Bosch Person / Car / Bike / Truck Analytics Tested

Author: Ethan Ace, Published on Jun 05, 2015

Automatically identify what objects are persons vs cars vs bikes vs trucks. That is the new feature and claim from Bosch in their newest IVA analytics (6.10 version). 

We first tested Bosch IVA here. With this new feature, we wanted to see how accurately this worked.

This video shows the basic setup process we used before testing:

We tested these analytics on multiple cameras in a busy outdoor scene, to answer these questions: 

  • Are cars, trucks, people, and bikes reliably detected and classified?
  • What objects are missed most often?
  • How do busy scenes impact performance?
  • Are VMSes able to receive these events distinctly?

************* ******** **** ******* *** ******* ** **** ** ***** vs ******. **** ** *** *** ******* *** ***** **** Bosch ** ***** ****** *** ********* (*.** *******). 

** *********** ***** *** ****. **** **** *** *******, ** ****** ** *** *** accurately **** ******.

**** ***** ***** *** ***** ***** ******* ** **** ****** testing:

** ****** ***** ********* ** ******** ******* ** * **** outdoor *****, ** ****** ***** *********: 

  • *** ****, ******, ******, *** ***** ******** ******** *** **********?
  • **** ******* *** ****** **** *****?
  • *** ** **** ****** ****** ***********?
  • *** ***** **** ** ******* ***** ****** **********?

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

Key ******** 

*****'* *** ****** ************** *** **** ******** **** **** *** people. ** *** ******** ******, ********* *** ******* ************** ** these ******* ****** * ~***' ***** ** **** *** ********, ******* *** objects.

********* ** ****** *** **** ********, **** ******** **** ******* together ********** ** * *****, *** **** ******* ****** ********** as ****.

******** **** ********** ***** ********, **** ****** ******* **** ********* **  and **** **** ******** ** *****. ****** ******** **** ************ missed ** ********** ** ******* **** ** ******.

*** ******** *********** *** ****** **************, ********* ***** ** ******* multiple **********/******** *****, ** **** ** *** ** **** ****** for ****** *********. *********** *** ****, ** ***** ************ *** known, *** ******* ******** ** *** ****/******** ***********.

***** *** ****** ********** **** ******* ******** ****** *** ********* XProtect, **** ******** ***** ******** ********** (*.*., ****** ********* **. vehicle *********, ***.).

***************/******

**** ***** ***** ***** ****** ************** *********, *****'* *** ********* take * **** ****** ** ******** ** ****** *** ******** providers **** ********/******* *** *******, ***** **** ******* ***** ************ for **** ****.

*******, ***** ****** ** ******* ** ***********, *** ***** ***** these ********* *** ********, **** **** ******** ****** ********** ******* objects ** ***** *** ** *************. ************, ** ********* ******** expectations ** ****** **. ******** (**** **** *** ******), ** proper ********* ** ******** ********* *****.

Firmware ************

***** ************ ** *** *** ********* ******** ** ******** *.**, available *** **** ******* ** ******* ** *** ***** ****. Firmware ** ********* *** ******** **** *** ***** ******** *******.

VMS ***********

*** ******* ****** ******** ****** ** ******* ******** ****** *** each *** **** ******* ** *** ******. **** ** ***** in *** ***** ****, ****, **** ****, ******, *** ******* "Detect *** ******" ***** ***** **********.

 

********* ******** ******** ** ** ** ******** ***** ********* ****** from ***** *** *******, ****** **** ***** *** *** ****** from *** ****** *** **** ** ********** **********.

******** ******* ****** *** ***** *** *** ******* ***** ******** events, **** ***** ****** *********.

Calibration *******

*********** ******** ***** ** **** ***** *********, *******, ***/** ****** in *** ******'* ***** ** ****. ** ********* *********** ***** Google **** ************ *** ***** ********* *** ***** ** ** be ****** ********, ****** * *** **** ** ****** ************.

