Uniview Deep Learning Camera Tested

By Ethan Ace and Rob Kilpatrick, Published Jul 14, 2020, 01:33pm EDT (Research)

*******'* ********* ************* ********* ****** ***** *********. ***, **** **** ******** ***** Prime ****** **** ******** *******, **** an "******** ********* *********", *** *** well ** ***** *** ****** ****?

IPVM Image

** ****** *** ****** ***********-***, *********:

  • *** ******** *** ****** *** ******* classification?
  • **** ** ****** ****** **** ********, running, ** **********?
  • **** ** ***** ***** ** ****** outdoor *******?
  • **** ** ****** ****** ****** ******* of ***** ******?
  • *** *** *** ** ****** ******?
  • **** ** ********* ** *****-***** *****?

*******

***** *** ********-*** ****** ****** ****** or ******** ** *** ***** *** did *** ******* ** ***** *******, rain, ** ******* *******, ** ******** from ***** ***** ****** ******* ** other ** ****** ** **** ****** (such *******************), **** ***** ******* *** *** wheels ************ ******** *** ********** ** human, *** ********** ******** **-********** ****** throughout *******, ******* *** ******.

Vs. ***** *********+ / *** *** ********* ********

*******'* *********** ** ***** ******** ** similarly ****** *********** ******** ****** **** Dahua *********+, ***, ** ********* ********.

  • *******'* **** ******** ****** ********* ********* to*****'* *********+, ***** **** ************ ********** ***** animals ** ****** *** *********** ** parked ********. *******, *******'* **** *** integration *** ************** ** ******* ***** as ****** **** ****** *** ******* in *********+.
  • *******'* ** ********* ****** *********'* ***** ****** ********* (***), ***** ******* ** *****/***** ******* and ******, **** **** ***** ********* range (~** *** **. ** ** Uniview).
  • *********'* ******** ******* *** *********** **** **** ***** ****** ***** did *** ******* *** ******* ******, including ***** ******* *** *******/***********. ******* to *******, ******** ********** *********** ** parked ********, *** *** *** ****** vehicle ***** ** ******.

No ****** ******* / ****** *** ******** **********

** *** *******, ****** *** ******** were ********** ********, **** ** ****** objects (****** **** ************** ******, ********* below). ***** ******** **** ********** ******** when *******, ********, *** *******, ***** here:

IPVM Image

Wheels ********** ** ******

****** *******, *** ******* ** ****** regularly ********* ** *** ******, *********** them ** ******, ***** *****:

**** ******** *** *** **** ** any ***** ****** ********* ******** ** have ****** (****** ** ***** ****** **** *** *******).

Large ******* ********** ** ******

*******, ***** ******* (**** ** *** dog, *****) **** ************ ********** ** people ** *** *****, ********** ***** alerts.

*** ******** *** *** ******* ** small ******* ** *** ***** ** view, **** ** ****, *********, *******, or *****.

No ****** ** ****

*******'* ** *** *** ******* ** heavy ****, ********** ***** ******** ****** in *** *******.

No ****** ** ******* / *******

** *** *****, *** ******* ** camera *** *** ***** ** *******/****** foliage ** *******, *** **** ****** typical ****** ** ***** ******.

No ****** ** ******* / ****** *******

*** ******* ** ****** *** *** alarm ** ****** ******* ** ****** false ******, ******. *** *******, ****** turning **/*** *** ****** ******* *** not ******* ***** ******, ****** ****** in **** ***** ** ******* *** non-AI *********.

Person ********* ** ~** ***

** *** *****, *** ******* ** camera ******** ****** ** ~** ***/~**' distance ***** * ~**-**° ***. **** PPF *********** ** ******* ** *********** such ** **** ****** (*** *** ********) ********** **,***** ***/***,***** *********+, ************ ********/**********

IPVM Image

No ***** ***** ******** ***** ***********

** *** *******, *** ********-***'* ******** events *** *** ********* **** ***** party *****, ********* ********, *****, *******, Milestone, *** ******* *****. ** ****** nor ******** ***** **** **** ** these *****.

Similar **** / ************ ** ******* *******

*** ********-*** ** ******* **** *** construction ** *********** ****** *******, **** as ***** *** *********, ***** ****, with *** ***** ***** ***** *** similar ******:

IPVM Image

*******

*** ********-*** *** ** ********* ****** price ** ~$***-*** ***, ******* ** Dahua's *** (*******,~$*** ***) ********* ********(**-*********-***,~$*** ***).

