the robustness and functional safety of autonomous vehicles. This paper proposes an object-level distance estimation method to develop a collision avoidance system, and it is applied to golfcarts utilized in country club environments. To improve the detection accuracy, we continually trained an object detection model based on pseudo labels generated by a pre-trained detector. Moreover, we propose object-aware depth estimation (OADE) method which trains a depth model focusing on object regions. In the OADE algorithm, we generated dense depth information for object regions by utilizing detection results and sparse LiDAR points, and it is referred to as object-aware LiDAR projection (OALP). By using the OALP maps, a depth estimation model was trained by backpropagating more gradients of the loss on object regions. Experiments were conducted on our custom dataset, which was collected for the travel distance of 22 km on 54 holes in three country clubs under various weather conditions. The precision and recall rate were respectively improved from 70.5% and 49.1% to 95.3% and 92.1% after the continual learning with pseudo labels. Moreover, the OADE algorithm reduces the absolute relative error from 4.76% to 4.27% for estimating distances to obstacles.

• ETRI Journal
• /
• 제40권2호
• /
• pp.246-256
• /
• 2018

A spatial augmented reality (SAR) system enables a virtual image to be projected onto the surface of a real-world object and the user to intuitively control the image using a tangible interface. However, occlusions frequently occur, such as a sudden change in the lighting environment or the generation of obstacles. We propose a robust object tracker based on a multithreaded system, which can track an object robustly through occlusions. Our multithreaded tracker is divided into two threads: the detection thread detects distinctive features in a frame-to-frame manner, and the tracking thread tracks features periodically using an optical-flow-based tracking method. Consequently, although the speed of the detection thread is considerably slow, we achieve real-time performance owing to the multithreaded configuration. Moreover, the proposed outlier filtering automatically updates a random sample consensus distance threshold for eliminating outliers according to environmental changes. Experimental results show that our approach tracks an object robustly in real-time in an SAR environment where there are frequent occlusions occurring from augmented projection images.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.164-164
• /
• 2000

This paper proposes a moving window technique that extracts lanes and vehicles using the images captured by a CCD camera equipped inside an automobile in real time. For the purpose, first of all the optimal size of moving window is determined based upon speed of the vehicle, road curvature, and camera parameters. Within the moving windows that are dynamically changing, lanes and vehicles are extracted, and the vehicles within the driving lanes are classified as obstacles. Assuming highway driving, there are two sorts of image-objects within the driving lanes: one is ground mark to show the limit speed or some information for driving, and the other is the vehicle as an obstacle. Using characteristics of three-dimension objects, a neural network can be trained to distinguish the vehicle from ground mark. When it is recognized as an obstacle, the distance from the camera to the front vehicle can be calculated with the aids of database that keeps the models of automobiles on the highway. The correctness of this measurement is verified through the experiments comparing with the radar and laser sensor data.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.385-386
• /
• 2007

This paper proposes obstacle detection and classification algorithm using a single laser scanner. The proposed algorithm searches the object singular points using a differential equation, and finds obstacle singular points shows a boundary of obstacle. And the proposed algorithm can classify object even if several obstacles overlapped. Simulation results show the feasibility of proposed algorithm using a single laser scanner, not using several laser scanners.

• 대한기계학회논문집A
• /
• 제37권2호
• /
• pp.169-176
• /
• 2013

알려지지 않은 실내에서 인간형 로봇의 이동경로 생성을 위해서는 주변 장애물의 형태를 정확히 인식하여 이에 적합한 로봇 움직임을 만들어야 한다. 이 때, 인식된 장애물의 형태에 따라 로봇이 접촉없이 통과할 수 있고, 발과 접촉하여 통과할 수도 있으며, 회피할 수도 있다. 이를 위해 장애물이 어떤 형태를 갖고 있는지를 분류하여 로봇의 이동경로를 생성할 때 활용 가능한 장애물 인식 및 분류 방법을 제안한다. 특히 장애물 형태를 정확히 인식하기 위한 기존 알고리즘은 많은 계산량으로 실시간 활용에 어려움이 있으며, 불필요한 장애물도 함께 추출하기 때문에 연산자원의 낭비가 불가피하다. 본 연구에서는 장애물 인식의 계산량을 줄이기 위해 장애물의 영역을 분류한 후 정확한 형상이 필요한 장애물에 한해 크기 및 형태를 추출하도록 알고리즘의 적용 범위를 제한하여 계산량을 줄이는 방법을 제안한다.

