Member Info for johnchucka

Probably way off and will make Colin smile but here goes.

Semicast made reference to the A team and Mr Dee not Tee?? something about 'handsome'??I don't have the quote but Face aka Faceman was the pretty boy of the bunch so that could lead to this recent SEE patent which is more focused around greater focus on facial feature detection than the pure Eye/head feature/position detection that most other patents closely focus upon. It has a 9 and a 40 reference which are copied below.

HIGH FRAME RATE IMAGE PRE-PROCESSING SYSTEM AND METHOD
https://worldwide.espacenet.com/publicationDetails/description?CC=WO&NR=2019241834A1&KC=A1&FT=D&ND=3&date=20191226&DB=&locale=en_EP#

[0026] Referring initially to Figure 1 , there is illustrated an image processing system 100 according to an embodiment of the invention. As illustrated in Figures 2 and 3, system 100 is particularly adapted for operating as a driver monitoring system for monitoring a driver 102 of a vehicle 104 during operation of a vehicle 104. System 100 is further adapted for performing various image processing algorithms on the captured images such as facial detection, facial feature detection, facial recognition, facial feature recognition, facial tracking or facial feature tracking, such as tracking a person’s eyes. Example image processing routines are described in US Patent 7,043,056 to Edwards et al. entitled“Facial Image Processing System” and assigned to Seeing Machines Pty Ltd (hereinafter“Edwards et al "), the contents of which are incorporated herein by way of cross-reference.

[0009] In some embodiments, the region of interest is the entire image.

0040] The raw image data, gaze position data and other data obtained by vision processor 118 is stored in memory 116.

Andrew Schneider
Global B Software Integration Engineer
Specializing in software robustness, integration, and testing.
Supporting the launch of GM's new digital vehicle platform (Global B)
https://www.linkedin.com/in/andrew-schneider-virginia-tech/

GM shows off 'digital vehicle platform' enabling more in-car tech and OTA updates
It appears to have dropped the sobriquet "Global B," but General Motors' new electrical architecture has bowed in drawings and video. This is the "digital vehicle platform" GM president Mark Reuss spoke to Reuters about in 2015, saying it would move a great deal of a vehicle's computer work to the cloud and enable over-the-air updates. Reuss took the microphone for the debut, too, saying, "Our new digital vehicle platform and its eventual successors will underpin all our future innovations across a wide range of technological advancements, including EVs and expanded automated driving."
https://tinyurl.com/wkzypht

TLS,
My guess was Semicast was referring to Templeton Peck aka Faceman rather than MR T. FMS
Some Qualcomm Investors day 2019 Auto talk here.
https://www.youtube.com/watch?v=Ce7_XdrWnLs
Also Friday is Patent day but it's quiet out there across the board.

Correction. GM Digital Vehicle Platform link replaces CT5 link.

Why General Motors won’t be showing its next electric car at CES
'Either way, General Motors would rather wait until the right time to unveil the car than rush it under the spotlights. “We want to do it right, because we’ve got a very powerful story to tell,” Barra concluded'.
https://www.digitaltrends.com/cars/general-motors-skipping-ces-2020-because-its-car-isnt-ready/
https://www.dailymotion.com/video/x79677k
https://www.gm.com/masthead-story/digital-vehicle-platform.html

Why General Motors won’t be showing its next electric car at CES
'Either way, General Motors would rather wait until the right time to unveil the car than rush it under the spotlights. “We want to do it right, because we’ve got a very powerful story to tell,” Barra concluded'.
https://www.digitaltrends.com/cars/general-motors-skipping-ces-2020-because-its-car-isnt-ready/
http://cadillacsociety.com/2019/12/23/most-cadillac-ct5-models-to-start-arriving-in-first-quarter-2020/

While we're on the subject of Glare.
Subaru's Driver Monitoring System explained.
'This relatively new technology does have some limitations. In order to work effectively, the DMS requires an unimpeded view of the driver’s face that can be reduced or completely blocked by a face covering or hat casting shade. And while the infrared camera can see through glasses, it can be affected by reflections or dark or polarised sunglasses'.
https://www.whichcar.com.au/car-advice/how-do-driver-monitoring-systems-work

