• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.335-347
• /
• 2024

Open-vocabulary 3D point cloud instance segmentation (OV-3DIS) is a challenging visual task to segment a 3D scene point cloud into object instances of both base and novel classes. In this paper, we propose a novel model Open3DME for OV-3DIS to address important design issues and overcome limitations of the existing approaches. First, in order to improve the quality of class-agnostic 3D masks, our model makes use of T3DIS, an advanced Transformer-based 3D point cloud instance segmentation model, as mask proposal module. Second, in order to obtain semantically text-aligned visual features of each point cloud segment, our model extracts both 2D and 3D features from the point cloud and the corresponding multi-view RGB images by using pretrained CLIP and OpenSeg encoders respectively. Last, to effectively make use of both 2D and 3D visual features of each point cloud segment during label assignment, our model adopts a unique feature ensemble method. To validate our model, we conducted both quantitative and qualitative experiments on ScanNet-V2 benchmark dataset, demonstrating significant performance gains.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.542-551
• /
• 2000

In this paper, a novel technique is presented for automatic brain region segmentation in single channel MR image data sets for 3D visualization and analysis. The method detects brain contours in 2D and 3D processing of four steps. The first and the second make a head mask and an initial brain mask by automatic thresholding using a curve fitting technique. The stage 3 reconstructs 3D volume of the initial brain mask by cubic interpolation and generates an intermediate brain mask using morphological operation and labeling of connected components. In the final step, the brain mask is refined by automatic thresholding using curve fitting. This algorithm is useful for fully automatic brain region segmentation of T1-weighted, T2-weighted, PD-weighted, SPGR MRI data sets without considering slice direction and covering a whole volume of a brain. In the experiments, the algorithm was applied to 20 sets of MR images and showed over 0.97 in comparison with manual drawing in similarity index.

• Journal of Biomedical Engineering Research
• /
• v.21 no.2
• /
• pp.145-156
• /
• 2000

본 논문에서는 중앙시상 두뇌 자기공명영상 분할결과를 이용한 3차원 시상 두뇌 자기공명영상의 자동분할기법을 제안한다. 제안된 알고리즘에서는 먼저 3차원 시상 두뇌 자기공명영상의 중앙영상을 분할하고, 분할된 중앙두뇌 자기공명영상을 인접하는 영상에 마스크로 적용한다. 이 때 마스크 적용으로 인하여 인접하는 영상이 절단되는 문제가 발생할 수 있다. 이러한 문제를 해결하기 위하여 절단 영역의 경계점을 검출한 후, 절단 영역에 대한 경로 재설정을 통해 절단 영역을 복원한다. 이러한 경로 재설정을 위해 connectivity-based threshold segmentation algorithm을 사용하였다. 실험결과 제안된 알고리즘의 유용성을 확인할 수 있었다.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.691-702
• /
• 2004

In this paper, we propose a sequence of method which extrats ROIs(Region of Interests) rapidly from the parcel image of large size. In the proposed method, original image is spilt into the small masks, and the meaningful masks, the ROIs, are extracted by two criterions sequentially The first criterion is difference of pixel value between Inner points, and the second is deviation of it. After processing, some informational ROIs-the areas of bar code, characters, label and the outline of object-are acquired. Using diagonal axis of each ROI and the feature of various 2D bar code, the area of 2D bar code can be extracted from the ROIs. From an experiment using above methods, various ROIs are extracted less than 200msec from large-size parcel image, and 2D bar code region is selected by the accuracy of 100％.

• Journal of Broadcast Engineering
• /
• v.7 no.3
• /
• pp.248-261
• /
• 2002

In this paper, we proposed a new 3-dimensional(3-D) object-tracking algorithm that can control a stereo camera using a variable window mask supported by which uses ,B-D information and an optical BPEJTC. Hence, three-dimensional information characteristics of a stereo vision system, distance information from the stereo camera to the tracking object. can be easily acquired through the elements of a stereo vision system. and with this information, we can extract an area of the tracking object by varying window masks. This extractive area of the tracking object is used as the next updated reference image. furthermore, by carrying out an optical BPEJTC between a reference image and a stereo input image the coordinates of the tracking objects location can be acquired, and with this value a 3-D object tracking can be accomplished through manipulation of the convergence angie and a pan/tilt of a stereo camera. From the experimental results, the proposed algorithm was found to be able to the execute 3-D object tracking by extracting the area of the target object from an input image that is independent of the background noise in the stereo input image. Moreover a possible implementation of a 3-D tele-working or an adaptive 3-D object tracker, using the proposed algorithm is suggested.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.310-312
• /
• 2003

