Apple wins a Project Titan Patent related to an Advanced Nighttime Sensing System with 3X the Power of Traditional Headlights

TruckElectric

Well-known member
First Name
Bryan
Joined
Jun 16, 2020
Threads
769
Messages
2,482
Reaction score
3,273
Location
Texas
Vehicles
Dodge Ram diesel
Occupation
Retired
Country flag
Apple wins a Project Titan Patent related to an Advanced Nighttime Sensing System with 3X the Power of Traditional Headlights
6a0120a5580826970c026bdec44afd200c-800wi.jpg


Today the U.S. Patent and Trademark Office officially granted Apple a patent that relates to Project Titan and more specifically to multi-modal sensing for nighttime autonomous driving object detection and recognition. The superiority of the new system over traditional headlights when driving at night is going to save a lot of lives in the future.

Overall Apple's invention covers implementations of multi-modal sensing for nighttime autonomous driving object detection and recognition.

Apple explains that nighttime or low-light environments present challenges for automated vehicle control systems. For example, the illumination level provided by headlights on a vehicle at night may be limited by laws or regulations, which may in turn limit the effective range of a visible spectrum sensor (e.g., a camera) used for detecting objects in or near the path of the vehicle.

Having a limited effective range (e.g., about 60 meters = 180 feet) for detecting and or classifying objects can reduce safety and/or reduce the speed at which the vehicle can travel safely.

A combination of multiple complimentary image sensing technologies may be employed to address the challenges of nighttime or low-light environment object detection and classification. For example, there may be looser or no restrictions on the illumination level of a near infrared illuminator mounted on a vehicle.

A near infrared sensor with a near infrared illuminator can be configured to capture high resolution image information about objects in or near a path of the vehicle out to a significantly longer range (e.g., 200 meters = 600 feet) from the vehicle.

The techniques described in Apple's patent application may provide improvements over prior computer vision systems for automated vehicles. Some implementations may increase the effective range at which objects in or near the path of a vehicle may be detected and classified. Some implementations may more accurately classify objects in a low-light environment. Safety of an automated vehicle control system may be improved and/or the maximum safe speed in low-light environments may be increased.

Apple's patent FIG. 4 below is a block diagram of an example of a vehicle configured for multi-modal sensing for nighttime autonomous object detection and recognition; FIG. 7 is a diagram of an example of overlapping fields of view for multiple sensors of different types mounted on a vehicle.

6a0120a5580826970c026bdec44b07200c-800wi.jpg



Yesterday the US Patent & Trademark Office published a patent application from Apple relating to Project Titan and more specifically to multi-modal sensing for nighttime autonomous driving object detection and recognition. The superiority of the new system over traditional headlights when driving at night is going to save a lot of lives in the future.

Some automated systems gather process large quantities of sensor data to identify objects in the surrounding environment. The processing of sensor data is often subject to a real-time constraint to facilitate navigation and/or robust control of the automated system. This is what Apple's invention is trying to improve upon.

Overall Apple's invention covers implementations of multi-modal sensing for nighttime autonomous driving object detection and recognition.

Apple explains that nighttime or low-light environments present challenges for automated vehicle control systems. For example, the illumination level provided by headlights on a vehicle at night may be limited by laws or regulations, which may in turn limit the effective range of a visible spectrum sensor (e.g., a camera) used for detecting objects in or near the path of the vehicle.

Having a limited effective range (e.g., about 60 meters = 180 feet) for detecting and or classifying objects can reduce safety and/or reduce the speed at which the vehicle can travel safely.

A combination of multiple complimentary image sensing technologies may be employed to address the challenges of nighttime or low-light environment object detection and classification. For example, there may be looser or no restrictions on the illumination level of a near infrared illuminator mounted on a vehicle.

A near infrared sensor with a near infrared illuminator can be configured to capture high resolution image information about objects in or near a path of the vehicle out to a significantly longer range (e.g., 200 meters = 600 feet) from the vehicle.