TLS,
The SEE patent that describes in/out camera fusion is;
SYSTEM AND METHOD FOR IDENTIFYING A CAMERA POSE OF A FORWARD FACING CAMERA IN A VEHICLE
https://worldwide.espacenet.com/publicationDetails/description?CC=US&NR=2019266751A1&KC=A1&FT=D&ND=3&date=20190829&DB=&locale=en_EP#
I could not see any reference to radar but it could be referred to as something I don't recognise. It also does not refer to gaze being limited by dark glasses as the Delphi Patent does. We knew why SEE always stated the importance of gaze detection thru dark glasses for driver in car monitoring but I think it's interesting that Delphi are limited by it especially in the application they describe where the camera and Radar images or frames of reference are aligned as a safety tool to detect external objects.
This I consider another barrier to entry as my own theory is that DMS in/out fusion is an important part of the data collecting process in developing the baseline safety architecture. This capacity ,and example of it's necessity to any systems development as well as the data collection is demonstrated in the recent Harman patent where the detected human gaze at external objects acts as an important back up , double check or support for the vehicle sensor system especially where the sensor system fails to recognise an object or threat.
My logic says that if other systems like the Aptiv's are handicapped by such a common feature like dark glasses then they are all but useless to the evolution of a baseline safety system . Dark glasses are not even an edge case scenario and the Aptiv system is incapacitated from what I can tell.
Interested to hear your thoughts.

Maybe this guy will be in the audience.
Clive Berrington
Contracts & Procurement Director at Network Rail
https://www.linkedin.com/in/clive-berrington-3bb0905/?miniProfileUrn=urn%3Ali%3Afs_miniProfile%3AACoAAADmqz8BTLyHndfLkjCSbcw0OGjmNtQKhzQ

Semicast post
https://www.youtube.com/watch?time_continue=19&v=QQpKPwtDdBg&feature=emb_logo

Hi TLS,
(Need to be brief so will look into further over coming days)

It does look like they are developing the in- Camera/out-Radar sensor fusion side of things. SEE patents I believe are both Camera in /Camera out so I'm not sure of the overlap capacity with Radar etc.
As to the question of who is doing the camera side of things I got to looking at a Aptiv Patent (below). It bought up an interesting point regarding the Dark Glasses and Object detection which is mentioned in 023 below which got me thinking about whether SEE have the same issue or have they overcome it. Will come back to this.

DELPHI TECH LLC 2020-01-02
VERIFICATION OF VEHICLE OPERATOR AWARENESS BEFORE TRANSITION FROM AUTONOMOUS-MODE TO MANUAL-MODE
[0023] Situations may arise when it is difficult to determine the gaze-direction 26 of the operator 18 because, for example, the operator is wearing dark glasses, and/or there are instances of the primary-targets 44 that are so close together that a change in the gaze-direction 26 necessary to view each instance of the primary-targets, is difficult to distinguish. Accordingly, the verification 60 may include as an addition or alternative to monitoring the gaze-direction 26 that the operator 18 has performed a visual-sweep 80 around the host-vehicle 12 more recently than a sweep-time 82. If the gaze-direction 26 can't be detected or distinguished, movement of the head of the operator 18 may be tracked to determine that the visual-sweep 80 has been performed by the operator 18. Requirements for completing the visual-sweep 80 may include looking at the rear-view and side-view mirrors, a general scan of the area forward of the host-vehicle, and moving the head enough to indicate that the blind-spots have been checked.
https://worldwide.espacenet.com/publicationDetails/description?CC=US&NR=2020004244A1&KC=A1&FT=D&ND=3&date=20200102&DB=&locale=en_EP#

Semicast Research@semicast_res
Coming on Feb 4. We’ll know soon after if the Super Cruise driver monitoring system is still blinded by bright, direct sunlight. Today’s episode has been brought to you by the numbers 9 and 40.
https://www.cnet.com/google-amp/news/cadillac-escalade-suv-debut/

GM to debut autonomous car without a steering wheel, report says
https://www.foxnews.com/auto/gm-autonomous-car-steering-wheel

Who better to debate Autonomous Vehicles with Alex Roy than Dr. Mark Rosekind - former head of the National Transportation Safety Board (NTSB), the National Highway Transportation Safety Administration (NHTSA) and Fatigue Countermeasures at NASA - currently the Chief Safety Innovation Officer at Zoox, and one of the most opinionated and colorful characters in America.
https://noparkingpodcast.com/podcast/mark-rosekind