Uniview **** ******** ****** *** *********

*** ******* ********-*** ****** **** * HiSilicon ***, **** *****.

IPVM Image

Versions ****

*** ********* ******** ******* *** **** in *** *****, *** ****** ** the **** ** *******:

  • ******* ********-***:*********-*************

******* ******* ** **** * *** firmware ******* ** ********* ** ***********, but *** ********* ** *** **** of *******, ***** **** ******* **** improve ************** ***********. ** **** ****** with **** *** ******** **** *********.

Comments (11)

Uniview ~$300, Hikvision ~$300, Dahua ~$300

IPVM Image

Chinese innovation at its best.

Agree: 2
Disagree: 1
Informative
Unhelpful: 2
Funny: 5

this is a nasty comment that serves no purpose, not even a cynical rant.

its priced at this point since that is what the buyer is willing to pay, and many cameras look this way, not just the Chinese.

Agree: 5
Disagree
Informative
Unhelpful
Funny

Lots look this way because these 3 companies OEM for like 200+ companies.

Agree: 6
Disagree
Informative
Unhelpful
Funny

its priced at this point since that is what the buyer is willing to pay, and many cameras look this way, not just the Chinese.

that sounds like a rational explanation: shared market forces, e.g. price/functionality, drive similar product outcomes.

sounds a lot like C.E.:

Convergent evolution is the process by which unrelated or distantly related organisms evolve similar body forms, coloration, organs, and adaptations.

IPVM Image

Agree
Disagree
Informative
Unhelpful
Funny

Ethan,

Informative article, as always. Presumably this camera's analytics performance should improve over time. Does it retrain itself? Does the manufacturer set expectations on rate of improvement, time to steady state, etc.? This AI approach makes a lot of sense and is probably the way all camera analytics will go in time.

Agree: 1
Disagree
Informative
Unhelpful
Funny

No, it does not retrain itself. Analytics which actually self-learn are pretty rare. Avigilon's H5/H4 self-learning analytics are probably the most well-known example.

The learning on most "deep learning" cameras comes from a pre-trained neural network, which is done in development, and updated in the camera(s) through firmware updates.

I would agree with you that AI is likely to replace "standard" analytics over time. It's getting more and more common, and there are a number of options with decent performance at this price point. Is it on the level of top-performing analytics? Not yet, but compared to standard VMD or intrusion analytics, a huge improvement.

Agree: 1
Disagree
Informative: 2
Unhelpful
Funny

after looking at so many cameras and AI, analytics and the shortcomings of their algorithms. have the manufacturers ever reached out to you guys (IPVM) to get advise and even ask you to assist with testing updated firmware or refined algorithms on these and other cameras? or do they just not care there is so many false positives.

Agree
Disagree
Informative
Unhelpful
Funny

Faheem, usually manufacturers give us feedback and updated firmware. It's almost become a joke inside of IPVM that each time we tell manufacturers our preliminary results show problems, they respond with some variant of (I am only slightly being facetious) "Oh, no, no, we'll get the good firmware now."

Agree: 1
Disagree
Informative
Unhelpful
Funny: 1

LOL, ya well thats what happens when you give excellent information, advise and testing services for free to them. you need to go to them and bundle it with a heft price tag then they would have taken you serious.

i have the exact same issue with uniview. no matter how many examples and test i do on their alphaview ptz to show them the inefficiencies of the algorithm and try to get them to fix it, not only for my benefit but for theirs as well. we go no no where.

anyways keep up the good work

Agree
Disagree
Informative
Unhelpful
Funny

What SoC did it use? Hisilicon?

Agree
Disagree
Informative
Unhelpful
Funny

Yes, the IPC264SA-DZK used a HiSilicon SoC, I added a section to the report with the SoC used.

Agree
Disagree
Informative
Unhelpful
Funny
Subscribe to IPVM Research to read the full report.
Why do I need to subscribe?
The IPVM Research Service includes products tests and shootouts plus competitive and financial analysis, helping decision-makers better evaluate purchasing, partnering, developing, and/or competing against companies in physical security.
Already have an account?
Loading Related Reports