Download PDF version Contact company

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.

Download PDF version Download PDF version

Dahua Technology Ltd news

Dahua Technology and Yeastar announce their new ECO partnership on PBX-Intercom integration

Dahua Technology, a video-centric smart IoT solution and service provider, and Yeastar, the provider of SME PBX systems, jointly announce their new ECO partnership on PBX-Intercom integration. The two top-notched companies aim to provide a comprehensive and unified communication solution for Small and Medium-sized Enterprises (SMEs), allowing mutual customers to benefit from visual intercom, remote access control, integrated video conferencing, instant messaging, file sharing, multi-client mana...

Dahua Technology unveils DeepHub smart interactive whiteboard for efficient and collaborative video conferencing

Dahua Technology, a video-centric smart IoT solution and service provider, is introducing its Dahua DeepHub Smart Interactive Whiteboard – an IFPD (Interactive Flat Panel Display) device designed for modern meeting rooms and remote communication demands. Based on customer needs of digital transformation, Dahua Technology has been exploring the video conferencing market for years and has utilised its technological innovation capability to equip Dahua DeepHub with a user-friendly...

Dahua explains 3 things to know about WDR

Scenario: One needs to install a camera in the lobby of a building to capture the entrance area. Problem: The area has a lot of windows which overexposes the image, making it difficult to capture the people coming in and out of the premises. Solution: A security camera with a good Wide Dynamic Range (WDR). What WDR does? Dynamic range refers to the ratio between the largest and smallest measurable quantities of something. In the case of video surveillance, the dynamic range measures the rati...

Dahua Technology Ltd case studies

Dahua Technology shows how intelligent cameras enhance safety in nursing homes

Patient falls in nursing homes are a serious problem. In the United States, for example, around 1,800 elderly people, living in nursing facilities, die each year from injuries related to falls, according to the Nursing Home Abuse Center. Those patients who survive their injuries often have a reduced quality of life and suffer some form of permanent disability. Rise in nursing home patient falls Figures show that between 50% and 75% of nursing home residents suffer falls each year, twice the c...

Dahua Technology provides CCTV cameras to enhance VMS at the Autodromo Internazionale Enzo e Dino Ferrari di Imola

The Autodromo Internazionale Enzo e Dino Ferrari di Imola is a legendary place for every motoring enthusiast. Since 1953, the Emiliano-Romagnolo circuit is the beating heart of a land historically tied to speed and scene of epic sporting achievements and beyond. “A small Nürburgring, with same technical and spectacular resources and an ideal track length,” says Drake Enzo Ferrari, Founder of the iconic racing team and automotive company and to whom the autodrome was named after...

Dahua Technology releases full-colour 2.0 network cameras with 4K vari-focal lens and AI features

With constant development in the modern society, continuous innovation is of paramount importance in order to address the diverse needs of customers. Dahua Technology, a video-centric smart IoT solution and service provider, recently released its upgraded full-colour 2.0 network cameras that offer brand new functions – including dual-lens, 4K colour image, vari-focal lens, and AI features – that can significantly optimise surveillance monitoring and greatly benefit end users in term...