Semicast Research retweet.
WRI Ross Center@WRIRossCities
“Safety can’t be the privilege of few… we hope that safe cars in India is going to be a standard for the future,” says @TataMotors’s JSR Kutty at #TTDC20. http://ow.ly/Xdme50xXsjk #Vision2Action

TLS,
I'm thinking/guessing the SEE camera Calibration IP maybe related to the Toyota and Waymo patents and the Toyota and Honda Robotics patents look to be describing a similar Robot/ Human interaction and I'm confident SEE are working with both of them in Auto.

'Seeing Machines is a world leader in human-machine interaction and an industry leader in the artificial intelligence (AI) technologies which enable machines to see, understand and assist the people who are using them'.

SEE also have Robotics enthusiasts on their payroll.
Shervin Emami
Senior Computer Vision & Robotics Engineer
https://www.linkedin.com/in/shervinemami/?miniProfileUrn=urn%3Ali%3Afs_miniProfile%3AACoAAAMgdyAB2jvRJOIi4rmvvAdDsWVjRjyU52I

ASSISTANCE SYSTEM, METHOD, AND PROGRAM FOR ASSISTING A USER IN FULFILLING A TASK
[0016] The assistance system enables a successful cooperation between the user and the robot by an efficient and intuitive communication. Improved communication minimizes human effort and maximizes task progress. The assistance system benefits from vastly available unstructured and semi-structured task descriptions by harvesting them and making them available to the cooperation of the user and the robot in performing the task. Moreover, the assistance system is able to adapt quickly to an individual user and task idiosyncrasies.

[0020] The invention is particularly suited when applying belief tracking of the task progress, communication state, and human state, e.g. using methods known from dialog state tracking as Partially Observable Markov Decision Processes (POMDP), possibly also implemented as a hierarchical belief tracking ( Williams, J., Raux, A., Ramachandran, D., & Black, A. (2013). The dialog state tracking challenge. In: Proceedings of the SIGDIAL 2013 Conference (pp. 404-413 ); Williams, J. & Raux, A. & Henderson, M. (2016). The dialog state tracking challenge series: A review. Dialogue & Discourse, 7(3), 4-33 ). The personalization of the communication between the user and the assistance system or the robot is achieved by learning user characteristics in the interaction between the assistance system and the user.

[0024] In a preferred embodiment, the processor is configured to monitor the task progress by interpreting the user input, the user input including at least one of an oral (acoustic) user input, at least one visually perceivable gesture of the user, a tactile input of the user, and by interpreting the image data acquired from a visual sensor, for example, at least one video camera. The visual sensor captures the image data which depicts the user and preferably the at least one object currently involved in the task.

[0025] A close cooperation between the user and the assistance system is achieved. The assistance system mirrors traditional cooperation between human workers acting together, for example, using speech as a typical communication channel for negotiating a shared workflow when performing a task. The cooperation with the assistance system is therefore intuitively understandable for the user. This is in particular the case because the entire task is divided into individual steps and/or subtasks. The subtasks may each consist of a plurality of steps. The representation of the entire task defines the relation of the individual subtask and/or steps and therefore is not limited to a step-by-step sequence having a strict timely order.
https://worldwide.espacenet.com/publicationDetails/biblio?II=36&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200109&CC=US&NR=2020012670A1&KC=A1#

Similarity here between
Toyota 2020-01-16
METHODS AND SYSTEMS FOR DETERMINING TELEOPERATING USER INTENT VIA EYE TRACKING
https://tinyurl.com/wghxa