**** ******* ** ******** ** *** ***** *****:

Detection ***********

**** ****** ******** ** *** *****, ****, ******, *** ****** are ********** ********* >**% ** *** ****. *** *******, ****** flags *** **** *** ****** *** ** **** ********* ******** to *** ********** ******* ** **** *****:

********* *** ******** *** ******, **** **** ******** ******* ** the *****.

**** *** ****** **** ********* ********** ** *** ******** ** cases, ****** ***** *** **** ******* **** ******, ********* ** size (*****):

*******, **** * **** (******** ** *********) *** *******, ** was ********* ********** ** *** *****, **** ** *** *** seen ****:

Misclassification ******

*******, ****************** **** ****** *** *****, *** ** * ****** extent, ******.

******* ******* ** "******"

**** ********, ****************** **** ****** ** ******** ******* ******* ******** when ***** *** **** ******** ** *** *****, ********* ** a ****** ****** ****** ** *** ******. **** *** **** often *** ** * ***** ** **** ********* ** * truck, **** ****:

** *** ************* *******, *** *********** ******* **** *** ****** is ****** **** *****. *********, ***** **** ** **** ******* a ******* ** *******, ********** ** *** ****. *******, ** some **** *********** ************ (*.*., ******* ** ******* ***** ****** are **********, ****-**** *********, ***.), ********* ** *** ******** ******* is *********.

***** ******* ********* ** *****

***** **** *** **** ****** *********** ****** ****, **** *********** every ***** ****** **** ********* ** * **** ** *** camera ** *** ***** ** *******. 

*** *******, * ***** ******* **** * ********:

** ******* * ******:

**** ** **** ** ***** *****, *** ****** ** *******, in * ******* ******* ** ******* ****** * ****, ****** the ****** *** *** *****************.

*******, ** *** ***** ****, *********, * *** *** ********** as * ******* ** ****:

 

Cameras **** 

*** ******* **** **** *** **** ****:

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

******* ******** ****** *.* *** *** **** *** *********.

Comments (14)

I'm curious how it would work with a different FOV. Two things I notice:

1) The camera seems relatively low, it looks like maybe 8-9' high. I would expect improved results from a higher vantage point with a little more downward tilt of the camera

2) The FOV seems exceptionally wide and you appear to be getting barrel distortion from the lens. Looks like a ~3mm lens. I'd suggest trying something no less than 4mm to get a flatter image and to keep the overall horizon line and geometry more squared up.

What was the logic in using this FOV? Was it more or less random in the sense you picked a "typical" scene, or did it conform to some recommendations from Bosch?

Are the analytics included with the camera purchase similar to the way Samsung bundles them in with the WiseNetIII. Overall they appear to work fairly well. It will be interesting to see how they perform over a longer period of time. I have had issues with "in camera" analytics where they just stop sending alerts and the camera needs to be rebooted.

They're included on all 7000/8000 series cameras at no charge (5MP starlight, 1080p HDR, 4K, etc.), but not on the 5000 series.

I think that Bosch is trying to do too much.

Avigilon approach of people/cars is much more reliable as I don't see any tech today that can really detect a the difference between a person and a bicycle.

Its better to do less in a good way than to do more poorly.

Finally, when a bike (bicicyle or motorbike) was present, it was correctly classified in all cases...

However, misclassifications were common for bikes...

Meaning other types were commonly misclassified as bikes, since no bikes were actually misclassified?

Ethan could you post some video clips from the intersection shot showing objects being detected? Also could you show images/video of the calibration setup for the intersection?

Just following up with the request for some video clips from the street shots.

I would really like to know detection ranges in day and night scenarios, with the lens length or angle used. That to me are the most important numbers along with reliability. Getting an idea of reliable ranges gives you an idea of how many cameras are needed for coverage.

In this test we were trying to get an idea of how well classification worked, not intending this to be a redo of their IVA detection performance. We tested that here (and in the rain). That being said, in this scene, I'd say detection of humans was reliable out to about 150' using the Bosch 5MP, or about a 285' HFOV, something like this:

I know I asked already asked but could you please post some video so we can see the detection range.

The issue with video clips here is that Bosch doesn't embed bounding boxes in the video (like Avigilon no longer does), and to my knowledge, no one has integrated the bounding boxes via metadata other than their own VMS, which we don't use. So we can see them live using Configuration Manager, but Genetec (which fully integrates the separate rules, sans bounding boxes) doesn't display the box.

So I can show you clips and you can see what is in the scene, but it's not going to show you bounding boxes. It's not going to show you events as they happen, either. Video associated with each event can be exported, but multiple events can't be exported with one stretch of video.

I will look through what we have saved as far as config/screen captures of Configuration Manager, as that's the only thing that'll show bounding boxes and path.

The cameras tested here don't support The Bosch CPP6 platform on which this IVA version is supported, therefore tests are i"not really relevant. Re-test on the Starlight 8000 and would be interesting to see results.

1. We used a Starlight 8000, the NBN-80052, as we mentioned in the report. The images in the report are taken from that camera.

