Artificial Intelligence Fights Crime and Terrorism at a New Level

High expansion of urban population and infrastructure complemented by recent geopolitical world events, triggered an increasingly alarming number of threats. Law enforcement authorities are now challenged to redesign societal security concepts. Although current technological advances eased the information access, e.g., via video surveillance cameras, satellite data, drones, wearables, manual analysis of such big and diverse data to extract strategic knowledge is not a solution anymore. There is the critical need for automatic solutions. Artificial Intelligence (AI) and the breakthrough of deep neural networks opened a new perspective for providing such solutions with a human-grade accuracy. Here, we provide a snapshot of our AI research for counter terrorism on automatic person and object identification, retrieval of speech intelligence, and dissimulated behavior analysis. The research was carried out during the UEFISCDI SPIA-VA research project at CAMPUS Research Center, University “Politehnica” of Bucharest, with the participation of UTI Grup and of the Military Equipment and Technologies Research Agency (ACTTM), having as public beneficiary the Protection Guard Service, Romania (SPP).

[1]  Markus Schedl,et al.  Benchmarking Violent Scenes Detection in movies , 2014, 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI).

[2]  Joon Son Chung,et al.  Lip Reading in the Wild , 2016, ACCV.

[3]  Bogdan Ionescu,et al.  Retrieval of distinctive regions of interest from video surveillance footage: a real use case study , 2015, ICDP.

[4]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[6]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[7]  Horia Cucu,et al.  Lemma-based Dynamic Time Warping Search for Keyword Spotting Applications in Romanian , 2019, 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD).

[8]  Corneliu Burileanu,et al.  Modulation-based Speech Emotion Recognition with Reconstruction Error Feature Expansion , 2019, 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD).

[9]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Horia Cucu,et al.  Overlapped Speech Detection and Competing Speaker Counting–‐Humans Versus Deep Learning , 2019, IEEE Journal of Selected Topics in Signal Processing.

[11]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[12]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Oswald Lanz,et al.  Learning to detect violent videos using convolutional long short-term memory , 2017, 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[14]  Yoshua Bengio,et al.  Speaker Recognition from Raw Waveform with SincNet , 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

[15]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  Little-Big Deep Neural Networks for Embedded Video Surveillance , 2018, 2018 International Conference on Communications (COMM).

[17]  Yiming Wang,et al.  Low Latency Acoustic Modeling Using Temporal Convolution and LSTMs , 2018, IEEE Signal Processing Letters.

[18]  Corneliu Florea,et al.  Large Margin Loss for Learning Facial Movements from Pseudo-Emotions , 2019, BMVC.

[19]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[20]  Corneliu Florea,et al.  Annealed Label Transfer for Face Expression Recognition , 2019, BMVC.

[21]  Horia Cucu,et al.  GMM-UBM Modeling for Speaker Recognition on a Romanian Large Speech Corpora , 2018, 2018 International Conference on Communications (COMM).

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Horia Cucu,et al.  Kaldi-based DNN Architectures for Speech Recognition in Romanian , 2019, 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD).

[24]  Tal Hassner,et al.  Violent flows: Real-time detection of violent crowd behavior , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.