Continental 2020-01-14
Method for warning a driver of a vehicle about a potentially critical traffic situation
BACKGROUND OF THE INVENTION
The alertness of a driver of a vehicle to the traffic conditions can fluctuate considerably during a journey. It is thus possible for a driver to identify, or respectively react to, critical situations which suddenly occur later than would be the case if he was fully alert. The driver's state of alertness can be monitored, for example, by means of an interior camera, wherein, if it is identified that the driver is not sufficiently alert, he can receive a notification, by way of example, of this deficiency.
Warnings generated by vehicle systems for a driver of a vehicle regarding identified critical traffic situations are usually based on physical calculations, by way of example with respect to a collision that may possible occur. The disadvantage of these is that even if the driver is alert, a warning might be triggered too late, in the event of an imminent potentially critical traffic situation, such that the driver does not have enough time left to recognize the possible critical circumstance in the traffic conditions. This is particularly true of drivers who have relatively little driving experience of the relevant traffic situations or of particularly complex traffic situations which can overwhelm even experienced drivers. As a result, traffic safety can be considerably compromised. On the other hand, a driver can also be distracted by warnings which are output and which he considers to be too premature or respectively unnecessary, and this can therefore likewise jeopardize traffic safety.

An aspect of the invention is based on the realization that the alertness of a driver of a vehicle to the traffic conditions or a driven route is frequently dependent on his knowledge of the route or the existing volume of traffic on the route. A driver's expectations, based on experience, regarding the respective traffic situations concerning the route are fundamental to this. For example, a situation can arise that a driver's alertness is permanently reduced because he believes that the traffic situation patterns will be replicated on a route which he drives repeatedly. This can be the case, for example, if the driver's commute is identical every day.
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200114&CC=US&NR=10532696B1&KC=B1#

Similarities with earlier posted Toyota Patent;
Toyota 2020-01-16
VEHICLE SYSTEMS AND METHODS FOR REDIRECTING A DRIVER'S GAZE TOWARDS AN OBJECT OF INTEREST
https://worldwide.espacenet.com/publicationDetails/biblio?II=4&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200116&CC=US&NR=2020018952A1&KC=A1#

Waymo 2020-01-16
VEHICLE SENSOR VERIFICATION AND CALIBRATION
An example method involves detecting a sensor-testing trigger. Detecting the sensor-testing trigger may comprise determining that a vehicle is within a threshold distance to a target in an environment of the vehicle. The method also involves obtaining sensor data collected by a sensor of the vehicle after the detection of the sensor-testing trigger. The sensor data is indicative of a scan of a region of the environment that includes the target. The method also involves comparing the sensor data with previously-collected sensor data indicating detection of the target by one or more sensors during one or more previous scans of the environment. The method also involves generating performance metrics related to the sensor of the vehicle based on the comparison.
https://worldwide.espacenet.com/publicationDetails/biblio?
II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200116&CC=WO&NR=2020014685A1&KC=A1#
https://patents.justia.com/patent/20200019160

SYSTEMS AND METHODS FOR ANNOTATING MAPS TO IMPROVE SENSOR CALIBRATION
System, methods, and other embodiments described herein relate to improving calibration of an onboard sensor of a vehicle. In one embodiment, a method includes, in response to acquiring sensor data from a surrounding environment of the vehicle using the onboard sensor, analyzing the sensor data to determine calibration parameters for the onboard sensor. The method includes identifying a suitability parameter that characterizes how well the surrounding environment provides for determining the calibration parameters. The method includes generating annotations within a map that specify at least the suitability parameter for a location associated with the sensor data. In further aspects, the method includes identifying, from the map, a calibration route for the vehicle that is a deviation from a current route in response to determining that the calibration state of the onboard sensor does not satisfy the calibration threshold.
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200116&CC=US&NR=2020018618A1&KC=A1#

Toyota 2020-01-16
SYSTEM AND METHOD FOR CALIBRATING A LIDAR AND A CAMERA TOGETHER USING SEMANTIC SEGMENTATION
System, methods, and other embodiments described herein relate to calibrating a light detection and ranging (LiDAR) sensor with a camera sensor. In one embodiment, a method includes controlling i) the LiDAR sensor to acquire point cloud data, and ii) the camera sensor to acquire an image. The point cloud data and the image at least partially overlap in relation to a field of view of a surrounding environment. The method includes projecting the point cloud data into the image to form a combined image. The method includes adjusting sensor parameters of the LiDAR sensor and the camera sensor according to the combined image to calibrate the LiDAR sensor and the camera sensor together.
https://worldwide.espacenet.com/publicationDetails/biblio?II=1&ND=3&adjacent=true&locale=en_EP&FT=D&date=20200116&CC=US&NR=2020018852A1&KC=A1#