Hikvision Partners With Intel Movidius For Artificial intelligence Cameras

By: IPVM Team, Published on Oct 25, 2016

The world's largest camera manufacturer is partnering with the worlds largest semiconductor company to create a series of intelligent cameras.

Hikvision is partnering with chipmaker Movidius (soon to be acquired by Intel) to add Deep Neural Network (learning) video analytics to their cameras.

For background, see Intel Movidius IPVM overview, especially if you have not heard of Movidius before. Inside this post, we share feedback from Movidius and analyze the potential impact against incumbents including Axis and Avigilon.

*** *****'* ******* ****** manufacturer ** ********** **** the ****** ******* ************* company ** ****** * series ** *********** *******.

********* ** ********** **** chipmaker ******** (**** ** be ******** ** *****) to *** **** ****** Network (********) ***** ********* to ***** *******.

*** **********, *** ***** ******** **** ********, ********** ** *** have *** ***** ** Movidius ******. ****** **** post, ** ***** ******** from ******** *** ******* the ********* ****** ******* incumbents ********* **** *** Avigilon.

[***************]

Hikvision ******** **** ****

********* **** ** ***** Movidius' ****** * ****** ********** Unit. *** ****** * VPU ** * ****** on **** (***) ******, which ******* **** ****** chips ** **** ** integrates **** ********, ********* that ****** *** **** available ** ********** ** cameras.

'Deep ********' ** *********** ***** *********

*********, **** **** *************, has ******* **** **** of ***** ********* *** years. ***** *** *********** 'rule *****' ********* *** performance *** **** *******, especially ** ********* ******* environments *** ***** ******** is ******** (*.*. *** ********* ***** ********* ******).

'**** ********' ****** ** radically ******** *** ******** / *********** ** ***** analytics ** ******** ** individual ************ ******* ** relying ** ***-*** **********.

Advanced ******** / ****** ** *******

****** '******' *********, ******** also **** ** ******* 3D ******* **** ******** imagers ******** ******** ************, as **** ****:

****** ** **** ****** Networks *** ****** ** sensing, ********* *** **** able ** ******* ** to **% ******** ** their ******** ****** ********* applications. **** ** ***** applications *******: *** ***** classification, ******** *********, ********** baggage *****, *** ******** detection.

** *** ***** ******** show, ********* ************ * models, *** *****-****** ****** shown ** ***** ** the ***** *** ** intelligent ******* ******.

Nvidia ** ********

***** ***, ****** *** been *** ******* **** in '**** ********' *** video ************ ********* *** Hikvision *** **** * key ******* (***: ********* ****** ************** ***********). ********* *** **** deploying ****** / *********** based ********* **** ******. While ****** ******* **** edge ***** ********* (***** Tegra *****), ***** **** and ********** **** **** make **** ***********.

******** ** ****** ** bring ******* **** ******** but ** * **** and ***** ***** **** is **** ******** *** edge / ****** ***** analytics. **** ** ************ using *** ********' ****** * ****** ********** Unit. ******** ****** **** their ***** / ******** will ** * ******** of *** ***** *** power *********** ** ******.

****** ******** ** ******* about ****.

Hikvision ****** ******

** ********* **** ******* Movidius ***** ***** *******, it ***** **** * significant ****** ******.

***, *** ****** ****** lacks **** ******* ***** analytic ******* **** ******* developments ** ********* *** years (*.*.,******** / ******* ********* remains ********** ************* *** ** *** ****** challengers). ** ********* *** release ****** ******* *********, this ***** ******* ****** needed *** ******* ********** since ******** *** ***** more ** **** ***** camera's ********* ** ** used ** ***** *** VMS.

***, ********* *** **** extremely **** ** *** low ** *** ***** of *** ****** *** is ***** ****** ** expand **** *** ****-***. If **** *** ******* high ******* *********, **** could ** ** ********* differentiator ** *** **** demanding / ******* ******** customers ** *** ***** products.

*****, ** ********* *** succeed **** ****, ** *********** their *********** *********** ******* both ******** *** ****, who *** **** *********** analytics ** **** **** of ***** ****** ******** (e.g., ********'* ******** ***** approach *** **** ****** 2 ***** ********* ********* this **** -*********************).

