Dahua Technology Ltd

Dahua Technology, a video-centric smart IoT solution and service provider, recently ranked 1st in the MIT Scene Parsing Benchmark.

Based on deep learning algorithms, Dahua Technology’s Scene Segmentation Technology tops the world's best results in Scene Parsing, surpassing other major AI companies and academic research institutions, and exceeding scene parsing research results in relevant papers of ICCV, ECCV, and CVPR. This achievement marks Dahua Technology’s position in the field of scene parsing.

Computer vision technologies

ADE20K_MIT is an evaluation dataset for MIT Scene Parsing Benchmark released and maintained by the MIT CSAIL research group. It is one of the internationally authoritative computer vision semantic segmentation algorithm evaluation datasets. The dataset is used to evaluate the performance of computer vision technologies such as Scene Perception, Scene Parsing, Instance Segmentation, and Semantic Segmentation.

The challenging evaluation attracts participants from hundreds of well-known AI laboratories

With a wide range of targets and a large range of target scales, the challenging evaluation attracts participants from hundreds of well-known domestic and foreign AI laboratories and top academic research institutions, including MIT, Microsoft, Peking University, Tsinghua University, Chinese Academy of Sciences, Alibaba, etc. Scene parsing is to segment and parse an image into different image regions associated with semantic categories, such as sky, road, person, and bed. It is one of the core technologies in the segmentation field, which solves problems such as occlusion, unclear categories, and easy confusion in complex scene parsing.

Self-developed deep learning platform

In this international evaluation, Dahua Technology innovatively utilised its algorithm advantages in Semantic Segmentation and Panoptic Segmentation based on its self-developed deep learning platform, and developed a set of Semantic Segmentation frameworks based on Graph Convolutional Neural Networks(GCN). Through multi-scale features fusion, adaptive IoU Loss Function on the frequency domain, and by taking advantage of Multi-model Feature Fusion Technology, the Dahua framework effectively improves the mean of the Pixel-wise Accuracy and Class-wise IoU of Scene Segmentation, which ultimately tops the evaluation records of scene parsing dataset.

Dahua Technology continues to cultivate and innovate in the field of AI technology, and constantly improves the core competitiveness of its algorithms and computing power. In 2018, Dahua Technology ranked first in 12 global AI rankings including road segmentation, vehicle tracking, multiple object tracking, 3D object detection, human detection, vehicle detection, scene flow, optical flow, and person re-identification.

Setting complex configurations

Dahua Scene Parsing Technology can automatically identify traffic sign information

In the succeeding year, 2019, Dahua Technology ranked first in 10 global AI rankings including person re-identification, instance segmentation, semantic segmentation, gait recognition, and remote sensing image analysis. Dahua Technology actively accelerates the transformation of AI technology achievements into real productivity and empowers the intelligent upgrade of the industry.

In the field of smart traffic management, Dahua Scene Parsing Technology can automatically identify traffic sign information including lane lines, turning arrows, stop lines, pedestrian crossings, etc. For example, in a violation preliminary trial, this technology can be used to achieve automatic analysis of the target’s trajectory and illegal behaviour without manually setting complex configurations, which improves work efficiency, eases the use of the product, and continuously expands the application of solutions related to traffic scene parsing.

Improving road safety and travel efficiency

At the same time, with AI enforcement camera, e-police system, dual-lens enforcement camera, smart traffic signal control and other deployments to maximise the advantages of AI technology, it can also improve road safety and travel efficiency, providing a powerful technical engine for intelligent traffic management.

In the future, Dahua Technology will provide key technical support for the expansion and application of smart logistics, smart water services, smart farming, and smart retail through the accumulation and breakthroughs in AI technology, aiding the industry's innovation and development.

Share with LinkedIn Share with Twitter Share with Facebook Share with Facebook
Download PDF version

Dahua Technology Ltd news

Dahua AI Technology ranks first in the Onera Satellite Change Detection (OSCD) Evaluation

Dahua Technology’s AI-based Remote Sensing Image Analysis Technology has obtains first place in the comprehensive precision ranking of the Onera Satellite Change Detection (OSCD) Evaluation released by Geoscience and Remote Sensing Society (GRSS). This achievement demonstrates Dahua Technology’s continuous development and innovation capabilities in the field of remote sensing image change detection. OSCD IEEE IADF TC recognition OSCD (Onera Satellite Change Detection) is jointly is...

Interphone partners with Dahua Technology to unveil temperature monitoring and flow control solutions

Interphone has teamed up with Dahua Technology, a global video surveillance specialist, to help private and public sector organisations create a safer in-building environment and experience as COVID-19 restrictions are lifted. As an accredited Dahua Integrator Partner, Interphone will have access to the latest innovations in thermal access control, temperature monitoring, people counting and flow control, which will be used to develop epidemic safety protection solutions all types of premises....

Eagle Eye Networks launches cloud-based, turnkey elevated temperature screening system

Eagle Eye Networks, the global renowned provider of cloud video surveillance, has announced the availability of a passive elevated temperature screening solution with the Eagle Eye Cloud Video Management Systems (VMS). Eagle Eye Networks will be providing a complete system via its reseller partners which includes a thermal camera, blackbody calibration unit, cloud-based recording subscriptions, and real-time notifications. Calibration unit The calibration unit is recommended by the FDA for th...

Dahua Technology Ltd case studies

Dahua provides its Mobile Solution to enhance patrolling services for the Buenos Aires police

As one of the most important provinces of Argentina, Buenos Aires Province has been seeking to improve work efficiency and emergency response speed of its police force. However, the local police was always lacking of evidence when performing legal actions towards violence, traffic accidents, and other social incidents. This created temporary loopholes in law enforcement that criminals and erring people took advantage of in order to escape legal sanctions. For this reason, the Ministry of Securi...

Dahua Technology’s intelligent video surveillance cameras offer AI-enabled video security for Allianz Parque

Allianz Parque has become one of the most modern multi-purpose arenas in Latin America since it was built in 2014 by WTorre Properties. The stadium is located at the same place of the old Palestra Itália Stadium with a capacity of more than forty thousand spectators. The stadium not just meets FIFA standards but was also awarded various prizes including the Master Award in the 11th edition of the Grand Prize for Corporate Architecture, the Accessibility Seal, delivered by the Permanent A...

Dahua delivers customised monitoring solution for Pengsheng Industrial Park in Uzbekistan

Pengsheng Industrial Park is the first investment project by a Chinese private enterprise in Uzbekistan that has been acknowledged and ratified by the governments of the two countries. Located in Uzbekistan's Sirdaryo state, the Pengsheng Industrial Park is the biggest non-energy cooperation project between China and the Central Asian country. At present, there are over 10 workshops covering various fields with a total number of more than 1,500 employees. As a model project of China-Uzbekistan...