• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.107-109
• /
• 2004

In this paper, authors propose the sensor fusion system that can recognize multiple 3D objects from 2D projection images and tactile information. The proposed system focuses on improving recognition performance of 3D object. Unlike the conventional object recognition system that uses image sensor alone, the proposed method uses tactual sensors in addition to visual sensor. Neural network is used to fuse these informations. Tactual signals are obtained from the reaction force by the pressure sensors at the fingertips when unknown objects are grasped by four-fingered robot hand. The experiment evaluates the recognition rate and the number of teaming iterations of various objects. The merits of the proposed systems are not only the high performance of the learning ability but also the reliability of the system with tactual information for recognizing various objects even though visual information has a defect. The experimental results show that the proposed system can improve recognition rate and reduce learning time. These results verify the effectiveness of the proposed sensor fusion system as recognition scheme of 3D object.

• 대한전자공학회논문지
• /
• 제27권6호
• /
• pp.851-860
• /
• 1990

This paper presents a recognition method which interprets 3-D object in terms of several silhouettes of quadtree and octree. Object representation used in object matching should be invariant with respect to locatin and orientation of the object. Generalized octree is projected on to image plane along the principal axes. Regular octree is made from orthogonal directions, but generalized octree is independent to viewing directions. Recognition process is achieved in two-stage matching. The quadtrees and octrees of unknown object with minimum dissimilarities are matched with the quadtrees and octrees of the models. So as to verify efficiency of 3-D object representation and accuracy of object recognition, experiments are performed for 14 different type of geometrical models and its results have been shown.

• 전자공학회논문지C
• /
• 제35C권1호
• /
• pp.55-63
• /
• 1998

This paper presents a new maching algorithm by Hopfield Neural Network for 3-D object recognition. In the proposed method, a model object is represented by a set of polygons in a single coordinate. And each polygon is described by a set of features; feature attributes. In case of 3-D object recognition, the scale and poses of the object are important factors. So we propose a strategy for 3-D object recognition independently to its scale and poses. In this strategy, the respective features of the input or the model objects are changed to the startegical constants when they are compared with one another. Finally, we show that the proposed method has a robustness through the results of experiments which included the classification of the input objects and the matching sequence to its 3-D rotation and scale.

• Journal of the Optical Society of Korea
• /
• 제14권4호
• /
• pp.388-394
• /
• 2010

In this paper the object recognition performance of a photon counting integral imaging system is quantitatively compared with that of a conventional gray scale imaging system. For 3D imaging of objects with a small number of photons, the elemental image set of a 3D scene is obtained using the integral imaging set up. We assume that the elemental image detection follows a Poisson distribution. Computational geometrical ray back propagation algorithm and parametric maximum likelihood estimator are applied to the photon counting elemental image set in order to reconstruct the original 3D scene. To evaluate the photon counting object recognition performance, the normalized correlation peaks between the reconstructed 3D scenes are calculated for the varied and fixed total number of photons in the reconstructed sectional image changing the total number of image channels in the integral imaging system. It is quantitatively illustrated that the recognition performance of the photon counting integral imaging system can be similar to that of a conventional gray scale imaging system as the number of image viewing channels in the photon counting integral imaging (PCII) system is increased up to the threshold point. Also, we present experiments to find the threshold point on the total number of image channels in the PCII system which can guarantee a comparable recognition performance with a gray scale imaging system. To the best of our knowledge, this is the first report on comparisons of object recognition performance with 3D photon counting & gray scale images.

• Journal of the Optical Society of Korea
• /
• 제11권3호
• /
• pp.108-112
• /
• 2007

Spectroscopic ellipsometry (SE) has become an important tool in scatterometry based nano-structure 3D profiling. In this paper, we propose a novel 3D nano object recognition method by use of phase sensitive scatterometry. We claims that only phase sensitive scatterometry can provide a reasonable 3D nano-object recognition capability since phase data gives much higher sensitive 3D information than amplitude data. To show the validity of this approach, first we generate various $0^{th}$ order SE spectrum data ($\psi$ and ${\Delta}$) which can be calculated through rigorous coupled-wave analysis (RCWA) algorithm and then we calculate correlation values between a reference spectrum and an object spectrum which is varied for several different object 3D shape.

