• ETRI Journal
• /
• 제45권5호
• /
• pp.847-861
• /
• 2023

Dynamic object detection is essential for ensuring safe and reliable autonomous driving. Recently, light detection and ranging (LiDAR)-based object detection has been introduced and shown excellent performance on various benchmarks. Although LiDAR sensors have excellent accuracy in estimating distance, they lack texture or color information and have a lower resolution than conventional cameras. In addition, performance degradation occurs when a LiDAR-based object detection model is applied to different driving environments or when sensors from different LiDAR manufacturers are utilized owing to the domain gap phenomenon. To address these issues, a sensor-fusion-based object detection and classification method is proposed. The proposed method operates in real time, making it suitable for integration into autonomous vehicles. It performs well on our custom dataset and on publicly available datasets, demonstrating its effectiveness in real-world road environments. In addition, we will make available a novel three-dimensional moving object detection dataset called ETRI 3D MOD.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.126-129
• /
• 2008

In this paper, we proposed a method extracting an object from background of the satellite image. The image segmentation techniques have been widely studied for the technology to segment image and to synthesis segment object with other images. Proposed algorithm is to perform the edge detection of a selected object using genetic algorithm. We segment region of object based on detection edge using watershed algorithm. We separated background and object in indefinite region using gradual region merge from segment object. And, we make GUI for the application of the proposed algorithm to various tests. To demonstrate the effectiveness of the proposed method, several analysis on the satellite images are performed.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.367-370
• /
• 2004

We model a moving object as a sizable physical entity equipped with GPS, wireless communication capability, and a computer such as a PDA and mobile phone. Furthermore, we have observed that a real trajectory of a moving object is the result of interactions among moving objects in the system yielding Multi-points instead of a line segment. In this paper, the new types and operations are integrated seamlessly into the moving object framework to achieve a relatively simple, consistent and powerful overall model and query language for constrained and unconstrained movement.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.317-320
• /
• 2005

The LBS (Location-Based Services) are valuable information services combined the location of moving object with various contents such as map, POI (point of Interest), route and so on. The must general service of LBS is route determination service and its applicable parts are FMS (Fleet Management System), travel advisory system and mobile navigation system. The core function of route determination service is determination of optimal route from source to destination in various environments. The MODB (Moving Object Database) system, core part of LBS composition systems, is able to manage current or past location information of moving object and massive trajectory information stored in MODB is value-added data in CRM, ERP and data mining part. Also this past trajectory information can be helpful to determine optimal route. In this paper, we suggest methods to determine optimal route by querying past trajectory information in MODB system and verify the effectiveness of suggested method.

• 한국멀티미디어학회논문지
• /
• 제17권5호
• /
• pp.556-565
• /
• 2014

This paper proposes a method to track object of real-time video transferred through single web-camera and to recognize risk-situation and human actions. The proposed method recognizes human basic actions that human can do in daily life and finds risk-situation such as faint and falling down to classify usual action and risk-situation. The proposed method models the background, obtains the difference image between input image and the modeled background image, extracts human object from input image, tracts object's motion and recognizes human actions. Tracking object uses the moment information of extracting object and the characteristic of object's recognition is moment's change and ratio of object's size between frames. Actions classified are four actions of walking, waling diagonally, sitting down, standing up among the most actions human do in daily life and suddenly falling down is classified into risk-situation. To test the proposed method, we applied it for eight participants from a video of a web-cam, classify human action and recognize risk-situation. The test result showed more than 97 percent recognition rate for each action and 100 percent recognition rate for risk-situation by the proposed method.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2009년도 춘계학술대회
• /
• pp.219-222
• /
• 2009

Rapid object recognition is one of the main stream research themes focusing to reveal how human recognizes object and interacts with environment in natural world. This field of study is of consequence in that it is highly important in evolutionary perspective to quickly see the external objects and judge their characteristics to plan future reactions. In this study, we investigated how human detect natural scene objects and categorize them in a limited time frame. We applied Magnetoencepahlogram (MEG) while participants were performing detection (e.g. object vs. texture) or basic-level categorization (e.g. cars vs. dogs) tasks to track the dynamic interaction in human brain for rapid object recognition process. The results revealed that detection and categorization involves different temporal and functional connections that correlated for the successful recognition process as a whole. These results imply that dynamics in the brain are important for our interaction with environment. The implication from this study can be further extended to investigate the effect of subconscious emotional factors on the dynamics of brain interactions during the rapid recognition process.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2002년도 추계학술발표논문집
• /
• pp.101-109
• /
• 2002

