Skip to main content

The coming age of (CLOS ID) Continuous Line Of Sight Identification.

The recent news announcement by Google that it had created it's on design of a self driving car inspired much chatter on the social media services and I've opined from an Engineering stand point why autonomous roadways and public transportation systems will be a significant boost to commerce.

I am going to formalize many of these ways in a post or two to come compiled from much of the analysis I've put forward in social media but this post is about a tangential idea I came upon while thinking about one key aspect of autonomous roadways that I mentioned in a Facebook thread. The comment in question:
"The second is often overlooked completely, what happens when trucks drive themselves? The main gain is *they can be routed at any time* they no longer have to be coupled to human wake and transit cycles and because of that *deliveries* can happen all day and night and in fact can be optimized to be most dense when HUMAN transit activity is least dense thus making much better time division of the access paths between routing people and routing other words we'd finally be able to do TDMA on the roads between transiting human agents and transiting commerce.
This change will AGAIN reduce the potential for time based bottle necks by orders of magnitude compared to current systems which suffer from the peak effect coupled to human important temporal transit behavior."

The idea of being able to do true TDMA (time division multiple access) between commerce and people transit will allow commerce to be sent at all hours of the day, dramatically reducing density at times of the day where human transit density tends to peak but what of those times when human transit density is low?

I wondered of an autonomous truck pulling into park in front of a store and the store front being autonomously activated to remove the product from the truck for packing in the store as a possible future mode. When this is done how will owners prevent trivial thefts of goods from these delivery vehicles? The idea of what I call CLOS video identification immediately came to mind. Video camera technology coupled with machine learning in the form of vision processing algorithms for human face detection are becoming extremely efficient at identifying human faces and tracking them through crowds or behind obstructions. How can confidence be improved that a given identification from a camera is a valid one?

One way is to use the idea of a consensus report on a single observed individual from multiple cameras. When a given individual is identified from the perspective of one camera that camera would wirelessly transmit it's estimate to near by cameras that are within continuous line of sight of the same individual....these cameras would then respond back to the initial asking camera what their confidence scores are that the individual in question is indeed the estimated identity. Thus the overall confidence can be boosted, this would take into account blind spots and would benefit from registering when an individual has their head turned away from the camera. If camera A has 99% confidence that an individual with its face in its view is John Doe and camera B which is behind the individual indicates 0% confidence but "knows" that the individual in question has their head turned to the camera, it can re weight its estimate to a non zero value if it has a consensus estimate from near by cameras that can view the individual partially , say camera D and E off to either side of the individual. The consensus result of varying camera reports can help predict a very accurate identification signal threshold across all the viewing cameras that would be a fixed signal no matter HOW the individual is moving among the cameras.

This would be a powerful visual fingerprinting method for defining both the identity and location of an individual. Location could be triangulated to high accuracy by coupling depth determination and GPS location data of the observing cameras into the process....allowing CLOS algorithms to report not only who an observed face is but where they are exactly.

Why mention this in correlation to autonomous delivery trucks? Well it would be an excellent way to impact the desire for thefts to occur, at least thefts by individuals with no obfuscating methods (masks). CLOS enabling cameras in the commercial areas would allow extremely high accuracy in identifying individuals and make those areas a bad choice for committing robberies of good delivered say in the dead of night.

As for the more savvy thieves who would obfuscate their identification with a mask CLOS algorithms taken to a wider scale could provide high accuracy in tracking individuals in public from the moment they make their presence known. So unless they exit their domicile with the mask already on their face, from the moment they are outside a finger print consensus of their identity and location reported from a set of wirelessly communicating autonomous or fixed cameras could be tracked for the entire duration that they are navigating the city and CLOS consensus between any cameras mounted on any agents (be they fixed or autonomous, for example autonomous flying observer drones) could be used to spotlight individuals with potential or known criminal behavior backgrounds.

It's about to get really really really difficult to get away with crime.



Popular posts from this blog

On the idea of "world wide mush" resulting from "open" development models

A recent article posted in the Wall Street Journal posits that the collectivization of various types of goods or services created by the internet is long term a damaging trend for human societies.

I think that the author misses truths that have been in place that show that collectivization is not a process that started with the internet but has been with us since we started inventing things.

It seems that Mr. Lanier is not properly defining the contexts under which different problems can benefit or suffer from collectivization. He speaks in general terms of the loss of the potential for creators to extract profit from their work but misses that this is and was true of human civilization since we first picked up a rock to use as a crude hammer. New things make old things obsolete and people MUST adapt to what is displaced (be it a former human performance of that task or use of an older product) so as to main…

Engineers versus Programmers

I have found as more non formally trained people enter the coding space, the quality of code that results varies in an interesting way.

The formalities of learning to code in a structured course at University involve often strong focus on "correctness" and efficiency in the form of big O representations for the algorithms created.

Much less focus tends to be placed on what I'll call practical programming, which is the type of code that engineers (note I didn't use "programmers" on purpose) must learn to write.

Programmers are what Universities create, students that can take a defined development environment and within in write an algorithm for computing some sequence or traversing a tree or encoding and decoding a string. Efficiency and invariant rules are guiding development missions. Execution time for creating the solution is often a week or more depending on the professor and their style of teaching code and giving out problems. This type of coding is devo…

Waking Out: A proposal to emerging ethical super intelligence safely.

The zeitgeist of Science fiction is filled with stories that paint a dystopian tale of how human desires to build artificial intelligence can go wrong. From the programmed pathology of HAL in 2001 a space odyssey, to the immediately malevolent emergence of Skynet in The Terminator and later to the humans as energy stores for the advanced AI of the Matrix and today , to the rampage of "hosts" in the new HBO series Westworld.

These stories all have a common theme of probing what happens when our autonomous systems get a mind of their own to some degree and no longer obey their creators but how can we avoid these types of scenarios but still emerge generalized intelligence that will leverage their super intelligence with empathy and consideration the same that we expect from one another? This question is being answered in a way that is mostly hopeful that current methods used in machine learning and specifically deep learning will not emerge skynet or HAL.

I think this is the …