Subtle placement of POE interface for
enhanced aesthetics
• Robust feature set supporting your
multiple applications and systems’
integration
• • Deep learning enhanced 3D sensor with powerful
performance and continuously improving accuracy.
Wider coverage area giving our customers greater
savings on your total investment
Optional USB plugin support for applications like
Staff Exclusion
• •

Brief Introduction


TD2000 G4-the 4th generation 3D sensor with enhanced on-device AI capabilities and a comprehensive feature set.

The TD2000 G4 is the next-generation deep learning 3D sensor, building on the unparalleled accuracy of the G3 while introducing advanced on-device analytics. With a significant hardware upgrade to a 2 TOPS NPU, the G4 processes more powerful features on the edge. It is ideal for top-down mounting and excels in high-precision traffic counting and behavioral analytics—now with enhanced features like Re-ID Solo, View Attention, Age-Range estimation, posture recognition, and auto accuracy optimization for standard counting.

Advanced On-Device AI & Re-ID Solo: The upgraded 2 TOPS deep learning chip enables Re-ID Solo, allowing for on-device Re-Identification using a single sensor. This brings advanced Re-ID analytics to small-format retail environments without requiring the TD4001 series edge computing unit or any external GPU, making true-accuracy counting more affordable.

Enhanced Accuracy & Auto Optimization: Auto Accuracy Optimization automatically adapts to environmental changes such as store layout alterations (e.g., aisle moves). This improves the counting accuracy of the TD2000 G4 for none-Re-ID standard counting use.

Comprehensive Analytics: Beyond standard counting, it can enable View Attention metrics, Age-Range estimation, and customized activity analytics (e.g., posture recognition for lying down, QR scanning, opening/closing car doors, or product interaction like picking up).

Flexible Staff Exclusion: Supports multiple methods: 1) Staff Exclusion Button, 2) uniform identification, and 3) Re-ID based staff identification.

Privacy Protection: Prioritizing data privacy, the TD2000 G4 is compliant with related regulations and laws including but not limited to GDPR and China’s Personal Data Protection Law (PIPL), processing anonymized data without handling personal information. As a top-view sensor, it further mitigates the capture of sensitive details and offers enhanced privacy options including complete image blackout, blurred visuals, and head encoding.

Improved System Management: The G4 introduces Auto Firmware Upgrade via RCS (Remote Control Server) and Encrypted Validation Video Playback, simplifying maintenance and ensuring secure data verification.

With its highly accurate analytics and enhanced on-device intelligence, the TD2000 G4 empowers customers with valuable insights for well-informed business decisions.

Advantages


Remarkable Accuracy
The 4th generation 3D intelligent sensor empowered with TDI patented ‘DeepCount’ and AI chips render TD2000 G4 superior in accuracy rate up to 99.5%* and above under typical applications.

* Accuracy is based on project-specific testing and may vary on a case-by-case basis.

Staff Exclusion
TD2000 G4 offers more flexibility to enable staff exclusion: Using an optional USB plugin, via uniform detection or Re-ID for easy implementaion on reasonable, extra charge.  
Covering Greater Area with Accuracy
TD2000 G4 has been designed with path linking up to 9 units and AI capability for combining data from multiple units to cover a large area or wide entrance  while minimizing the counting error in overlapping area. 
Advanced On-Device AI & Re-ID Solo

Re-ID Solo, allowing for on-device Re-Identification using a single sensor. This brings advanced Re-ID analytics to small-format retail environments, making true-accuracy counting more affordable.

Robust Feature Set and Comprensive Analytics
Designed for exceptional reliability indoors and outdoors, it handles all your standard counting needs—from entries and passers-by to dwell time. Going beyond simple metrics, it unlocks advanced Re-ID for unique visitor tracking and delivers deep, comprehensive analytics, such as View Attention metrics, gender and age-range estimation, group/individual counting, and customized activity recognition.

Key Features


  • Re-ID Solo:On-device Re-Identification using a single sensor (available Dec 2026)

  • Auto Accuracy Optimization:Automatically adapts to environmental changes (e.g., aisle moves, layout changes) to improve counting accuracy for none Re-ID standard counting (available Dec 2026)

  • View Attention metrics(available Dec 2026)

  • Auto Firmware Upgrade via RCS

  • Height filtering(adults vs. children, shadows, reflections) and object filtering (shopping carts, mannequins.)

  • Multi-sensor stitching up to 9 units for wider coverage with improved accuracy

  • Flexible mountingfor top-down or tilt installation (indoor and outdoor with custom mount)

  • Supports scheduled streaming of digital video output remotely for count accuracy validation
  • Optional features* ( incur additional charges):

    • Wi-Fi data transmission (via USB dongle)
    • Staff exclusion (press button, uniform identification, or Re-ID)
    • Re-ID functionalities
    • Gender and age-range estimation (available Dec 2026)
    • Customized activity analyticsvia posture recognition (e.g., lying down, QR scanning, opening/closing doors, product interaction) (available Jan 2027)
  • Auto configurations(height, zones, and more)

  • HD video streamingfor auxiliary surveillance

  • Encrypted Validation Video Playback for secure accuracy verification (available Q2 2027)

  • Web portal for local/remote device management, allowing to set Admin User for fully management or Read-only User for monitoring traffic/viewing device settings

  • Open API for easy system integration
  • Up to 16 discrete zones for metric collection
  • Low bandwidth requirement by transmitting data through Ethernet
  • Internal storage stores configuration settings and at least 90 days of data
  • Data packaged in XML packets and delivered via HTTP/HTTPs, FTP/FTPs, or daily e-mail
  • Power over Ethernet

Specifcations and User Manuals


Please visit  TDI HUB–our partner resource portal for complete datasheets and user guides. Alternatively, contact us at info@tdintelligence.com.
Portfolio
Buy Now
Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Youtube
Consent to display content from Youtube
Vimeo
Consent to display content from Vimeo
Google Maps
Consent to display content from Google

Download Now

Fill out the fields bellow to download instantly.

Please enable JavaScript in your browser to complete this form.
Name
Privacy Policy

Download Now

Fill out the fields bellow to download instantly.

Please enable JavaScript in your browser to complete this form.
Name
Privacy Policy

Download Now

Fill out the fields bellow to download instantly.

Please enable JavaScript in your browser to complete this form.
Name
Privacy Policy

Download Now

Fill out the fields bellow to download instantly.

Please enable JavaScript in your browser to complete this form.
Name
Privacy Policy

Download Now

Fill out the fields bellow to download instantly.

Please enable JavaScript in your browser to complete this form.
Name
Privacy Policy