v i s i o n l a b s
play

V I S I O N L A B S GPU-Powered Megacity Scale Transport Management, - PowerPoint PPT Presentation

V I S I O N L A B S GPU-Powered Megacity Scale Transport Management, Municipal Services and Public Safety Solutions Talk ID: S8584 | Anton Nazarkin, Global BDO VisionLabs About: Customers: We are proud to serve the industry leaders and SMBs


  1. V I S I O N L A B S GPU-Powered Megacity Scale Transport Management, Municipal Services and Public Safety Solutions Talk ID: S8584 | Anton Nazarkin, Global BDO

  2. VisionLabs About: Customers: We are proud to serve the industry leaders and SMBs VisionLabs is a team of Computer Vision and Deep Learning experts. Founded in 2012, today we offer face recognition products and custom Computer Vision solutions globally Products: Collaboration: We are happy to work together with the global The flagship products of VisionLabs are LUNA SDK facial technology leaders analysis and recognition engine and LUNA PLATFORM biometric data management system. We also provide solutions for AR/VR field (3D face avatars) and Smart City field (traffic analysis and classification). 02

  3. PyTorch contributor Companies & Universities developing PyTorch 03

  4. Outstanding facts Our production face We are the only company More than 1 000 000 Our products process recognition algorithm in the TOP 5 according to cameras are streaming more than 60B face was independently the LFW test result having video to our products recognition requests per tested by NIST and is commercially available daily with the largest year globally with the TOP rated for algorithm with the same single Customer largest single Customer accuracy and speed performance implementtion of implementation of 15B characteristics 250 000+ cameras requests per year 04

  5. Accuracy TPR at FPR 10 -3 ≈ 99,18% • TPR at FPR 10 -6 ≈ 99,00% • TPR at FPR 10 -8 ≈ 92,44% • TPR: True Positive Rate FPR: False Positive Rate Face Descriptor Size ~ 256 bytes 05

  6. Deep learning dataset 10M+ face images • Access to data from multiple device types, face capture scenarios with varying quality settings and environment conditions guarantees robust algorithm operation • Intense use of NVIDIA GPUs for training; parallel training on 4-8 GPSs gives faster training and better accuracy with larger batch sizes 06

  7. Privacy Customers’ data is 100% encrypted and 100% protected against unauthorized access Handling of personal data is fully aligned with local laws and corporate IT security 07

  8. VL plug-in for NVIDIA DriveIX • VL Driver Monitoring Integrated as a plug-in for DriveIX • Jetson or DrivePX box solution for public transport security • Real-time face-based immobilizer and driver state monitoring 14

  9. Driver monitoring (demo) 09

  10. Public transport, service transport, car sharing • Takeover prevention in case of terrorists attacks • Not the appointed driver = engine stop • Driving time and work hours control 11

  11. Megacity traffic monitoring NVIDIA TESLA P40 Megacity scale vehicle traffic analysis and anomalies detection powered by NVIDIA Tesla P40 with 80M+ recognition requests daily 15

  12. Traffic monitoring (demo) 08

  13. Traffic monitoring (demo) 08

  14. National scale biometric platform NVIDIA TESLA P40 National scale face identification platform for financial services with 110M+ faces database. 21

  15. Cross-platform face recognition • Set of front-end modules for face detection, best shot selection and normalization Door bell • Stable cross-platform operation and simple configuration for multiple ATM / Terminal Personal computers architectures Server • Ultra-fast GPU powered backend face recognition platform with extremely low latency WEB-browsers Mobile devices IP-cameras 22

  16. ID Management 27

  17. Audience Measurement • Visitor counting and Customer dwell time estimation • Accurate gender (99.5%) and age (+- 1,5 years) detection • Detailed marketing research based on impersonal data analysis 23

  18. Visitors distribution by zone Enter Cashbox_1 Cashbox_2 Cashbox_3 Alcohol cashbox 1000 897 872 900 854 845 796 796 800 701 679 700 635 600 Quantity 500 410 409 409 406 399 386 400 359 359 359 358 350 331 332 332 321 286 281 275 264 300 255 249 239 209 207 195 191 168 174 200 163 157 120 117 118 100 96 82 100 0 14.08.2017 15.08.2017 15.08.2017 16.08.2017 17.08.2017 18.08.2017 19.08.2017 20.08.2017 21.08.2017 25

  19. Anton Nazarkin GBDO, VisionLabs E-mail: sales@visionlabs.ai Web: www.visionlabs.ai

Recommend


More recommend