Real Time Segmentation(实时分割)研究综述
Real Time Segmentation 实时分割 - Further application of the proposed architecture is carried out for real-time segmentation of 8 NASA LANDSAT / ESA satellite images. [1] Without using any pre-trained model, our method achieves state-of-the-art performance among exiting real-time segmentation models on several challenging datasets. [2] Second, analyzing the characteristics of the experimental data and combining with the moving window method, the real-time segmentation and output of the data are carried out, the overall model is simplified and the modeling accuracy and speed are improved. [3] A lightweight semantic segmentation network is proposed to solve the problem of real-time segmentation of blind sidewalk. [4] However, the real-time segmentation of strawberries in an unbridled farming environment is a challenging task due to fruit occlusion by multiple trusses, stems, and leaves. [5] In this paper, we introduce two key modules aimed to design a high-performance decoder for real-time semantic segmentation for reducing the accuracy gap between real-time and non-real-time segmentation networks. [6] EdgeBooster provides real-time segmentation by developing parallel technology that enables segmentation on slices of a camera frame and using presegmentation based on superpixels to accelerate the graph-based segmentation. [7] Our network attained precise real-time segmentation results on Cityscapes, CamVid datasets. [8] Because the existing finger vein segmentation networks are too large and not suitable for implementation in mobile terminals, the reduction of the parameters of the lightweight network leads to the reduction of the segmentation index, and the long-running time of deep network on hardware platforms; this paper proposes a lightweight real-time segmentation method for finger veins based on embedded terminal technique. [9] In this paper, we propose a lightweight real-time segmentation model, named Parallel Complement Network(PCNet), to address the challenging task with fewer parameters. [10] To solve this problem, we propose a multi-branch feature fusion network (MBFFNet), which is an accurate real-time segmentation method for detecting colonoscopy. [11] In this paper, Mask R-CNN, a deep learning detection and segmentation model, is used to extract gait silhouettes and achieve effective and real-time segmentation of human gait silhouettes. [12] This paper proposes a deep learning model for real-time segmentation of heartbeats. [13] In this work, we aim at designing a more efficient and lightweight network without accuracy reduction for real-time segmentation of magnetic resonance images. [14] The empirical mode decomposition method can eliminate the baseline wander caused by the changes in the downhole environment, but it is difficult to achieve real-time segmentation processing due to the influence of the end effect. [15] In this paper, we propose RSCA: a Real-time Segmentation-based Context-Aware model for arbitrary-shaped scene text detection, which sets a strong baseline for scene text detection with two simple yet effective strategies: Local Context-Aware Upsampling and Dynamic TextSpine Labeling, which model local spatial transformation and simplify label assignments separately. [16] However, this metric cannot currently be employed as part of a screening test due to a lack of robust and real-time segmentation tools. [17] Real-time segmentation helps the inspection robot avoid obstacles or land