• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.2C
• /
• pp.147-161
• /
• 2003

Video object segmentation is one of the core technologies for content-based real-time MPEG-4 encoding system. For real-time requirement, the segmentation algorithm should be fast and accurate but almost all existing algorithms are computationally intensive and not suitable for real-time applications. The MPEG-4 VM(Verification Model) has provided basic algorithms for MPEG-4 encoding but it has many limitations in practical software development, real-time camera input system and compression efficiency. In this paper, we implemented the preprocessing system for real-time camera input and VOP extraction for content-based video coding and also implemented motion detection to achieve the 180 : 1 compression rate for real-time and high compression MPEG-4 encoding.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2483-2494
• /
• 2024

Instance segmentation is a challenging research in the field of computer vision, which combines the prediction results of object detection and semantic segmentation to provide richer image feature information. Focusing on the instance segmentation in the street scene, the real-time instance segmentation method based on SOLOv2 is proposed in this paper. First, a cross-stage fusion backbone network based on position attention is designed to increase the model accuracy and reduce the computational effort. Then, the loss of shallow location information is decreased by integrating two-way feature pyramid networks. Meanwhile, cross-stage mask feature fusion is designed to resolve the small objects missed segmentation. Finally, the adaptive minimum loss matching method is proposed to decrease the loss of segmentation accuracy due to object occlusion in the image. Compared with other mainstream methods, our method meets the real-time segmentation requirements and achieves competitive performance in segmentation accuracy.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.482-483
• /
• 2024

Real-time Point Cloud Ground Segmentation은 자율주행에서 판단 및 객체 탐지/추적 등 다양한 분야에 도움을 준다. 이에 따라, Real-time Point Cloud Ground Segmentation을 했으며, 센서로는 라이다, 알고리즘으로는 TRAVEL논문을 인용했다. 또한 Real-time Point Cloud Ground Segmentation뿐 만 아니라 이동가능지형 판단(Traversability)을 하였다. 그리고 최종적으로, 위와 같은 알고리즘들을 회사 로봇(Scout Mini Robot)에 접목시켰으며 그 과정에서 TRAVEL 알고리즘내에 내제된 파라미터 값들을 최적화시키는 과정이 필요하였다. 그래서 3가지의 방법을 통해 파라미터 값을 선정한 후, 결과값을 비교 분석하였다. 연구 결과, Rellis-3D와 베이지안 최적화를 사용한 베이지안 파라미터가 최적의 파라미터임을 확인할 수 있었다.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1986.10a
• /
• pp.186-190
• /
• 1986

This paper describes a way of implementing the segmentation of 128*128 pixel images to be used as the inputs. to a real-time automatic video tracker. The suggested method uses the lowest valley-value of the computed intensity historgram with 16 levels. This method improves smoothing effects and also significantly reduces hardware requirements. Entire segmentation process is caried out in 10msec thus making a real time application possible.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.670-673
• /
• 2002

This paper proposes a digital algorithm for gray-scale/color image segmentation of real-time video signals and a cell-network-based implementation architecture in state-of-the-art CMOS technology. Through extrapolation of design and simulation results we predict that about 300$\times$300 pixels can be integrated on a chip at 100nm CMOS technology, realizing very high-speed segmentation at about 1600sec per color image. Consequently real-time color-video segmentation will become possible in near future.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.51-56
• /
• 2022

This paper presents an Ground Segmentation algorithm to eliminate unnecessary Lidar Point Cloud Data (PCD) in an autonomous driving system. We consider Random Sample Consensus (Ransac) Algorithm to process lidar ground data. Ransac designates inlier and outlier to erase ground point cloud and classified PCD into two parts. Test results show removal of PCD from ground area by distinguishing inlier and outlier. The paper validates ground rejection algorithm in real time calculating the number of objects recognized by ground data compared to lidar raw data and ground segmented data based on the z-axis. Ground Segmentation is simulated by Robot Operating System (ROS) and an analysis of autonomous driving data is constructed by Matlab. The proposed algorithm can enhance performance of autonomous driving as misrecognizing circumstances are reduced.

