Earticle

본 논문에서는 단일 프레임 영상에 존재하는 객체를 Active Contour 기반의 영 역 분할 과정을 거쳐 분할하 였다. Active Contour는 영상에서 객체의 윤곽 형태를 검출해내는 것으로 다중 객체 분할을 위해 각 객체의 윤곽 형 태를 검출해 낼 수 있도록 다중 탐색 시작점을 갖도록 하였다. 생성된 객체 별 윤곽 정보를 기반으로 이진화하여 초 기 객체 영역을 생성하였다. 초기 객체 영역 내부의 홀 영역과 픽셀 값의 변화로 인한 내부 분할을 hole filling을 수 행하여 보정함으로써 최종 객체 영역을 생성하였다. 제안한 기법은 기존 영역 기반 분할의 문제점인 잡음이나 경계선 부근에서 객체 분할이 정확히 이루어지지 않는 부분을 보완하였다. 제안 방법을 비교하기 위해 실제 영상에 기존에 제안된 객체 분할 방법과 제안한 방법을 각각 적용하여 비교하였다.

This paper presents the technique separating objects on the single frame image from the background using region segmentation technique based on active contour. Active contour is to extract contours of objects from the image, which is set to have multi-search starting point to extract each objects contours for multi-object segmentation. Initial rough object segments are generated from binary-coded image using object specific contour information, and then the hole filling is performed to compensate internal segmentation caused by the change of inner object hole area and pixels. This procedure complements the problems caused by the noise from the region segmentation and the errors of segmentation near by the contour. The proposed method and conventional method is compared to verify the superiority of the proposed method.

본 논문에서는 단일 프레임 영상에서 초점을 이용하여 초기 깊이정보를 추출한 후 입체 영상을 생성하는 방법을 제안하였다. 단일 프레임 영상에서 깊이를 추정하기 위해 원본 영상과 가우시안 필터를 중첩 적용하여 생성된 영상의 비교를 통해 영상의 초점 값을 추출하고 추출된 값을 기반으로 초기 깊이정보를 생성하도록 하였다. 생성된 초기 깊이정보를 Normalized cut을 이용한 객체 분할 결과에 할당하고 각 객체의 깊이를 객체 내 깊이 정보의 평균값으로 보정하여 동일 객체가 같은 깊이 값을 갖도록 하였다. 객체를 제외한 배경 영역은 객체를 제외한 배경 영역의 에지 정보를 이용하여 깊이를 생성하였다. 생성된 깊이를 DIBR(Depth Image Based Rendering)을 이용하여 입체 영상으로 변환하였고 기존 알고리즘을 통해 생성된 영상과 비교 분석하였다.

In this paper we present creating 3D image from 2D image by extract initial depth values calculated from focal values. The initial depth values are created by using the extracted focal information, which is calculated by the comparison of original image and Gaussian filtered image. This initial depth information is allocated to the object segments obtained from normalized cut technique. Then the depth of the objects are corrected to the average of depth values in the objects so that the single object can have the same depth. The generated depth is used to convert to 3D image using DIBR(Depth Image Based Rendering) and the generated 3D image is compared to the images generated by other techniques.

As the number of single-person households increases in South Korea, there is a growing demand for more personalized and space-efficient interior design, particularly among the MZ generation who value individuality. Recently, AI-powered services are being developed for efficient interior design. These services utilize indoor photographs to create digital twin-based 3D interior design programs. However, the quality of service varies significantly depending on the algorithm used. In response to this challenge, this study compares and analyzes the image segmentation performance of Grounded SAM and FastSAM, both derived from the Segment Anything Model (SAM) announced by Meta in early 2023. The ADE20K dataset, related to interior design, and the DAVIS2016 dataset, which focuses on single-object segmentation, were used to evaluate the accuracy and processing speed of the two models and to explore their applicability in real-world interior design workflows. The experimental results shows that Grounded SAM outperforms FastSAM in terms of object recognition accuracy. This research will offer valuable criteria for model selection in the automation of interior design and the development of AR/VR applications.

