FB pixel

Hitachi develops detection and tracking technology using AI

Categories Biometrics News  |  Surveillance

Hitachi, Ltd. has developed detection and tracking technology using artificial intelligence (AI) which can distinguish a person in real-time using features from over 100 categories of external characteristics including sex, color of clothing or items in hand.

Once the system determines the identity of the individual, it can immediately detect and track the person’s movements.

Law enforcement and security personnel can use Hitachi’s technology to detect a suspicious individual or a lost child using information from eye-witness accounts to detect a person matching that description from public security cameras installed in large facilities or city areas.

They can also analyze the entire image of the person detected, enabling them to follow the person from camera images where only the rear-view is captured without a clear view of the person’s face, or the person is captured from afar.

Hitachi will apply this technology to wide-area security and surveillance systems such as those in public areas, contributing to public safety and security.

The high-speed person detection technology categorizes and searches using characteristics of external appearance and movement.

The technology’s AI can conduct real-time simultaneous detection to identify from camera images, more than 100 characteristics related to 12 types of appearance such as sex, age, hair style, color and form of clothing, items in hand, and movement characteristics from 10 categories including walking, running, and bending.

Instead of standard practices which calculate each item separately to distinguish the characteristics, Hitachi’s technology is able to simultaneously calculate multiple items.

The method cuts down the calculation time to 1/40th, which provides specific conditions based on characteristics categorized in real-time by AI to enable high-speed detection of an individual.

The high-speed person tracking technology analyzes in detail the entire image of the body and extracts images of the same individual.

The technology uses AI that recognizes an individual as the same person by analyzing and converting the image of the entire body into a numerical description so that the same person will be recognized regardless of a change in body angle or lighting.

The technology records the result of the AI analysis in a database with high-speed vector processing developed by Hitachi, extracting an image of the same person from among several ten thousands of recorded images in less than 1 second.

During the development of the AI, Hitachi’s R&D team found over a three-fold improvement in accuracy of obtaining an image of the same person compared with that of facial analysis only.

The team was able to develop real-time people detection and tracking by combining the technologies.

Previously reported, Hitachi Insight Group, Hitachi Ltd.’s global unified internet of things (IoT) business and go-to-market (GTM) unit, released new video analytics software to improve and expand on its Smart City and Public Safety solutions portfolio.

Article Topics

 |   |   | 

Latest Biometrics News


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read This Week

Featured Company

Biometrics Insight, Opinion

Biometrics White Papers

Biometrics Events

Explaining Biometrics