1
     
  • COMPUTER VISION &
    DEEP LEARNING
  • COMPUTER VISION &
    DEEP LEARNING
3
2

VIDEO SURVEILLANCE

 

Solutions

Video-surveillance concerns models, computer vision techniques and machine learning systems to :

 

acquire videos about the 3D external world 
detect targets along the time and the space  
recognize interesting or dangerous situations  
riconoscere situazioni di interesse o pericolose  
generate real-time alarms  
record meaningful data about the controlled scene

There are several applications: fire detection, crowd monitoring, accident detection, urban control, access control, security and safety, people behavior analysis etc. applied both to pedestrian and/or vehicles of any kind.

 

 Experience

Pikkart’s R&D team has years of experience in academic research on video surveillance: above all on distributed automated surveillance systems and on people re-Identification. 

 

Pikkart’s R&D team is qualified for the creation of advanced software solutions for security and surveillance applications based on the most cutting edge techniques, from Stochastic Graph Models to Deep Learning. 

 

Privacy preserving solutions can also be developed to obtain accurate people counting and crowd monitoring, protecting sensitive data about surveilled people.

 

Relevant publications

 

“People reidentification in surveillance and forensics: A survey”, Vezzani et al., ACM Computing Surveys, 2013 
“People orientation recognition by mixtures of wrapped distributions on random trees”, Baltieri et al., European Conference on Computer Vision, 2012

 

Why choose Pikkart?

 

 

 

Last update:  12/12/2017