의미있는 객체를 배경과 분리하는 영상분할기법은 침입자 경보 시스템, 교통 감시 시스템 등에서 중요한 역할을 담당하며, 일반적으로 공간적 동질성이나 시간적 정보를 이용하는 방법으로 나눌 수 있다. 시간적 정보를 이용하는 방법은 프레임간의 화소값이나 에지성분을 이용한다. 화소값 이용은 간단하며 효과적이나 조명 변화 등이 발생할 경우 움직임 검출이 어렵고 에지성분의 이용은 조명의 영향을 받지 않지만 복잡하며 잡음처리에 어려운 점이 있다. 따라서 본 논문은 카메라가 고정된 감시 시스템에서 화소값 비교와 에지 정보를 이용하여 조명 등의 영향을 최소화하는 움직임 객체 추출 방법을 제안한다. 이는 조명변화와 배경영상의 존재여부에 따라 세 가지 움직임 객체 추출 방법을 달리 적용하며, 투영과 형태 처리 연산자를 사용하는 후처리 과정을 거친 후 움직임 객체를 추출한다. 모의실험 결과 제안알고리즘은 조명변화가 발생하더라도 객체 추출의 결과가 우수함을 보이고 있다.

Surveillance system with the fixed field of view generally has an identical background and is easy to extract and segment a moving object. However, it is difficult to extract the object when the gray level of the background is varied due to illumination condition in the real circumstance. In this paper we propose the segmentation to extract effectively the object in spite of the illumination change. In order to minimize the effect of illumination, the proposed algorithm is composed of three modes to the background generation and the illuminational change. Then the object is finally obtained by using projection and the morphological operator in post-processing. A good seg-mentation performance is demonstrated by the simulation result.

This paper presents a hybrid content-based video coding scheme that encodes arbitrary shaped objects instead of blocks of images. The scheme achieves efficient compression for low bit-rate applications by separating moving objects from stationary background and transmitting the shape, motion and residuals for each segmented object. Furthermore, a new content-based object segmentation algorithm is proposed in the scheme, which does not assume any prior modeling of the objects being segmented. The algorithm is based on a threshold function that calculates block histograms and takes image noise into account. The experimental results show that the scheme proposed outperforms the classical object-based coding methods in terms of PSNR or the average number of bits required for coding a single frame.

In this paper, we propose a novel method for automatic object segmentation using Mean shift with Grid-mask for Grab Cut algorithm. The main idea of proposed method is a rapid and exact technique for extracting initial foreground information using Mean shift with Grid-mask then we make initial rectangle around estimated initial foreground. And then Grab Cut algorithm is applied to segment foreground form background based on initial rectangle provided by previous process. In order to evaluate our proposed method, we compare the proposed method with several competitive automatic methods on the MSRA database which has 1000 images with ground truth. The scheme successfully segments objects without prior knowledge with both higher precision and better recall than competitive methods.

A multiple moving object segmentation algorithm based on Background Modeling and Adaptive Clustering (named as BMAC) algorithm is proposed in this paper. For moving object segmentation, the algorithm uses Chebyshev inequality and the kernel density estimation method to do background modeling firstly. Then in order to classify image pixels as background points, foreground points and suspicious points, an adaptive threshold algorithm is proposed accordingly. After using background modeling, adaptive clustering is used for multi-object segmentation. It defines pixel space connectivity rate and designs a perpendicular split method, initial cluster adaptive splitting and merging self-organizing the iterative clustering segmentation algorithm, without pre-set number of clustering, completes multi-object segmentation for the foreground image. The segmentation results are consistent with the human visual judgment, the use of space connectivity information improve the accuracy of clustering segmentation, comparison and analysis the experimental results show that the proposed algorithm is feasible, rapid and effective.

A novel framework for highly dynamic scene segmentation through foreground hypothesis is developed here. This framework enables robust foreground segmentation by ranking object hypothesis over spatial space to achieve consistent object candidates and binary segmentation of a video sequence. Inside object candidates derived from spatial features in each frame are first estimated. This is followed by ranking the object candidates over a specific hypothesis space so as to yield consistent and dense object proposals. An efficient higher-order graph-cut method is adapted to optimize a Markov Random Field (MRF) model, which is instantiated by the estimated foreground hypothesis with highest score. We demonstrate the performance of our approach through experimental evaluation on a typical dynamic scene benchmark from Freiburg-Berkeley Motion Segmentation Dataset. Compared with a state-of-the-art algorithm, our method achieves improved and robust segmentation performance when dealing with highly dynamic image sequences. The segmentation accuracy of the proposed method improved by 10.19% and 92.66% pixels are correctly classified.