• 한국지능시스템학회논문지
• /
• 제24권2호
• /
• pp.111-116
• /
• 2014

투명 장애물이 포함된 환경에서 레이저 거리 측정기만을 사용하여 장애물을 인식하다는 것은 이동 로봇이 장애물과의 충돌로부터 자유로운 자율 주행을 보장할 수 없는 문제를 야기한다. 이를 해결하기 위해 레이저 거리 측정기를 사용하는 이동 로봇은 투명 장애물을 인식할 수 있는 초음파 센서와 같은 추가적인 센서를 사용해야 한다. 본 논문에서는 레이저 거리 측정기만을 이용하여 환경 내에 존재하는 투명 장애물을 인식할 수 있도록 하는 투명 장애물 인식 알고리즘을 제안한다. 투명 장애물 인식 알고리즘은 레이저 거리 측정기를 이용하여 투명 장애물을 인식하였을 경우, 투명 장애물에 의해 발생되는 반사 잡음(reflected noise)만을 추출하여 이를 처리함으로서 투명 장애물의 위치를 찾도록 하는 것이다. 이를 통해 이동 로봇은 투명 장애물 환경에서 레이저 거리 측정기만을 사용하더라도 장애물과의 충돌로부터 자유로운 자율 주행을 보장받을 수 있다. 또한 본 논문에서 제안한 알고리즘의 유효성을 평가하기 위해 세 가지의 실험 환경에서 실제 이동 로봇 및 레이저 거리 측정기를 사용하여 측정하였다.

• International Journal of Aeronautical and Space Sciences
• /
• 제12권3호
• /
• pp.274-282
• /
• 2011

This paper is focused on dynamic modeling and control system design as well as vision based collision avoidance for multi-rotor unmanned aerial vehicles (UAVs). Multi-rotor UAVs are defined as rotary-winged UAVs with multiple rotors. These multi-rotor UAVs can be utilized in various military situations such as surveillance and reconnaissance. They can also be used for obtaining visual information from steep terrains or disaster sites. In this paper, a quad-rotor model is introduced as well as its control system, which is designed based on a proportional-integral-derivative controller and vision-based collision avoidance control system. Additionally, in order for a UAV to navigate safely in areas such as buildings and offices with a number of obstacles, there must be a collision avoidance algorithm installed in the UAV's hardware, which should include the detection of obstacles, avoidance maneuvering, etc. In this paper, the optical flow method, one of the vision-based collision avoidance techniques, is introduced, and multi-rotor UAV's collision avoidance simulations are described in various virtual environments in order to demonstrate its avoidance performance.

• International Journal of Aeronautical and Space Sciences
• /
• 제12권3호
• /
• pp.252-259
• /
• 2011

This paper is focused on dynamic modeling and control system design as well as vision based collision avoidance for multi-rotor unmanned aerial vehicles (UAVs). Multi-rotor UAVs are defined as rotary-winged UAVs with multiple rotors. These multi-rotor UAVs can be utilized in various military situations such as surveillance and reconnaissance. They can also be used for obtaining visual information from steep terrains or disaster sites. In this paper, a quad-rotor model is introduced as well as its control system, which is designed based on a proportional-integral-derivative controller and vision-based collision avoidance control system. Additionally, in order for a UAV to navigate safely in areas such as buildings and offices with a number of obstacles, there must be a collision avoidance algorithm installed in the UAV's hardware, which should include the detection of obstacles, avoidance maneuvering, etc. In this paper, the optical flow method, one of the vision-based collision avoidance techniques, is introduced, and multi-rotor UAV's collision avoidance simulations are described in various virtual environments in order to demonstrate its avoidance performance.