본고에서는 움직이는 물체를 추적하는 알고리즘을 제시한다. 이미지의 색상에 대한 불변치를 활용하여 비디오 클립에서 물체 영역을 추출하고 co-occurrence matrix를 구한 후 인접 프레임 간의 대응되는 물체를 결정하여 물체의 괘적을 추적한다. 물체 영역에 적응되는 특징값들의 분리정도치를 활용하여 시스템의 성능을 향상시키는 방법과 실험 결과를 제시한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.941-942
• /
• 2006

A depth measurement system to recognize 3D shape of objects using single camera, line laser and a rotating mirror has been investigated. The camera and the light source are fixed, facing the rotating mirror. The laser light is reflected by the mirror and projected to the scene objects whose locations are to be determined. The camera detects the laser light location on object surfaces through the same mirror. The scan over the area to be measured is done by mirror rotation. The Segmentation process of object recognition is performed using the depth data of restored 3D data. The Object recognition domain can be reduced by separating area of interest objects from complex background.

• 대한원격탐사학회지
• /
• 제38권5_1호
• /
• pp.535-543
• /
• 2022

농업분야에서 드론을 활용하여 작물의 생육을 진단하고 정보를 영상으로 제공하고 있다. 들녘 단위에 대한 고해상도 드론 영상을 활용하는 경우 객체별 생육정보를 생산할 수 있으나 정확하게 작물을 탐지하고 인접한 객체를 효율적으로 구분하기 위한 작업이 요구된다. 본 연구에서는 작물 객체를 탐지하고 위치 정보를 추출하는 알고리즘을 개발하는 것이 목적이다. 드론 다중분광영상과 컴퓨터 비전 기술을 활용하여 객체 탐지를 위한 알고리즘을 개발하였으며, 대상 작물은 가을배추로 선정하였다. 2018년~2020년까지 가을배추를 대상으로 정식 후 7일~15일 사이의 드론 영상을 취득하였으며, 2019년 영상 기반으로 객체 탐지 알고리즘을 개발한 뒤 2018년, 2020년 영상을 기반으로 알고리즘 평가를 수행하였다. 분광반사도 기반 지수와 식생의 분광반사도 특성을 고려하여 식생 지역을 추출하였다. 이후 추출된 식생 지역에서 객체의 크기를 고려하여 팽창(Dilatation), 침식(Erosion), 이미지 분할 등과 같은 모폴로지(Morphology) 기법을 통해 객체 탐지 정확도를 향상시켰다. 개발된 객체 탐지 알고리즘의 정밀도는 95.19% 이상이었으며, 재현율과 정확도는 각각 95.4%, 93.68% 이상이었다. 객체 탐지 알고리즘의 F1-Score는 0.967 이상으로 나타났다. 본 연구에서 개발한 알고리즘을 이용하여 추출된 배추 객체 중심에 대한 위치 정보는 작물의 재배시기에 따라 영농단계별 의사결정 정보를 제공하기 위한 자료로써 활용될 것이다.

• 제어로봇시스템학회논문지
• /
• 제21권10호
• /
• pp.958-964
• /
• 2015

In this paper, an object recognition method based on the depth information from the RGB-D camera, Xtion, is proposed for an indoor mobile robot. First, the RANdom SAmple Consensus (RANSAC) algorithm is applied to the point cloud obtained from the RGB-D camera to detect and remove the floor points. Next, the removed point cloud is classified by the k-means clustering method as each object's point cloud, and the normal vector of each point is obtained by using the k-d tree search. The obtained normal vectors are classified by the trained multi-layer perceptron as 18 classes and used as features for object recognition. To distinguish an object from another object, the similarity between them is measured by using Levenshtein distance. To verify the effectiveness and feasibility of the proposed object recognition method, the experiments are carried out with several similar boxes.