This may enable earlier detection and classification of objects as the vehicle moves and improve safety and/or maximum speed. Near infrared illuminators may project near infrared light in a relatively narrow field of view (e.g., a 30-degree cone).

Although their range may be relatively limited, visible spectrum sensors can provide high resolution image data in multiple color channels (e.g., red, green, and blue). Visible spectrum sensors also may provide a wider field of view (e.g., a 120-degree field of view) of the path in front of a vehicle.

Long wave infrared sensors (LWIR) capture naturally occurring thermal radiation from objects in the environment around a vehicle and therefore do not rely on an illuminator. The effective range of a long wave infrared sensor may be limited by the sensor resolution and the resolution requirements for object detection and/or classification.

A long wave infrared sensor, which may include an array of component sensors, may provide a wide field of view around the vehicle (e.g., a 180-degree field of view). Long wave infrared sensors may provide images of objects in the environment that are of relatively low resolution.

In some implementations, objects detected based on low resolution image data from a long wave infrared sensor are classified by adjusting control parameters for other sensing modalities and/or image processing resources to focus computer vision resources of the vehicle on a region of interest associated with the detected objects.

For example, an integration time, an aperture size, a filter, or a gain for a sensor (e.g., a near infrared sensor or a visible spectrum sensor) may be adjusted to enhance a portion of a captured image associated with a region of interest.

For example, a power level or a field of view for an illuminator (e.g., a near infrared illuminator or a visible spectrum illuminator) may be adjusted to enhance a portion of a captured image associated with a region of interest. For example, a computational control parameter (e.g., a resolution used for image processing or a count of image processing passes) may be adjusted and applied to an image portion associated with a region of interest.

For more details, you could review our original patent application report here or review Apple's granted patent 10,949,679.


SOURCE: Patently Apple



Apple Car could see three times farther at night by using infrared headlights

Infra-red-headlights.jpg



Infrared headlights could allow an Apple Car autonomous driving system to “see” three times farther at night than a human driver.

Apple was today granted a patent for the night vision system that combines visible light, near-infrared (NIR), and long-wave infrared (LWIR) sensors for a comprehensive view of what lays ahead …

Apple’s patent explains that self-driving cars have the same limitations as human drivers when it comes to seeing at night, citing the typical 60-meter (200 feet) range of car headlights.

Nighttime or low-light environments present challenges for automated vehicle control systems. For example, the illumination level provided by headlights on a vehicle at night may be limited by laws or regulations, which may in turn limit the effective range of a visible spectrum sensor (e.g., a camera) used for detecting objects in or near the path of the vehicle. Having a limited effective range (e.g., about 60 meters) for detecting and or classifying objects can reduce safety and/or reduce the speed at which the vehicle can travel safely.
Apple notes that the law limiting the power of headlights applies only to visible light, so infrared ones could be more powerful.

A combination of multiple complimentary image sensing technologies may be employed to address the challenges of nighttime or low-light environment object detection and classification. For example, there may be looser or no restrictions on the illumination level of a near infrared illuminator mounted on a vehicle. A near infrared sensor with a near infrared illuminator can be configured to capture high resolution image information about objects in or near a path of the vehicle out to a significantly longer range (e.g., 200 meters) from the vehicle. This may enable earlier detection and classification of objects as the vehicle moves and improve safety and/or maximum speed. Near infrared illuminators may project near infrared light in a relatively narrow field of view (e.g., a 30-degree cone).
The patent notes that visible light provides the highest resolution; near-infrared provides the greatest range; and long-wave infrared provides the widest field of view. Combining input from all three would give the car the best possible model of what is in front of and around it at night.

Screenshot-2021-03-16-at-12.54.40.jpg

Some existing cars use infrared imaging to provide additional range to the driver’s view of the road ahead, highlighting pedestrians and other hazards that lay beyond the range of the headlights. The system shown above is a Porsche one.

