Hybrid deep learning and HOF for Anomaly Detection

Anomalies detection in video footage is a daunting task treated with many challenges in crowded scenes. In this paper, we propose an efficient method based on deep learning and handcrafted spatio-temporal feature extraction for anomaly detection using a pre-trained CNN (convolution neural network) and HOF (Histogram of Optical Flow) features. Abnormal motion is picked by relative thresholding. One-class SVM is trained with spatial features for robust classification of abnormal shapes. Moreover, a decision function is applied to correct the false alarms and the miss detections. Our method has a high performance in terms of speed and accuracy. It achieved anomaly detection with good efficiency in challenging datasets and reduced computational complexity compared to state-of-the-art methods.