Breaking News

Micron Announces New 2600 NVMe SSD HighPoint Launches Next-Gen External PCIe Gen5 x16 Switching Adapter LG Display Begins Mass Production of Ultimate Gaming OLED Panel with 4th-Generation OLED Technology PlayStation Plus Monthly Games for July 2025 Samsung Releases Smart Monitor M9 With AI-Powered QD-OLED Display

logo

  • Share Us
    • Facebook
    • Twitter
  • Home
  • Home
  • News
  • Reviews
  • Essays
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map

Search form

Fujitsu Technology Recognizes Faces Appearing In Low-Resolution Images

Fujitsu Technology Recognizes Faces Appearing In Low-Resolution Images

Enterprise & IT Mar 6,2015 0

Fujitsu has developed a technology that provides highly accurate detection of people's movements and that can recognize the flow of people from low-resolution imagery incapable of distinguishing faces. In existing systems that analyze video taken from surveillance cameras, the video resolution should be high enough in order the system to identify individuals. Typically, in order to extract information on flows of people appearing in a video, current approached extract a person-like shape from an image and by using multiple cameras, it is determine whether a person detected by one camera is the same person detected by other cameras. Because these teqniques have used information detected from a person's face, build, gender, and other personal characteristics to determine if it is the same person, the problem has been that the person may be identified, causing the video to be unusable due to privacy issues.

 

Using features that people have in common, Fujitsu Laboratories has devised person-recognition technology that extracts body-like shapes such as heads and torsos in low resolution images, and determines if the person is the same based on clothing colors.

Fujitsu focused on the fact that, even in low-resolution images, the head persists as a distinctive human characteristic that is unaffected by a person's posture or the angle from which the person is seen. Regardless of whether viewed from the front, back, left, or right side, the established characteristics of the head being a roughly elliptical shape and at the top of a person's body have the advantage of persisting even in low-resolution images.

The extraction process is as follows:

Focusing on head-shaped characteristics in the input image, extract head-shaped candidates. Because many similar shapes were detected, treating the lower ones as torso shapes makes it possible to accurately detect people even from low-resolution images.

Based on the people detected in Step 2, the teqnique detects their relative proximity to the camera, beginning with the closest person, and updates the image of more distant persons to compensate for partially obscured areas of a body. This makes it possible to accurately detect even multiple, overlapping people.

Fujitsu says that the technology can independently recognize the heads and torsos of multiple people.

Fujitsu's technology makes it possible to recognize a person's movements between cameras.

By selectively extracting only the distinctive colors of a person's clothing, Fujitsu has been able to perform reliable person matching using low-resolution images.

Fujitsu Laboratories performed an indoor trial, in which it was able to detect, in the flow of people, the paths of approximately 80% of the people.

As a result, when arranging merchandize or deploying staff inside a store, for example, it makes it possible to use surveillance camera images that respect the privacy of the people whose images are being recorded, and enables the use of images that do not identify individuals to improve customer service.

Fujitsu Laboratories plans to conduct more practical testing to improve detection accuracy, and aims for commercial implementation during fiscal 2015.

Tags: Fujitsu
Previous Post
Windows Also Vulnerable to FREAK Encryption Flaw
Next Post
Apple Allowed App Developers Fine-tune Apps Before Watch Debut

Related Posts

  • Fujitsu Achieves Major Technical Milestone with World's Fastest 36 Qubit Quantum Simulator

  • Fujitsu Launches 14 New Models of Enterprise Notebooks, Tablets and Workstations

  • Fujitsu AI-Video Recognition Technology Promotes Hand Washing Etiquette and Hygiene in the Workplace

  • Fujitsu and Qualcomm Complete Multi-Gigabit Data Call Using 5G Carrier Aggregation

  • Fujitsu Launches Japan's First Commercial Private 5G Network

  • Fujitsu Streamlines AI Video Recognition with Compression Technology

  • Fujitsu Develops Magnetic Tape Storage High-Speed Access Technology

  • Japan Approves Bill to Help Firms Develop 5G, Drone

Latest News

Micron Announces New 2600 NVMe SSD
Enterprise & IT

Micron Announces New 2600 NVMe SSD

HighPoint Launches Next-Gen External PCIe Gen5 x16 Switching Adapter
Enterprise & IT

HighPoint Launches Next-Gen External PCIe Gen5 x16 Switching Adapter

LG Display Begins Mass Production of Ultimate Gaming OLED Panel with 4th-Generation OLED Technology
Enterprise & IT

LG Display Begins Mass Production of Ultimate Gaming OLED Panel with 4th-Generation OLED Technology

PlayStation Plus Monthly Games for July 2025
Gaming

PlayStation Plus Monthly Games for July 2025

Samsung Releases Smart Monitor M9 With AI-Powered QD-OLED Display
Enterprise & IT

Samsung Releases Smart Monitor M9 With AI-Powered QD-OLED Display

Popular Reviews

be quiet! Light Loop 360mm

be quiet! Light Loop 360mm

be quiet! Dark Mount Keyboard

be quiet! Dark Mount Keyboard

Arctic Liquid Freezer III 420 - 360

Arctic Liquid Freezer III 420 - 360

be quiet! Light Mount Keyboard

be quiet! Light Mount Keyboard

Soundpeats Pop Clip

Soundpeats Pop Clip

Noctua NH-D15 G2

Noctua NH-D15 G2

Crucial T705 2TB NVME White

Crucial T705 2TB NVME White

be quiet! Light Base 600 LX

be quiet! Light Base 600 LX

Main menu

  • Home
  • News
  • Reviews
  • Essays
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map
  • About
  • Privacy
  • Contact Us
  • Promotional Opportunities @ CdrInfo.com
  • Advertise on out site
  • Submit your News to our site
  • RSS Feed