Apple’s car plans are still unclear, though if the company intends to sell a complete vehicle, one existing manufacturer warned the company that it will need to be ready to provide 40 years of support. Apple typically declares products obsolete five to seven years after they are discontinued, at which point no further parts or repair services are offered.

Via Patently Apple


SOURCE: 9to5mac.com
Sponsored

 

BillyGee

Well-known member
First Name
Bill
Joined
Jan 22, 2020
Threads
8
Messages
708
Reaction score
1,534
Location
Northern California
Vehicles
Model Y P, Model 3 LR, Founders CT (Ordered)
Occupation
Technician
Country flag
This is literally the first time I've ever heard of a patent being "won" and not issued.
 

Tinker71

Well-known member
First Name
Ray
Joined
Aug 8, 2020
Threads
82
Messages
1,484
Reaction score
1,967
Location
Utah
Vehicles
1976 electric conversion bus
Occupation
Project Manager
Country flag
In generalities here, I think Tesla is right on with their FSD strategy. All the sensors in the world are not going to help if the car cannot filter and predict movements fast enough. Actually too many sensors will only make it more difficult. If a human can see it and react fast enough they will avoid most accidents however most accidents are caused by distracted drivers or over reactions not lack of data availability. If Tesla can see just a little better than a human, plus monitor blinds spots or maybe seeing in the fog then when they get the software and processor right they will be golden.
 
OP
OP
TruckElectric

TruckElectric

Well-known member
First Name
Bryan
Joined
Jun 16, 2020
Threads
769
Messages
2,482
Reaction score
3,273
Location
Texas
Vehicles
Dodge Ram diesel
Occupation
Retired
Country flag
Apple Car Could Be Able to Detect and Follow Traffic Officers' Hand Signals

18 Mar 2021, 7:26 UTC ·
by Bogdan Popa
bogdan-popa-64.jpg



Apple doesn’t say a single thing about its plans for the automotive market, but everybody knows already the company is currently working on an electric vehicle.
-and-follow-traffic-officers-hand-signals-157816-7.jpg
1 photo
While the Cupertino-based tech behemoth does its best to keep all details away from our eyes and ears, information continues making the headlines through unofficial channels. The latest suggests the Apple Car project has reached the phase where the company is seeking a partner to manufacture the vehicle.

In the meantime, Apple keeps focusing heavily on its car's software side, so it has already filed for a series of patents covering technology that would eventually help its EV stand out from the crowd.

One such idea is described in a patent called “traffic direction gesture recognition,” which details how a car can automatically detect the hand signals of a traffic officer and then act accordingly. In other words, an autonomous vehicle can read the gesture and slow down, stop, or take a turn according to what the officer in front of it indicates using a hand gesture.

To do this, the car would be equipped with an army of sensors, all supposed to make sure the signal is correctly detected.

“Traffic direction gesture recognition may be implemented for a vehicle in response to traffic diversion signals in the vehicles vicinity. Sensors implemented as part of a vehicle may collect data about pedestrians and other obstacles in the vicinity of the vehicle or along the vehicle's route of travel. Sensor data may be combined and analyzed to identify a traffic diversion condition, including identifying a traffic director directing traffic using gestures or signs,” Apple explains in the patent.

What’s more, Apple says the data collected by a vehicle can be used for other connected cars, thus preparing them for the moment they approach the traffic police officer for an even faster response.

“Gestures of a traffic director may be interpreted and understood by the vehicle as commands to perform maneuvers related to the traffic diversion, including stopping, slowing, or turning onto a detour route. The vehicle may be equipped with a command acknowledgement device for acknowledging to a traffic director the vehicle's understanding of the traffic diversion condition or maneuver commands. Information, such as traffic diversion and detour information, may be shared with other vehicles and devices, or stored in a database,” the document reads.

As usual, this patent isn’t by any means a guarantee such a technology reaches mass production.


SOURCE: Autoevolution
 
 




Top