Graduate and Research Department, Tecnologico Nacional de Mexico / I.T. Chihuahua, Av. Tecnologico 2909, Chihuahua, 31310, Mexico.
Intel Tecnologia de Mexico, Guadalajara, Mexico.
Cogn Process. 2022 Feb;23(1):27-40. doi: 10.1007/s10339-021-01065-y. Epub 2021 Nov 15.
Scene analysis in video sequences is a complex task for a computer vision system. Several schemes have been addressed in this analysis, such as deep learning networks or traditional image processing methods. However, these methods require thorough training or manual adjustment of parameters to achieve accurate results. Therefore, it is necessary to develop novel methods to analyze the scenario information in video sequences. For this reason, this paper proposes a method for object segmentation in video sequences inspired by the structural layers of the visual cortex. The method is called Neuro-Inspired Object Segmentation, SegNI. SegNI has a hierarchical architecture that analyzes object features such as edges, color, and motion to generate regions that represent the objects in the scenario. The results obtained with the Video Segmentation Benchmark VSB100 dataset demonstrate that SegNI can adapt automatically to videos with scenarios that have different nature, composition, and different types of objects. Also, SegNI adapts its processing to new scenario conditions without training, which is a significant advantage over deep learning networks.
视频序列中的场景分析对于计算机视觉系统来说是一项复杂的任务。在该分析中已经提出了几种方案，例如深度学习网络或传统图像处理方法。然而，这些方法需要彻底的培训或手动调整参数才能获得准确的结果。因此，有必要开发新的方法来分析视频序列中的场景信息。为此，本文提出了一种受视觉皮层结构层启发的视频序列中的目标分割方法。该方法称为神经启发式对象分割，SegNI。SegNI 具有分层架构，可分析边缘、颜色和运动等对象特征，以生成代表场景中对象的区域。在 Video Segmentation Benchmark VSB100 数据集上获得的结果表明，SegNI 可以自动适应具有不同性质、组成和不同类型对象的视频。此外，SegNI 无需训练即可适应新的场景条件，这是优于深度学习网络的一个显著优势。
