[论文解读] Detecting abnormal events in video using Narrowed Motion Clusters.

Radu Tudor Ionescu, Sorina Smeureanu+2 more|arXiv (Cornell University)|Jan 12, 2018

Anomaly Detection Techniques and Applications参考文献 35被引用 5

一句话总结

该论文提出了一种两阶段异常事件检测框架，利用k-means聚类和一类SVM从正常视频的运动特征中识别异常值。通过剪枝稀疏聚类并缩小剩余聚类的边界，该方法在CPU上实现了30 FPS的实时检测，同时在四个基准数据集上优于最先进方法。

ABSTRACT

We formulate the abnormal event detection problem as an outlier detection task and we propose a two-stage algorithm based on k-means clustering and one-class Support Vector Machines (SVM) to eliminate outliers. After extracting motion features from the training video containing only normal events, we apply k-means clustering to find clusters representing different types of motion. In the first stage, we consider that clusters with fewer samples (with respect to a given threshold) contain only outliers and we eliminate these clusters altogether. In the second stage, we shrink the borders of the remaining clusters by training a one-class SVM model on each cluster. To detected abnormal events in the test video, we analyze each test sample and consider its maximum normality score provided by the trained one-class SVM models, based on the intuition that a test sample can belong to only one cluster of normal motion. If the test sample does not fit well in any narrowed cluster, than it is labeled as abnormal. We also combine our approach based on motion features with a recent approach based on deep appearance features extracted with pre-trained convolutional neural networks (CNN). We combine our two-stage algorithm with the deep framework using a late fusion strategy, keeping the pipelines of the two approaches independent. We compare our method with several state-of-the-art supervised and unsupervised methods on four benchmark data sets. The empirical results indicate that our abnormal event detection framework can achieve better results in most cases, while processing the test video in real-time at 30 frames per second on CPU.

研究动机与目标

• 解决仅在正常训练数据可用的情况下检测视频序列中异常事件的挑战。
• 通过在流水线早期过滤掉稀疏且易受异常值影响的运动聚类，提升基于运动的异常检测的鲁棒性。
• 利用一类SVM细化正常运动聚类的决策边界，以提高检测精度。
• 通过晚期融合将基于运动的检测与预训练CNN提取的深层外观特征相结合，以提升性能。
• 在无需GPU加速的情况下，实现在CPU上30 FPS的实时推理。

提出的方法

• 对仅包含正常事件的训练视频中提取的运动特征应用k-means聚类，以对相似运动模式进行分组。
• 将样本数少于预设阈值的聚类移除，假设其代表异常值。
• 在剩余的每个聚类上训练一类SVM，以缩小其边界并定义更紧致的正常运动区域。
• 对于测试样本，计算所有训练过的一类SVM模型中的最大正常度分数，以判断该样本是否符合任一正常聚类。
• 如果样本在任何经过收紧的聚类中匹配度均不足，且最大分数低于阈值，则将其标记为异常。
• 通过晚期融合将基于运动的框架与深层外观特征流水线结合，同时保持两条流独立。

实验结果

研究问题

• RQ1 剪枝稀疏运动聚类是否能提升视频中异常事件检测的准确性？
• RQ2 通过一类SVM缩小聚类边界是否能增强对细微异常事件的检测能力？
• RQ3 通过晚期融合将运动特征与深层外观特征结合，是否能带来优于单一模态方法的性能提升？
• RQ4 所提方法是否能够在不牺牲准确性的前提下，实现在CPU上30 FPS的实时推理？
• RQ5 该方法在标准基准测试中与最先进监督与无监督异常检测方法相比表现如何？

主要发现

• 所提方法在四个基准数据集上优于多种最先进监督与无监督方法。
• 该框架在CPU上以30帧每秒的速度实时处理测试视频，展现出高效率。
• 通过晚期融合将运动特征与深层外观特征结合，相比单独使用任一模态，检测精度均有提升。
• 两阶段方法——先剪枝聚类，再通过一类SVM优化边界——有效减少了误报，因早期剔除了易受异常值影响的聚类。
• 由于核心检测机制为无监督，该方法在未见异常事件上仍保持较强的泛化能力。