Upload
others
View
3
Download
0
Embed Size (px)
Citation preview
GTC'16, San Jose, USA
April 5, 2016
Recent Advances in GPU-Based Intelligent
Video Analysis
Beijing Vion Technology Inc.
Hai Tao, Dr., CEO
Company Introdution
• The Beijing Vion Technology, Inc.(BVT) was founded in 2005,
specialized in computer vision technology. The company currently
employs around 200 talented staff members.
• The company has developed products in several markets including
intelligent transportation systems (ITS),business intelligence
systems, security and urban management systems. These products are
deployed broadly across China and BVT is recognized as one of the
leading computer vision companies in China.
• Recently, BVT has developed core algorithms for ADAS and UBI
products.
San J
ose
, U
SA
Apri
l 5,
2016
A Typical IVA System
San J
ose
, U
SA
Apri
l 5,
2016
Analog Cam
Concealed Camera
Half Dome Cam
IP Cam
IVA Box
Network
Switch
PC Client
Data Manage
ment
Mobile App
数据中心
TK1-Based IVA Box - VT-B2081A (CBOX)
San J
ose
, U
SA
Apri
l 5,
2016
TK1-Based IVA Box - VT-B2082A (IBOX)
2 TK1 GPU's
8 analog video inputs
8 audio inputs
2 RJ45 1000M ethernet ports
built-in GPS
1 2.5" hard drive
Alarm: 4 in, 2 out
1 RS232 and 1 RS485
SPF connection
San J
ose
, U
SA
Apri
l 5,
2016
DEMO: IVA Algorithms Running on CBOX/IBox
San J
ose
, U
SA
Apri
l 5,
2016
• People counting - Shopping mall
• People counting - Summer Palace
• People counting - Bus
• People counting - Subway
• People counting - Cinema
• Urban management - Vending
• Law enforcement - Fighting detection
• Law enforcement - Parking violation
A GPU-Based Smart Camera - VT-E412
San J
ose
, U
SA
Apri
l 5,
2016
A 12MP@30fps GPU smart camera
The 1st GPU-based smart camera that can reach 12MP @30 fps
Applications: Face recognition, gender and age recognition, people counting, LPR, fight and chasing detection, premiter monitoring
Main features
12 MP CMOS sensor @ 30 fps
FPGA+TK1 ISP pipeline
Full resolution video analytics
Sensors: gyroscope, accelerometer, digital compass
GPS & Wifi/3G/4G supported
Audio: 1 in, 1 out
Storage: 2 SD cards
Alarm: 2 in, 1 out, 1 RS232 and 1 RS485
DEMO: IVA Algorithms Running on VT-E412
San J
ose
, U
SA
Apri
l 5,
2016
• Facial detection
• Gender and age recognition
• Vehicle detection, tracking and recognition
StartNet GPU Cluster
San J
ose
, U
SA
Apri
l 5,
2016
40 GPUs in a 2U Rack Server
Characteristics of backend IVA
Handreds of h.264/HEVC video streams from IPCs
The computation need for decoding and vision algorithm roughly in 1:1 to 1:10 range
Using traditional server: not enough matching HW decoding power, higher FLOPS/Watt, Lower computing density (FLOPS/SpaceUnit)
Many-GPU solution
TK1/TX1 balances the HW video decoding/encoding capabilities with computing power
Lower FLOPS/Watt
Much higher computing density
San J
ose
, U
SA
Apri
l 5,
2016
Vehicle barnd/model and color recognition
Frontal and back view of vehicles
Day/night time
Average 90% accuracy for vehicle brand recognition
San J
ose
, U
SA
Apri
l 5,
2016
Driver behavior recognition
Not fastening seatbelt
Using cell phones
San J
ose
, U
SA
Apri
l 5,
2016
Prototype ADAS Algorithm Framework
Deep neural network based object detection and tracking (vehicles, pedestrians, bicycles, etc)
Deep neural network based road scene understanding (traffic lane detection and following)
License plate recognition
ADAS main functions including lane departure warning (LDW),vehicle distance monitoing warning (HMW), pedestrian collision warning (PCW), and driving behavior analysis (DBA)
San J
ose
, U
SA
Apri
l 5,
2016
Prototype ADAS Algorithm Framework
Demonstration
San J
ose
, U
SA
Apri
l 5,
2016
Thank you!
San J
ose
, U
SA
Apri
l 5,
2016