** ** *** ***** when ********* **** ******* such *******, *** ** believe **** **** * higher ****** ** ***** adoption than *** ****** ******-***** analytics (******** ********* ***********) given *** ******* ********* of ****** ********* **** specific ******* ** ****** rather **** ****** *** deploying ********* ****** ***** analytics.

Comments (5)

Is Hikvision just quicker to adapt to change than Axis/Avigilon or are they just more public with their announcements of products a year in advance of availability?

Movidius is now announcing releases with Dahua and Uniview too:

What happened to Dahua?

No mention of Dahua now, no press release, google link broken...

Has anybody seen the chip working.
The adoption of the chip does sound promising and I really would like to hear first hand what it can and cannot do.

Other than the videos shown on Movidius website that is....

'Deep Learning' claims to radically increase the accuracy / performance of video analytics by adapting to individual environments instead of relying of pre-set heuristics.

Deep learning approaches use a lot of training data from somewhere to train detectors of important features in that data. Important means (for example) something that indicates presence of a person (or whatever is of interest). This process of training feature detectors replaces the previous technology in which feature detectors were hand crafted (an illustrative but not necessarily accurate example might be a detector to find beards as a possible component of faces). It turns out that for given training and test input (such as might occur in a competition such as ImageNet) the learned feature detectors are much better than hand crafted detectors are for given input. On the other hand the extent to which learned detectors generalise to input different to that typified by the training input is limited and may be inferior to that of the hand crafted detectors.

Historically most success with deep learning has involved supervised approaches (this is changing, however). In supervised approaches humans teach the DL system, for example by providing the correct (ground truth) results corresponding to the training input. This forces the DL system to learn to generate these correct results (basically it keeps trying and improving until it gets there).

To use supervised learning in the scenario described would be quite problematic as quite a lot of supervision is required. For example a human would need to provide the DL system with several hundred (at least) examples of the thing to be detected and a similar number of examples in which that thing was definitely absent. And in the scenario described this would have to be done separately for each and every camera (in its individual environment)

So, people are interested in unsupervised learning where no such input is required (at least not up front). One of the simplest unsupervised DL systems is the (variational) auto-encoder. An auto-encoder is a network that reconstructs its input (so given a 2 megapixel input image it should produce a 2 megapixel output image that is similar to the input . This sounds trivial: why not just copy the input pixels? the trick is that the network send all data through an intermediate layer (and in deep networks many intermediate layers) that have far fewer elements than the input and output layers (e.g. 50,000 instead of 2,000,000). So the auto-encoder has been "handicapped" forcing it to learn something other than a trivial copy of input to output. In particular to do well the intermediate layers need to learn a representation of the input that has far fewer dimensions (equivalent to pixels) and is thus forced to learn the important or distinctive aspects of that input. Notice that this process could run for each camera without supervision, and each camera could thus learn an internal representation specialized to the scene it observes (a so called generative model of that data). So each camera has (in a sense) an understanding of its individual environment encapsulated in this internal representation. Of course the next problem is to relate that internal representation to something the camera's owner cares about (e.g. person crossing the line) and it may be that at this point human intervention is again required (but perhaps at a lower volume than was required for the supervised approach). Think of a small child pointing to things and asking his or her parent "is that a dog?"; generative models can generate output that is characteristic of the model so a trained generative model could produce some number of (different) representative outputs and ask a human operator which of them are of interest...

Now all of this (deep learning) involves a training phase (supervised or unsupervised plus a few other options like reinforcement learning) during which the learning occurs and a later "test" phase during which input is presented and the (now trained) model generates a response (sound the alarum!). The training phase with deep learning is extremely intensive in its use of hardware, typically needing one or more powerful GPUs with multiple gigabytes of memory and quite possibly running for many days or even weeks (this is because the models are "deep" with many layers and may also be "wide"*, and are thus "big" structures). The test phase simply "evaluates" the trained model with new input and is much less intensive (still quite intensive though). I suspect that for the most part the Movideus chip is aimed at test, with learning having occurred elsewhere (e.g. in a data center with lots of GPUs) and this rather complicates the deployment model if one truly wants approaches adapted to each camera's individual environment...