• Clinical Endoscopy
• /
• v.55 no.3
• /
• pp.390-400
• /
• 2022

Background/Aims: Previous artificial intelligence (AI) models attempting to segment gastric intestinal metaplasia (GIM) areas have failed to be deployed in real-time endoscopy due to their slow inference speeds. Here, we propose a new GIM segmentation AI model with inference speeds faster than 25 frames per second that maintains a high level of accuracy. Methods: Investigators from Chulalongkorn University obtained 802 histological-proven GIM images for AI model training. Four strategies were proposed to improve the model accuracy. First, transfer learning was employed to the public colon datasets. Second, an image preprocessing technique contrast-limited adaptive histogram equalization was employed to produce clearer GIM areas. Third, data augmentation was applied for a more robust model. Lastly, the bilateral segmentation network model was applied to segment GIM areas in real time. The results were analyzed using different validity values. Results: From the internal test, our AI model achieved an inference speed of 31.53 frames per second. GIM detection showed sensitivity, specificity, positive predictive, negative predictive, accuracy, and mean intersection over union in GIM segmentation values of 93%, 80%, 82%, 92%, 87%, and 57%, respectively. Conclusions: The bilateral segmentation network combined with transfer learning, contrast-limited adaptive histogram equalization, and data augmentation can provide high sensitivity and good accuracy for GIM detection and segmentation.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.173-180
• /
• 2011

This paper shows an approach for real-time object segmentation on GPU (Graphics Processing Unit) using CUDA (Compute Unified Device Architecture). Recently, many applications that is monitoring system, motion analysis, object tracking or etc require real-time processing. It is not suitable for object segmentation to procedure real-time in CPU. NVIDIA provide CUDA platform for Parallel Processing for General Computation to upgrade limit of Hardware Graphic. In this paper, we use adaptive Gaussian Mixture Background Modeling in the step of object extraction and CCL(Connected Component Labeling) for classification. The speed of GPU and CPU is compared and evaluated with implementation in Core2 Quad processor with 2.4GHz.The GPU version achieved a speedup of 3x-4x over the CPU version.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1C
• /
• pp.92-101
• /
• 2004

This paper proposes a algorithm to extract the variety region (object) from video for the real-time encoding of MPEG-4 based. The previous object segmentation methods cannot used the videophone or videoconference required by real-time processing. It is difficult to transfer a video to real-time because it increased complexity for the operation of each pixel on the spatial segmentation and temporal segmentation method proposed by MPEG-4 Working Group. But algorithm proposed for this thesis not operates a pixel unit but operates a macro block unit. Thus this enables real-time transfer. But this algorithm cannot extract several object for a image using proposed algorithm as previous algorithm. On system constructed by encoder and decoder. A proposed algorithm inserted for encoder as pre-process.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.1-8
• /
• 2023

In this paper, we propose a black ice detection platform framework using Convolutional Neural Networks (CNNs). To overcome black ice problem, we introduce a real-time based early warning platform using CNN-based architecture, and furthermore, in order to enhance the accuracy of black ice detection, we apply a multi-scale dilation convolution feature fusion (MsDC-FF) technique. Then, we establish a specialized experimental platform by using a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Experimental results of a real-time black ice detection platform show the better performance of our proposed network model compared to conventional image segmentation models. Our proposed platform have achieved real-time segmentation of road black ice areas by deploying a road black ice area segmentation network on the edge device Jetson Nano devices. This approach in parallel using multi-scale dilated convolutions with different dilation rates had faster segmentation speeds due to its smaller model parameters. The proposed MsCD-FF Net(2) model had the fastest segmentation speed at 5.53 frame per second (FPS). Thereby encouraging safe driving for motorists and providing decision support for road surface management in the road traffic monitoring department.