Sabokrou Mohammad, Fayyaz Mohsen, Fathy Mahmood, Klette Reinhard
IEEE Trans Image Process. 2017 Apr;26(4):1992-2004. doi: 10.1109/TIP.2017.2670780. Epub 2017 Feb 17.
This paper proposes a fast and reliable method for anomaly detection and localization in video data showing crowded scenes. Time-efficient anomaly localization is an ongoing challenge and subject of this paper. We propose a cubicpatch- based method, characterised by a cascade of classifiers, which makes use of an advanced feature-learning approach. Our cascade of classifiers has two main stages. First, a light but deep 3D auto-encoder is used for early identification of "many" normal cubic patches. This deep network operates on small cubic patches as being the first stage, before carefully resizing remaining candidates of interest, and evaluating those at the second stage using a more complex and deeper 3D convolutional neural network (CNN). We divide the deep autoencoder and the CNN into multiple sub-stages which operate as cascaded classifiers. Shallow layers of the cascaded deep networks (designed as Gaussian classifiers, acting as weak single-class classifiers) detect "simple" normal patches such as background patches, and more complex normal patches are detected at deeper layers. It is shown that the proposed novel technique (a cascade of two cascaded classifiers) performs comparable to current top-performing detection and localization methods on standard benchmarks, but outperforms those in general with respect to required computation time.
本文提出了一种快速可靠的方法，用于在显示拥挤场景的视频数据中进行异常检测和定位。高效的异常定位是一个持续存在的挑战，也是本文的主题。我们提出了一种基于立方块的方法，其特点是有一个级联分类器，该方法利用了先进的特征学习方法。我们的级联分类器有两个主要阶段。首先，一个轻量级但深度的3D自动编码器用于早期识别“许多”正常立方块。这个深度网络在小立方块上运行作为第一阶段，然后仔细调整其余感兴趣的候选块大小，并在第二阶段使用更复杂、更深的3D卷积神经网络（CNN）对其进行评估。我们将深度自动编码器和CNN划分为多个子阶段，这些子阶段作为级联分类器运行。级联深度网络的浅层（设计为高斯分类器，充当弱单类分类器）检测“简单”的正常块，如背景块，而更复杂的正常块在更深层被检测到。结果表明，所提出的新技术（两个级联分类器的级联）在标准基准测试中的性能与当前顶级的检测和定位方法相当，但在所需计算时间方面总体上优于这些方法。
