GPU-Based Supervoxel Generation With a Novel Anisotropic Metric
GPU-Based Supervoxel Generation With a Novel Anisotropic Metric
复制标题
DOI：
10.1109/tip.2021.3120878
复制
发表时间：
2021-10
影响因子：
10.6
通讯作者：
Xiaopan Dong;Zhonggui Chen;Yong-Jin Liu;Junfeng Yao;Xiaohu Guo
中科院分区：
文献类型：
--
作者：
Xiaopan Dong;Zhonggui Chen;Yong-Jin Liu;Junfeng Yao;Xiaohu Guo
视频过分割成超体素是许多计算机视觉任务的重要预处理技术。视频比图像大一个数量级。大多数现有的生成超级电平的方法要么是内存效率低，要么是时间效率低，这限制了它们在后续视频处理任务中的应用。在本文中，我们提出了一种各向异性的超体素方法，它可以在图形处理单元（GPU）上执行，并且具有内存效率。因此，我们的算法在分割质量、内存使用和处理时间之间取得了很好的平衡。为了对视频中的运动物体进行精确分割，我们利用光流信息设计了一种全新的非欧几里得度量来计算种子和体素之间的各向异性距离。为了有效地计算各向异性度量，我们调整了经典的跳跃泛洪算法（设计用于在GPU上并行执行），在组合的颜色和时空空间中生成各向异性Voronoi镶嵌。我们从分割性能、计算速度和内存效率三个方面评价了我们的方法和代表性的超体素算法。我们还将超体素结果应用于前景传播在视频中的应用，以测试其在解决实际问题时的性能。实验表明，该算法的分割速度比现有方法快得多，在分割质量和分割效率上取得了很好的平衡。
Video over-segmentation into supervoxels is an important pre-processing technique for many computer vision tasks. Videos are an order of magnitude larger than images. Most existing methods for generating supervovels are either memory- or time-inefficient, which limits their application in subsequent video processing tasks. In this paper, we present an anisotropic supervoxel method, which is memory-efficient and can be executed on the graphics processing unit (GPU). Therefore, our algorithm achieves good balance among segmentation quality, memory usage and processing time. In order to provide accurate segmentation for moving objects in video, we use the optical flow information to design a brand new non-Euclidean metric to calculate the anisotropic distances between seeds and voxels. To efficiently compute the anisotropic metric, we adjust the classic jump flooding algorithm (which is designed for parallel execution on the GPU) to generate anisotropic Voronoi tessellation in the combined color and spatio-temporal space. We evaluate our method and the representative supervoxel algorithms for their capability on segmentation performance, computation speed and memory efficiency. We also apply supervoxel results to the application of foreground propagation in videos to test the performance on solving practical problems. Experiments show that our algorithm is much faster than the existing methods, and achieves good balance on segmentation quality and efficiency.