2. As per Bosch's documentation IVA 6.10 is supported on more than CPP6.

IP cameras from Bosch are grouped by their common
product platform (CPP) generation. IVA 6.10 is
available on CPP4 and CPP6 based IP cameras

The NBN-932 (now numbered NBN-71027) is CPP4, and supported.

Login to read this IPVM report.
Why do I need to log in?
IPVM conducts unique testing and research funded by member's payments enabling us to offer the most independent, accurate and in-depth information.

Related Reports on Video Analytics

Best and Worst ISC West 2018 on Apr 16, 2018
ISC West 2018 had strong attendance, modest overall new products, and a surge in Artificial Intelligence marketing. First, here are 20+...
Eocortex / Macroscop VMS Company Profile on Apr 09, 2018
Eocortex is the international brand of Russian VMS manufacturer Macroscop. Macroscop was founded in 2008, and the Eocortex name created in 2013. We...
VMS New Developments Spring 2018 (Avigilon, Exacqvision, Genetec, Hikvision, Milestone, Network Optix) on Apr 04, 2018
What's new with VMS software? In this report, we examine new features and releases for Spring 2018 to track different areas of potential...
Favorite Video Analytic Manufacturers 2018 on Apr 02, 2018
Video analytics is one of the biggest trends in 2018, driven by marketing for Artificial Intelligence and Deep Learning. But what do integrators...
Destructive Video Analytics Hype Returns on Mar 27, 2018
It is not just Hikvision's false advertising campaign. With marketing money being pumped into deep learning, we are returning to the bad old...
Startup Image Intelligence 10X Accuracy Guarantee on Mar 26, 2018
An Australian startup, Image Intelligence, is targeting the biggest problem of video analytics, poor accuracy, with quite a claim: Is this...
Axis Z-Wave IP Camera Tested Poorly on Mar 20, 2018
Z-Wave is drawing notable interest for video surveillance use. In IPVM's initial coverage, 84% expressed interest in it, with nearly half being...
Video Analytics Usage Statistics 2018 on Mar 09, 2018
Video analytics is hot again (one of the top 2 trends going into this year), this time driven by deep learning and artificial intelligence. But,...
Directory of 50+ LPR / ANPR Providers on Feb 21, 2018
License Plate Recognition / Automatic Number Plate Recognition are a type of video analytics software that can identify and match license / number...
Hikvision DeepInMind Tested Terribly on Feb 15, 2018
While Hikvision is heavily marketing deep learning and 'AI' as their next big thing, new IPVM test results of their DeepInMind NVR shows their deep...

Most Recent Industry Reports

May 2018 Camera Course on Apr 20, 2018
Save $50 on early registration until this Thursday, the 26th. Register now (save $50) for the Spring 2018 Camera Course This is the only...
Global Real-Time Video Surveillance - EarthNow on Apr 20, 2018
A new company, EarthNow, with backing from Bill Gates, Airbus and more, is claiming that: Users will be able to see places on Earth with a delay...
Dedicated Vs Converged Access Control Networks (Statistics) on Apr 20, 2018
Running one's access control system on a converged network, with one's computers and phones, can save money. On the other hand, hand, doing so can...
April 2018 IP Networking Course on Apr 19, 2018
This is the last chance to register for our IP Networking course. Register now. NEW - 2 sessions per class, 'day' and 'night' to give you double...
Rare Video Surveillance Fundraising - Verkada $15 Million on Apr 19, 2018
Fundraising in video surveillance (and the broader physical security market) has been poor recently. Highlights are few and far in between...
'Best In Show' Fails on Apr 19, 2018
ISC West's "Best In Show" has failed. For more than a decade, it has become increasingly irrelevant as the selections exhibit a cartoon level...
Security Camera Cleaning Frequency Statistics on Apr 18, 2018
150+ integrators told IPVM how often they clean cameras on customer's sites and why.  Inside we examine their answers and break down feedback...
Worst Access Control 2018 on Apr 18, 2018
Three access control providers stood out as providing the most problems for integrators. In this report, we analyze the answers to: "In the...
Axis VMD4 Analytics Tested on Apr 17, 2018
Axis is now on its 4th generation of video motion detection (VMD), which Axis calls "a free video analytics application." In this generation, Axis...
Arecont CEO And President Resign on Apr 17, 2018
This is good news for Arecont. Arecont's problems have been well known for years (e.g., most recently Worst Camera Manufacturers 2018 and starting...

The world's leading video surveillance information source, IPVM provides the best reporting, testing and training for 10,000+ members globally. Dedicated to independent and objective information, we uniquely refuse any and all advertisements, sponsorship and consulting from manufacturers.

About | FAQ | Contact