본 논문은 3차원 얼굴 형상을 이용한 얼굴 인식에 있어서, 정규화 과정에 사용될 얼굴의 특징 영역을 추출하는 방법을 제안한다. 3차원 얼굴 형상은 조명의 변화에 상관없이 얼굴의 특징 분석이 가능하고, 이를 이용한 얼굴 인식이 가능하다. 그러나, 입력된 형상에 따라 회전, 기울어진 정도, 그리고 좌우로 움직인 정도가 다르다 이런 특성을 고려하지 않고 추출된 특징들은 잘못된 인식 결과를 초래할 수 있다. 이런 이유로 입력시의 오류 돌을 바로잡는 정규화 과정이 필요하다. 정규화 과정에서는 얼굴의 기하학적인 특징(눈, 코, 입 등)을 이용하는 것이 일반적이다. 이들 중, 코는 3차원 얼굴 형상에서 두드러진 특징이 될 수 있다. 본 연구에서는 코의 실제 형상과 유사한 코 형상 추출 마스크를 사용하여 입력된 형상으로부터 코 영역을 추출하는 방법을 제안한다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.10
• /
• pp.146-153
• /
• 1990

A new 3-D segmentation-based coding technique is proposed for transmitting the motion video with reasonablly acceptable quality even at a very low bit rate. Only meaningful motion areas are extracted by using two change detection masks and a current frame is directly segmented rather than a difference frame itself so that a good quality of image can be obtained at high compression ratios. Through the experiments, the sequence of Miss America is reconstructed with visually acceptable quality at the very high compression ratio of 360:1.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.1-7
• /
• 2004

This paper proposes a new method for facial feature extraction, and the method could be used to normalize face images for 3D face recognition. 3D images are much less sensitive than intensity images at a source of illumination, so it is possible to recognize people individually. But input face images may have variable poses such as rotating, Panning, and tilting. If these variances ire not considered, incorrect features could be extracted. And then, face recognition system result in bad matching. So it is necessary to normalize an input image in size and orientation. It is general to use geometrical facial features such as nose, eyes, and mouth in face image normalization steps. In particular, nose is the most prominent feature in 3D face image. So this paper describes a nose feature extraction method using 3D nasal masks that are similar to real nasal shape.

• The Journal of the Korea Contents Association
• /
• v.2 no.3
• /
• pp.1-15
• /
• 2002

A noel automated brain region extraction method in single channel MR images for visualization and analysis of a human brain is presented. The method generates a volume of brain masks by automatic thresholding using a dual curve fitting technique and by 3D morphological operations. The dual curve fitting can reduce an error in clue fitting to the histogram of MR images. The 3D morphological operations, including erosion, labeling of connected-components, max-feature operation, and dilation, are applied to the cubic volume of masks reconstructed from the thresholded Drain masks. This method can automatically extract a brain region in any displayed type of sequences, including extreme slices, of SPGR, T1-, T2-, and PD-weighted MR image data sets which are not required to contain the entire brain. In the experiments, the algorithm was applied to 20 sets of MR images and showed over 0.97 of similarity index in comparison with manual drawing.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1891-1894
• /
• 2003

본 논문에서는 분할 영상 좌보계 (split image coordinate: SIC)를 제안하여 3차원 영상의 주요 특징 중의 하나인 유, 무한 소실점을 그 위치의 무한성이나 카메라의 보정과 관계없이 정확하게 자동 추출하였다. 제안한 방법에서는 가우시안 구 (Gaussian sphere) 기반의 기존 방법들과는 달리 영상 공간을 누적 공간으로 활용함으로써 카메라 보정이나 영상의 사전정보가 없어도 원 영상의 정보 손실 없이 소실점을 추출할 수 있고, 영상을 무한대까지 확장한 후 분할하여 재정의 함으로써 유, 무한 소실점을 모두 추출할 수 있도록 하였다. 정확한 소실점의 검출을 위하여 직선 검출 과정에서는 방향성 마스크 (mask)를 사용하였으며, 직선들의 군집화 (clustering) 과정에서는 기울기 히스토그램 방법과 수평/수직 군집화 방법을 적응적으로 적용하였다. 제안한 방법을 합성 영상 및 건축물 (man-made environment) 영상에 적용시켜 유, 무한 소실점들을 효과적이고 정확하게 찾을 수 있음을 확인하였다.