on the wire during the inspection task. [18] Also, the faster segmentation with multi-scaling process accelerates the speed of ensuring real-time segmentation process. [19] In this work, the FASSD-Net model is used as a novel proposal that promises real-time segmentation in high-resolution images exceeding 20 FPS. [20] Real-time segmentation is utilized to measure the fire and smoke boundaries. [21] This paper introduces an index-based improved spatial-temporal big data computing platform, uses adjacent continuous storage technology to improve the data reading performance of the monitoring platform, proposes two models of interest point (POI) matching and adaptive interest point clustering, analyzes the actual use of the vehicle, and then provides a real-time segmentation market identification and segmentation model. [22] However, accurate and real-time segmentation of endoscopic images is extremely challenging due to its high operator dependence and high-definition image quality. [23] This paper designs a simple and efficient end-to-end real-time segmentation algorithm. [24] However, the enormous computational complexity of existing high-precision networks limits the application of the model in real-time segmentation tasks. [25] Finally, our best model tested on Google images demonstrated satisfying promising results on both accuracy scores and losses, which will be the precondition in real-time segmentation. [26] The new features allow to obtain lighter and performing segmentation models, either by shrinking the network size or improving existing networks proposed for real-time segmentation. [27] To address these issues, a lightweight and dual-path deep convolutional architecture, namely Aerial Bilateral Segmentation Network (Aerial-BiSeNet), is proposed to perform real-time segmentation on high-resolution aerial images with favorable accuracy. [28]对 8 个 NASA LANDSAT / ESA 卫星图像的实时分割对所提出的架构进行了进一步的应用。 [1] 在不使用任何预训练模型的情况下，我们的方法在几个具有挑战性的数据集上的现有实时分割模型中实现了最先进的性能。 [2] 其次，分析实验数据的特点，结合移动窗口法，对数据进行实时分割和输出，简化整体模型，提高建模精度和速度。 [3] 针对盲人行道实时分割问题，提出了一种轻量级语义分割网络。 [4] 然而，由于水果被多个桁架、茎和叶遮挡，在肆无忌惮的农业环境中对草莓进行实时分割是一项具有挑战性的任务。 [5] 在本文中，我们介绍了两个关键模块，旨在设计一种用于实时语义分割的高性能解码器，以减少实时和非实时分割网络之间的精度差距。 [6] EdgeBooster 通过开发并行技术来提供实时分割，该技术可以在相机帧的切片上进行分割，并使用基于超像素的预分割来加速基于图形的分割。 [7] 我们的网络在 Cityscapes、CamVid 数据集上获得了精确的实时分割结果。 [8] 由于现有的指静脉分割网络规模过大，不适合在移动端实现，轻量级网络参数的减少导致分割指标降低，深度网络在硬件平台上运行时间过长；提出一种基于嵌入式终端技术的轻量级指静脉实时分割方法。 [9] 在本文中，我们提出了一种轻量级的实时分割模型，称为并行互补网络（PCNet），以解决具有较少参数的具有挑战性的任务。 [10] 为了解决这个问题，我们提出了一种多分支特征融合网络（MBFFNet），这是一种用于检测结肠镜检查的准确实时分割方法。 [11] 本文采用深度学习检测和分割模型Mask R-CNN提取步态轮廓，实现对人体步态轮廓的有效实时分割。 [12] 本文提出了一种用于实时分割心跳的深度学习模型。 [13] 在这项工作中，我们旨在设计一个更高效、更轻量级的网络，而不会降低实时分割磁共振图像的精度。 [14] 经验模态分解法可以消除井下环境变化引起的基线漂移，但受端部效应影响，难以实现实时分割处理。 [15] 在本文中，我们提出了 RSCA：一种基于实时分割的上下文感知模型，用于任意形状的场景文本检测，它通过两种简单而有效的策略为场景文本检测设置了强大的基线：局部上下文感知上采样和动态TextSpine Labeling，对局部空间变换进行建模并分别简化标签分配。 [16] 但是，由于缺乏强大的实时分割工具，该指标目前不能用作筛选测试的一部分。 [17] 实时分割帮助巡检机器人在巡检任务中避开障碍物或落在电线上。 [18] 此外，多尺度过程的更快分割加快了确保实时分割过程的速度。 [19] 在这项工作中，FASSD-Net 模型被用作一种新颖的提议，它承诺在超过 20 FPS 的高分辨率图像中进行实时分割。 [20] 实时分割用于测量火灾和烟雾边界。 [21] 本文介绍了一种基于索引的改进时空大数据计算平台，利用相邻连续存储技术提高监控平台的数据读取性能，提出兴趣点（POI）匹配和自适应兴趣点聚类两种模型，分析实际使用车辆，进而提供实时细分市场识别和细分模型。 [22] 然而，由于其对操作者的高度依赖和高清图像质量，内窥镜图像的准确和实时分割极具挑战性。 [23] 本文设计了一种简单高效的端到端实时分割算法。 [24] 然而，现有高精度网络的巨大计算复杂度限制了该模型在实时分割任务中的应用。 [25] 最后，我们在 Google 图像上测试的最佳模型在准确度得分和损失方面都表现出令人满意的有希望的结果，这将是实时分割的先决条件。 [26] 新功能允许通过缩小网络大小或改进为实时分割提出的现有网络来获得更轻且性能更好的分割模型。 [27] 为了解决这些问题，提出了一种轻量级的双路径深度卷积架构，即航空双边分割网络（Aerial-BiSeNet），以对高分辨率航空图像进行具有良好精度的实时分割。 [28]