Anomaly detection algorithms based on deep neural networks have achieved favorable performance in finding abnormal events in surveillance video. Recently, end-to-end methods that combine feature extraction, model learning, and anomaly scoring into one training procedure have become popular. However, most existing research studies have relied on a deep convolutional structure, which faces overfitting problems for a limited training set. An anomaly detection algorithm based on the state-of-the-art prediction framework is proposed, leveraging the gap between frame prediction and its ground truth to detect abnormal events. The residual block is transferred from image classification, and we modify its modules to suit the prediction application in order to tackle the difficulties in training a deeper prediction network. As far as we know, the proposed method is the first anomaly detection residual network trained from scratch, which is different from several existing ones with fixed resnet-50 layers as feature extractor. Furthermore, a new perceptual constraint focusing on high-level information is proposed and combined with the commonly used spatial–temporal constraints. Experimental results on challenging public surveillance sequences verify that our proposed framework can effectively produce state-of-the-art performance.
Bam seismogenic fault is blind, so it is important to discover its strike and pattern for earthquake prediction and
hazard mitigation of this area. Firstly we use the interferometric algorithm to process seven scenes synthetic aperture
radar data, which are provided by European Space Agency, and obtain the coseismic deformation interferograms. Then
considering the similarity of interferometric stripes on two deformation interferograms from the descending orbits and
the difference of their imaging geometry, we use Fialko's method to construct the 3D coseismic deformation
displacement field. Finally we infer the strike and pattern of the Bam fault according to the difference of the vector's
orientation in the horizontal displacement field. The strike of Bam main fault is from northwest-southeast to north-south,
and a branch is stretching toward northeast. The projection of the Bam fault is "Y" shaped on the Earth's surface,
basically consistent with the Nakamura's results inferred from seismic data.
Parameters of two spherical waves are firstly optimized to get the exact groove densities of diffractive gratings.
Consequently, the groove density differences between on the plane and on the curved substrates are derived. Therefore,
some experimental results are provided to demonstrate the validity of this method above. Meanwhile, the curvatures of
the substrates are measured three times by using long trace profiler (LTP), which assures the repeatability of the bending
technique for grating substrates. At last, the advantage of this method is exhibited through comparing the errors of
grating groove density fabricated by this technique with only two spherical waves.