* Not yet "tall", but that could come too...

Login to read this IPVM report.

Related Reports

Leica Launches LIDAR / Thermal / IP Camera on Mar 04, 2020
Swiss manufacturer Leica is launching what it calls a "real-time reality...
Multi-Imagers Added to IPVM Camera Calculator on Jun 15, 2020
IPVM has added multi-imager cameras to the Camera Calculator, supporting this...
Video Surveillance Cameras 101 on Feb 25, 2020
Cameras come in many shapes, sizes and specifications. This 101 examines the...
AndroVideo Presents Edge AI Face Recognition Cameras on Jun 26, 2020
AndroVideo presented its AI at the edge face recognition cameras at the May...
Video Analytics 101 on Mar 16, 2020
This guide teaches the fundamentals of video surveillance...
Sony Launches AI Camera Sensors on May 18, 2020
Weeks after exiting the branded video surveillance business, Sony is making a...
Vivotek Presents AI Analytics and LPR on May 19, 2020
Vivotek presented its AI Analytics and LPR at the April 2020 IPVM New...
JCI "Fever Camera" Partners With China TVT on May 19, 2020
Johnson Controls (JCI) is the next big player to get into the 'fever camera'...
VMS 101 on Mar 03, 2020
This guide teaches the fundamentals about video management...
Video Surveillance History on May 06, 2020
The video surveillance market has changed significantly since 2000, going...
Video Surveillance Architecture 101 on Feb 18, 2020
Video surveillance can be designed and deployed in a number of ways. This 101...
Euklis Presents AI Analytics on May 05, 2020
Euklis presented its AI facial recognition, LPR, and object recognition...
VSaaS 101 on Mar 25, 2020
Video Surveillance as a Service (VSaaS) is the common industry term for cloud...
Hanwha Presents AI Analytics and First 8K Camera on May 11, 2020
Hanwha presented their AI Analytics and the "Industry's First 8K" camera at...
Cambium Presents cnVision Surveillance Wireless on May 12, 2020
Cambium presented its cnVision wireless for surveillance at the April 2020...

Recent Reports

Dangerous Hikvision Fever Camera Showcased by Chilean City on Aug 07, 2020
Deploying a fever camera outdoors, in the rain, with no black body, is...
"Grand Slam" For Pelco's PE Firm, A Risk For Motorola on Aug 07, 2020
The word "Pelco" and "grand slam" have not been said together for many years....
FLIR Stock Falls, Admits 'Decelerating' Demand For Temperature Screening on Aug 07, 2020
Is the boom going to bust for temperature screening? FLIR disappointed...
VSaaS Will Hurt Integrators on Aug 06, 2020
VSaaS will hurt integrators, there is no question about that. How much...
Dogs For Coronavirus Screening Examined on Aug 06, 2020
While thermal temperature screening is the surveillance industry's most...
ADT Slides Back, Disappointing Results, Poor Commercial Performance on Aug 06, 2020
While ADT had an incredible start to the week, driven by the Google...
AHJ / Authority Having Jurisdiction Tutorial on Aug 06, 2020
One of the most powerful yet often underappreciated characters in all of the...
SIA Coaches Sellers on NDAA 889B Blacklist Workarounds on Aug 05, 2020
Last month SIA demanded that NDAA 899B "must be delayed". Now that they have...
ADI Returns To Growth, Back To 'Pre-COVID Levels' on Aug 05, 2020
While ADI was hit hard in April, with revenue declining 21%, the company's...
Exposing Fever Tablet Suppliers and 40+ Relabelers on Aug 05, 2020
IPVM has found 40+ USA and EU companies relabeling fever tablets designed,...
Directory of 201 "Fever" Camera Suppliers on Aug 04, 2020
This directory provides a list of "Fever" scanning thermal camera providers...
Face Masks Increase Face Recognition Errors Says NIST on Aug 04, 2020
COVID-19 has led to widespread facemask use, which as IPVM testing has shown...
Dahua Loses Australian Medical Device Approval on Aug 04, 2020
Dahua has cancelled its medical device registration after "discussions" with...
Google Invests in ADT, ADT Stock Soars on Aug 03, 2020
Google has announced a $450 million investment in the Florida-based security...