Detection, Classsification, Recognition and Identification (DCRI)

By: John Honovich, Published on Feb 04, 2013

Detection, classification, recognition and identification is all very easy until you put it in practice. Then you realize that there are big practical and subjective problems that make using them difficult.

Academically, the terms are straightforward and reflect what they mean in real English:

  • Detection - The ability to detect if there is some 'thing' vs nothing.
  • Recognition - The ability to recognize what type of thing it is (person, animal, car, etc.)
  • Identification - The ability to identify a specific individual from other people

Obviously, each level is harder and requires more detail, going from detection to recognition to identification.

Many manufacturers overview these categories including an Axis tutorial and a Bosch white paper [link no longer available]. For instance, here's the PPF chart that Bosch uses to provide concrete numbers:

And here is the Axis table:

Both relate a targeted PPF number to a certain level. While Bosch uses imperial and Axis uses metric units, the two manufacturers numbers are way off.

For identification:

  • Bosch recommends ~50ppf
  • Axis recommends ~80ppf
  • The Swedish National Lab recommends ~150ppf (cited inside the Axis paper)

Your first reaction might be, "What is going on here? Is someone wrong, lying or confused?"

Get Notified of Video Surveillance Breaking News
Get Notified of Video Surveillance Breaking News

Any of them might be the case individually, but, unfortunately, two fundamental issues exist with using these metrics.

2 Fundamental Issues

First, the terms are inherently subjective and depend on the perception and preferences of the individual viewer.

What is good enough for 'identification' can vary considerably among people. In our trainings and presentations, we have seen passionate debates break out about what passes for identification.

Try this for yourself. Look at the 3 images side by side below:

Which one, for you, is sufficient for identification? 40 (on the left), 60 (in the center) or 80 (on the right)?

In an IPVM class, it was a three way tie.

You face the same challenges in determining what's good enough for detection. Again take these image side by side:

What makes this particularly challenging is that seemingly modest changes in visual details captured can mean the difference of 2x the number of pixels per foot, which can have a massive impact on camera layouts and project design.

Warning

When people look at an image by themselves, the answer often appears 'obvious'. It is only when they confer with other people that it becomes a debate as they realize many others have different perceptions.

How do you resolve this scientifically? It is a tough call and ultimately the 'winner' is whoever is paying for the system.

Pixels and Image Quality

The other issue is that the same number of pixels will deliver different image quality depending on the time of day. You might be OK in perfect even lighting conditions with 50ppf for identification but if the sun sets or rises in line with the camera you might need more. Worse, if you only have street lighting at night, you still might need twice as many pixels per foot.

What to Do?

Using these terms and thinking about them as a goal is useful. Just do not treat this as simple math that is guaranteed to always work.

Most importantly, set the right expectations:

  • What level of details does the user/buyer/decision maker really want? Decide with a visual example, don't just say 'detection' and hope they agree when the system is commissioned.
  • What lighting or environmental issues are faced and how much of an impact will it have? Make this clear up front with the user/buyer/decision marker so they understand the inherent challenges in a real world operation.
Comments (16) : PRO Members only. Login. or Join.

Related Reports

Camera Focusing Tutorial on Oct 14, 2019
Camera focus is fundamental to quality imaging. Mistakes can significantly reduce details, making cameras less effective. In this guide, we...
Avigilon H5A Analytic Cameras Tested on Oct 07, 2019
Avigilon has released its H5A analytic cameras, claiming to "detect more objects with greater accuracy even in crowded scenes." We tested the...
Vivotek 4K S-Series Camera Tested on Sep 30, 2019
Vivotek's highest-end S-series camera claims "Supreme Night Visibility", "Smart IR II", "Smart Stream II", "WDR Pro for unparalleled visibility in...
Consumer IP Camera Analytics Shootout - Arlo, Google / Nest, Amazon / Ring, Hikvision / Ezviz, Wyze Cam, Yi Home on Sep 26, 2019
AI analytics are hitting the mainstream in the consumer camera market, with entrants Wyze and Yi Home releasing free people detection on their...
Hikvision Acusense Analytics Tested on Sep 23, 2019
Hikvision touts "The Magic Behind It All" in their new Acusense line are 'deep learning algorithms' inside these cameras and recorders. But how...
Axis Perimeter Defender Improves, Yet Worse Than Dahua and Wyze on Sep 19, 2019
While Axis Perimeter Defender analytics improved from our 2018 testing, the market has improved much faster, with much less expensive offerings...
Vivotek "Neural Network-Powered Detection Engine" Analytics Tested on Sep 17, 2019
Vivotek has released "a neural network-powered detection engine", named Smart Motion Detection, claiming that "swaying vegetation, vehicles passing...
Panasonic 4K Camera Tested (WV-S2570L) on Sep 13, 2019
Panasonic has released their latest generation 4K dome, the WV-S2570L, claiming "Extreme image quality allows evidence to be captured even under...
Uniview Pro 4K Camera Tested (IPC3238ER3-DVZ) on Aug 29, 2019
In our 8MP / 4K Fixed Lens Camera Shootout, Uniview's low end 8MP was firmly in the middle of the pack. Does their higher end Pro Series 4K camera...
Anyvision Facial Recognition Tested on Aug 21, 2019
Anyvision is aiming for $1 billion in revenue by 2022, backed by $74 million in funding. But does their performance live up to the hype they have...

Most Recent Industry Reports

Axis HD Analog Encoder Tested on Oct 11, 2019
Two years after declaring "Everything is IP", Axis has released their first HD analog encoder, the P7304, with support for AHD, CVI, TVI, and SD...
Dahua Celebrates PRC 70th Wearing Communist Party Hammer and Sickle on Oct 11, 2019
Dahua celebrated the PRC's 70th anniversary with a video of various Dahua employees wearing China Communist Party hammer and sickle pins as shown...
Last Chance - Register Now - October 2019 IP Networking Course on Oct 10, 2019
Last Chance - Register Now - Fall 2019 IP Networking Course. The course starts next week. This is the only networking course designed...
Network Optix NxWitness 4.0 Tested on Oct 10, 2019
Network Optix released Nx Witness 4.0, proclaiming new features like a deep learning analytics metadata SDK, increased H.265 support, and UX...
HID Fingerprint Reader Tested on Oct 09, 2019
HID has released their first access reader to use Lumidigm optical sensors, that touts it 'works with anyone, anytime, anywhere'. We bought and...
ONVIF Suspends Dahua and Hikvision on Oct 09, 2019
Dahua and Hikvision have been 'suspended', and effectively expelled, from ONVIF, immediately following US sanctions being placed on the 2 mega...
Hikvision And Dahua Sanctioned For Human Rights Abuses on Oct 07, 2019
In a groundbreaking move that will have drastic consequences across the video surveillance market, Dahua and Hikvision have been sanctioned by the...
Avigilon H5A Analytic Cameras Tested on Oct 07, 2019
Avigilon has released its H5A analytic cameras, claiming to "detect more objects with greater accuracy even in crowded scenes." We tested the...
Crisis At China's Largest VMS Provider, Netposa, Now State-Controlled on Oct 07, 2019
NetPosa, which bills itself as the PRC's largest VMS provider, is in a crisis. The firm is pursuing huge unpaid bills from clients, and its...
Knightscope Sells Just 1 Net New Robot In 6 Months on Oct 04, 2019
For the first half of 2019, US government records show that Knightscope has sold just 1 net new robots ('machines-in-network'), inching up from 52...