Your browser version is outdated. We recommend that you update your browser to the latest version.

Browse by category...

Hikvision

SIGN UP to Defsec  eNewsletters

Fields marked with * are required.

DEFSECmedia

DEFSEC Media is New Zealand's defence, security and fire B2B/B2G publishing group. Our leading magazines, Line of DefenceNZ Security and Fire NZ are read by key business, government and military decision makers and influencers. This website is the online home of cutting-edge content from each of our titles.

Itron

C-27J Spartan

Dahua Technology’s ARI Method Ranked #1 in the KITTI 2D Object Detection Evaluation 2012

Posted 12/8/2018

Dahua Technology’s ARI 2D object detection method took the 1st place in KITTI Vision Benchmark Suite’s Object Detection Evaluation 2012 on July 26th, 2018 - with an accuracy of 91.48 percent based on the moderate difficulty level.

Dahua’s ARI Method Ranked #1 in KITTI Object Detection Evaluation 2012. Source: Dahua.Dahua’s ARI Method Ranked #1 in KITTI Object Detection Evaluation 2012. Source: Dahua.

 

The KITTI vision benchmark suite is a systematic benchmarking platform designed to evaluate computer vision performance. Funded by the Karlsruhe Institute of Technology and the Toyota Technological Institute at Chicago, it is probably the world's first and largest benchmarking suite for vision based autonomous driving. 

KITTI includes real life images collected from a variety of scenery, from urban streets in the mid-size city of Karlsruhe to rurals roads and highways. Each image contains sophisticated scenarios involving at most 15 vehicles and 30 pedestrians with varying levels of overlapping. The KITTI vision Benchmark suite comprises of real-world benchmarks for stereo, optical flow, visual odometry, object detection and tracking. 

This competition has provided Dahua with an excellent opportunity to further its independent research and development of deep learning algorithms. Based upon the advantages of network structures such as ResNet, Dahua Technology has successfully improved the structures of its deep learning detection algorithm. 

Utilising reinforcement learning and other training techniques, as well as multi-model fusion technology, Dahua Technology has made a significant improvement in the detection rate of small and/or overlapped targets.

About 2D Object Detection

2D object detection algorithms are able to realize target detection in videos. They then capture the targets after classifying them. 2D object detection is widely applied in the company’s newly launched intelligent products, especially the cameras, NVRs and servers based upon AI deep-learning.

Innovation is Dahua Technology’s driving force for development, and is also its source of energy. Dahua Technology’s high ranking in 2D object detection, has for yet another time, showcased its world class technical research ability in this field. With a mission of “Enabling a Safer Society and Smarter Living”, Dahua Technology will continue to focus on “Innovation, Quality, and Service”, to serve partners and customers around the world.

About Dahua Technology

Zhejiang Dahua Technology Co., Ltd. is a leading solution provider in the global video surveillance industry. In 2016, Dahua was ranked 4th in “Security Top 50” by A&S International. Dahua is committed to providing the highest quality solutions and products with the latest technologies to enable our end users to perform their business successfully. 

The company has more than 5,000 R&D engineers and technical staff working on cutting-edge technologies in camera lens, image sensor, video encoding & transmission, embedded processor, graphic processing, video analytics, software reliability, network security and other technologies.

Visit http://www.dahuasecurity.com to learn more.

Follow us

f

Contact us

Phone: 022 366 3691

Email: nick@defsecmedia.co.nz   

© 2015. Defsec Media Limited. All Rights Reserved.

OUR PARTNERS

Advertise     

Subscribe 

Contribute

OUR MAGAZINES

Line of Defence     

Fire NZ     

NZ Security

OUR COMMUNITY

Linkedin

Twitter

Facebook