• 정보학연구
• /
• 제7권4호
• /
• pp.1-8
• /
• 2004

3차원 영상의 깊이 정보는 3차원 물체를 2차원 스크린에 투사시킴에 의해 손실될 수 있다. 만약 깊이 정보가 재저장되고 3차원 물체 인식을 우해 사용된다면 더 효율적인 인식시스템을 만들 수 있다. 이 정보는 재 저장하기 위하여 스테레오 알고리즘으로부터 형상을 이용한다. 본 논문에서는 3차원 Hough 변환 영역을 3차원 물체 표현에 채택하여 3차원 물체 인식시스템을 제안한다. 본 시스템은 정합 시간 감소를 위하여 물체의 이동 벡터와 미지의 입력 영상을 8진 트리 구조로 이루어진 기준 영상과 비교하여 정합 단계를 이용한다. 8진 트리 구조 코드는 3차원 물체의 형태 기반에 사용되었다. 모의실험 결과 제안된 3차원 물체 인식 시스템은 만족할 수 있는 성능을 보였다.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1493-1503
• /
• 2018

We propose an object recognition system and experiential game contents using Kinect to maximize object recognition rate by utilizing underwater robots. we implement an ice hockey game based on object-aware interactive contents to validate the excellence of the proposed system. The object recognition system, which is a preprocessor module, is composed based on Kinect and OpenCV. Network sockets are utilized for object recognition communications between C/S. The problem of existing research, degradation of object recognition at long distance, is solved by combining the system development method suggested in the study. As a result of the performance evaluation, the underwater robot object recognized all target objects (90.49%) with 80% of accuracy from a 2m distance, revealing 42.46% of F-Measure. From a 2.5m distance, it recognized 82.87% of the target objects with 60.5% of accuracy, showing 34.96% of F-Measure. Finally, it recognized 98.50% of target objects with 59.4% of accuracy from a 3m distance, showing 37.04% of F-measure.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.255-263
• /
• 2022

3D object detection pipelines often incorporate RGB-based object detection methods such as YOLO, which detects the object classes and bounding boxes from the RGB image. However, in complex environments where objects are heavily cluttered, bounding box approaches may show degraded performance due to the overlapping bounding boxes. Mask based methods such as Mask R-CNN can handle such situation better thanks to their detailed object masks, but they require much longer time for data preparation compared to bounding box-based approaches. In this paper, we present a 3D object recognition pipeline which uses either the YOLO or Mask R-CNN real-time object detection algorithm, K-nearest clustering algorithm, mask reduction algorithm and finally Principal Component Analysis (PCA) alg orithm to efficiently detect 3D poses of objects in a complex environment. Furthermore, we also present an improved YOLO based 3D object detection algorithm that uses a prioritized heightmap clustering algorithm to handle overlapping bounding boxes. The suggested algorithms have successfully been used at the Artificial-Intelligence Robot Challenge (ARC) 2021 competition with excellent results.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 C
• /
• pp.1682-1684
• /
• 2000

In this study, 3-D underwater object recognition using ultrasonic sensor fabricated with porous PZT-polymer 3-3 composites and SCL neural networks are presented. The recognition rates for the training data and the testing dara were 100 and 94.6% respectively.

• 전자공학회논문지B
• /
• 제30B권4호
• /
• pp.92-103
• /
• 1993

In this paper, we propose an adaptive classifier based on uncertainty of features for 3D planar object recognition. First, we investigate the uncertainty of depth information and the feature values of 3D planar object by numerical method. And, we observed that the statistical behavior of feature is dependent on the position and orientation of objects. After that, the approximation of the statistical behavior is executed. Subsequently, the recognition procedure is executed by the adaptive classifier. By computer simulation, we confirmed that the proposed classifier is useful for 3D planar object recognition.