This study addresses the issue of apple detection and segmentation, which plays a crucial role in agricultural automation systems, by employing multi-object detection using machine learning. A Support Vector Machine (SVM) model was used to accurately distinguish apples from leaves, with apple pixels classified as red and leaf pixels as green. The performance of the SVM model was evaluated using various metrics. Key evaluation metrics included IoU (Intersection over Union), Precision, Recall, and mAP (mean Average Precision). The results showed an IoU of 0.48, a Precision of 0.51, a Recall of 0.90, and an mAP of 0.48. Consequently, the SVM model exhibited a high recall rate, successfully detecting most apples, but also had a high false-positive rate due to its low precision. In the future, the need for models that can simultaneously handle real-time processing and accurate boundary recognition is emerging, which could address a critical issue in agricultural automation systems.

In this paper, we proposed an automatic segmentation method of object color images with irregular texture. Recently segmentation often used for the image retrieval and in the application. It is more important to approximate the regions than to decide precise region boundary. A color image is divided into blocks, and edge strength for each block is computed by using the modified color histogram intersection method that has been developed to differentiate object boundaries from irregular texture boundaries effectively. The edge strength is defined to have high values at the object boundaries, while it is designed to have relatively low values at the texture boundaries or in the interior of a region. The proposed method works based on small-size blocks, the color histogram of each of which is computed preliminarily once. Thus it works fast but provides rough segmentation. A hybrid color quantization method is used to select a small number of appropriately quantized colors quickly. The proposed method can be applicable for the segmentation in object based image retrieval.

Texture segmentation is the process of partitioning an image into regions with different textures containing similar group of pixels. Texture is an important spatial feature, useful for identifying object or region of interest. In texture analysis the foremost task is to extract texture features, which efficiently embody the information about the textural characteristics of the image. This can be used for the segmentation of different textured images. This paper presents a new approach for color texture segmentation using Haralick’s features extracted from color co-occurrence matrices. The originality of this approach is to select the most discriminating color texture features extracted from the color co-occurrence. Symbolic Object Approach is used for achieving texture segmentation.

High-precision 3D Object Detection is a crucial component within autonomous driving systems, with far-reaching implications for subsequent tasks like multi-object tracking and path planning. In this paper, we propose a novel approach designed to enhance the performance of 3D Object Detection, especially in heading angle estimation by employing a moving object segmentation technique. Our method starts with extracting point-wise moving labels via a process of moving object segmentation. Subsequently, these labels are integrated into the LiDAR Pointcloud data and integrated data is used as inputs for 3D Object Detection. We conducted an extensive evaluation of our approach using the KITTI-road dataset and achieved notably superior performance, particularly in terms of AOS, a pivotal metric for assessing the precision of 3D Object Detection. Our findings not only underscore the positive impact of our proposed method on the advancement of detection performance in lidar-based 3D Object Detection methods, but also suggest substantial potential in augmenting the overall perception task capabilities of autonomous driving systems.

