Robust and Computationally-Efficient Anomaly Detection using Powers-of-Two Networks
This work addresses computational efficiency and robustness for video surveillance systems, but it is incremental as it builds on existing CNN and GAN methods with specific optimizations.
The authors tackled the problem of robust and computationally efficient anomaly detection in videos by proposing a CNN-based detector that uses optical flow, denoising intermediate layers, and powers-of-two weights to replace multiplications with bit-shifts. They achieved a 10% speedup while detecting all anomalies in testing and improved robustness to background motion.
Robust and computationally efficient anomaly detection in videos is a problem in video surveillance systems. We propose a technique to increase robustness and reduce computational complexity in a Convolutional Neural Network (CNN) based anomaly detector that utilizes the optical flow information of video data. We reduce the complexity of the network by denoising the intermediate layer outputs of the CNN and by using powers-of-two weights, which replaces the computationally expensive multiplication operations with bit-shift operations. Denoising operation during inference forces small valued intermediate layer outputs to zero. The number of zeros in the network significantly increases as a result of denoising, we can implement the CNN about 10% faster than a comparable network while detecting all the anomalies in the testing set. It turns out that denoising operation also provides robustness because the contribution of small intermediate values to the final result is negligible. During training we also generate motion vector images by a Generative Adversarial Network (GAN) to improve the robustness of the overall system. We experimentally observe that the resulting system is robust to background motion.