비디오에서 움직이는 객체의 외곽선은 객체를 정확하게 분할하기 위하여 매우 중요하다. 그러나 움직이는 객체의 외곽선에는 단락된 외곽선들이 존재하게 된다. 우리는 단락된 외곽선을 연결할 수 있는 새로운 외곽선 연결 알고리즘을 개발하였다. 외곽선 연결 알고리즘은 단락된 외곽선의 말단 픽셀에 사분면을 형성하고 동심원을 구성하면서 반지름 내에서 다른 말단 픽셀을 찾는 탐색을 전진하면서 수행한다. 외곽선 연결 알고리즘은 객체의 외곽선에서 가장 짧게 외곽선을 연결한다. 그리고 시스템은 비디오로부터 배경을 구하여 저장한다. 시스템은 외곽선 연결로부터 객체 마스크를 생성하고, 배경된 저장으로부터 또 하나의 객체 마스크를 생성하여 이 두 개의 객체 마스크를 보완적으로 사용하여 움직이는 객체를 분할한다. 논문의 주요 장점은 정확한 객체 분할을 위한 새로운 객체 외곽선 연결 알고리즘의 개발이다. 제안된 알고리즘은 개발된 새로운 객체 외곽선 연결 알고리즘과 배경 저장을 이용하여 정확한 객체 분할, 다중 객체 분할, 내부에 구멍이 존재하는 객체의 분할, 가느다란 객체의 분할, 그리고 복잡한 배경을 가진 객체를 자동으로 분할하여 보여주었다. 우리는 알고리즘들을 표준 MPEG-4 실험 영상과 카메라로 입력된 실제 영상을 가지고 실험하였다. 제안된 알고리즘들은 매우 효율이 좋으며 펜티엄-IV 3.4GHz CPU에서 평균적으로 QCIF 영상을 1초당 70.20 프레임 그리고 CIF 영상을 1초당 19.7 프레임을 실시간 객체 응용을 위하여 처리할 수 있다.

Moving object boundary is very important for the accurate segmentation of moving object. We extract the moving object boundary from the moving object edge. But the object boundary shows broken boundaries so we develop a novel boundary linking algorithm to link the broken boundaries. The boundary linking algorithm forms a quadrant around the terminating pixel in the broken boundaries and searches for other terminating pixels to link in concentric circles clockwise within a search radius in the forward direction. The boundary linking algorithm guarantees the shortest distance linking. We register the background from the image sequence using the stationary background filtering. We construct two object masks, one object mask from the boundary linking and the other object mask from the initial moving object, and use these two complementary object masks to segment the moving objects. The main contribution of the proposed algorithms is the development of the novel object boundary linking algorithm for the accurate segmentation. We achieve the accurate segmentation of moving object, the segmentation of multiple moving objects, the segmentation of the object which has a hole within the object, the segmentation of thin objects, and the segmentation of moving objects in the complex background using the novel object boundary linking and the background automatically. We experiment the algorithms using standard MPEG-4 test video sequences and real video sequences of indoor and outdoor environments. The proposed algorithms are efficient and can process 70.20 QCIF frames per second and 19.7 CIF frames per second on the average on a Pentium-IV 3.4GHz personal computer for real-time object-based processing.

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.

Foreground estimation in object segmentation has been an important issue for last few decades. In this paper we propose a GrabCut based automatic foreground estimation method using block clustering. GrabCut is one of popular algorithms for image segmentation in 2D image. However GrabCut is semi-automatic algorithm. So it requires the user input a rough boundary for foreground and background. Typically, the user draws a rectangle around the object of interest manually. The goal of proposed method is to generate an initial rectangle automatically. In order to create initial rectangle, we use Gabor filter and Saliency map and then we use 4 features (amount of area, variance, amount of class with boundary area, amount of class with saliency map) to categorize foreground and background. From the experimental results, our proposed algorithm can achieve satisfactory accuracy in object segmentation without any prior information by the user.

We have proposed a method to detect and track moving ships using position from Radar and image processor. Real-time segmentation of moving regions in image sequences is a fundamental step in the radar-camera integrated system. Algorithms for segmentation of objects are implemented by composing of background subtraction, morphologic operation, connected components labeling, region growing, and minimum enclosing rectangle. Once the moving objects are detected, tracking is only performed upon pixels labeled as foreground with reduced additional computational burdens.

This paper represents an efficient algorithm to segment objects from the background using multiple images of distinct luminous intensities. The proposed algorithm obtains images with different luminous intensities using a camera flash. From the multiple intensities for a pixel, a saturated luminous intensity is estimated together with the slope of intensity rate. Then, we measure the sensitivities of pixels from their slopes. The sensitivities show different patterns according to the distances from the light source. Therefore, the proposed algorithm segments near objects using the sensitivity information by minimizing an energy function. Experimental results on various objects show that the proposed algorithm provides accurate results without any user interaction.