Optical sensors let "machine vision" enter thousands of households

[ Focus on Chemical Machinery Equipment Network ] Oregon State University in the United States has made significant progress in the research and development of new optical sensors .
They developed a new type of optical sensor that can more realistically mimic the human eye's ability to perceive changes in objects.
This achievement is expected to bring major breakthroughs in the fields of image recognition, robotics, and artificial intelligence.

 

Current information processing algorithms and architectures have become more and more like human brains, but the way of receiving information is still designed for traditional computers.
In order to realize its full potential, a computer that "thinks" more like the human brain needs an image sensor that "sees" more like the human eye.

 

New optical sensor mimics human eye perception
 

Optical sensor is a kind of small electronic equipment, the key element to realize optical conversion in various optical detection systems.
It is mainly a sensor that uses various properties of light to detect the presence or absence of objects and changes in surface conditions.
The optical sensor is mainly composed of a light-emitting part that emits light and a light-receiving part that receives light.
If the projected light is blocked or reflected due to different detection objects, the amount reaching the light receiving part will change.
The light-receiving unit will detect this change, convert it into an electrical signal, and output it.

 

　　Traditional sensing technologies, such as chips in digital cameras and smart phones, are more suitable for sequential processing.
Each sensor generates a signal whose amplitude varies with the intensity of the light it receives, which means that a static image will cause the sensor to produce a relatively constant output voltage.

 

　　In the new retinal morphology sensor, the unique photoelectric properties of perovskite are used.
Perovskite is placed in an ultra-thin layer with a thickness of only a few hundred nanometers to act as a capacitor.
Under light, it changes from an electrical insulator to a conductor.
Therefore, the sensor remains relatively quiet under static conditions.
When it detects a change in light, it will record a short and sharp signal, and then quickly return to its baseline state.

 

　　This new type of sensor can also be perfectly matched to neuromorphic computers.
Neuromorphic computers are different from traditional computers in that they are a massively parallel network that simulates the human brain, providing support for the next generation of artificial intelligence used in autonomous vehicles, robotics, and advanced image recognition.

 

　　Principle and application of optical sensor
 

　　Optical sensor is the key element to realize optical conversion in various optical detection systems.
The optical detection method has the advantages of high accuracy, fast response, non-contact, etc.
, and has many measurable parameters.
The sensor has a simple structure and flexible and diverse forms.
Therefore, optical sensors are widely used in detection and control.

 

　　The light-emitting diode illuminates the sampling surface, and the image to be sampled with strong contrast is imaged on the CMOS through the lens.
CMOS converts the optical image into a matrix electrical signal and transmits it to the dsp.
The dsp compares this image signal with the stored image of the previous sampling period.
Analyze, and then send a displacement distance signal to the interface circuit.
The interface circuit integrates and processes the displacement signal sent by the dsp, and the displacement signal that has been passed into the computer is further processed by the driver program, and finally forms the displacement of the cursor in the system.

 

　　Optical sensors can be used to detect such as light intensity, illuminance, radiation temperature measurement, gas composition analysis, etc.
; can also be used to detect such as part diameter, surface roughness, strain, displacement, vibration, speed, acceleration, as well as the shape and working state of objects Recognition, etc.

 

　　Among them, the ambient light sensor has been widely used in consumer electronic products in recent years.
It can be used to perceive the surrounding light conditions and inform the processing chip to automatically adjust the brightness of the display backlight to reduce the power consumption of the product.
For example, in mobile applications such as mobile phones and notebooks, the display consumes up to 30% of the total battery power, and the use of ambient light sensors can maximize the working time of the battery.
On the other hand, the ambient light sensor helps the display provide a soft picture.
When the ambient brightness is high, the LCD display using the ambient light sensor will automatically adjust to high brightness.
When the external environment is dark, the display will be adjusted to low brightness to achieve automatic brightness adjustment.

 

　　Optical sensors help machine vision
 

　　Drones are getting smarter! Many users have such feelings.
In the past, you had to be cautious when operating drones for fear of encountering obstacles in the way and encountering the tragic disaster of bombers.
Today's drones can completely dodge and avoid various obstacles in the flight path in time, so that many beginners can easily control them.

 

　　Are there any secrets to smart drones? The answer is the blessing of optical sensors.
Through optical sensors, the drone can not only perceive obstacles, but also know the distance between itself and obstacles, so as to achieve precise obstacle avoidance and circumvention.
The concept of machine vision originates from the field of robotics.
The American Robot Industry Association defines it as: "Automatically receive and process an image of a real object through optical devices and non-contact sensors to obtain required information or to control robots.
Movement device.
"
 

　　It is precisely with optical sensors that machine vision is no longer an exclusive term in the field of industrial automation, and has been easily integrated into our lives, so there is also the emerging field and concept of "consumer machine vision".
For example, the sweeping robots that enter many homes are equipped with machine vision technology, which can thoroughly clean dead corners.
The small and convenient translation pen can read multiple languages ​​due to machine vision technology.
In industrial automated production lines, machine vision systems are still used to automatically complete highly sophisticated automated manufacturing and detection of defective products.

 

　　With the widespread implementation of AI applications, such as face scanning payment and face recognition access control, it has penetrated into people's work and life at an extremely fast speed.
Even shopping malls have no shortage of smart interactive electronic screens, smart full-length mirrors and other interactive smart video devices based on AI and machine vision.
On the whole, optical sensors have been perfectly integrated with our lives through the link of "consumer machine vision".

 

　　Original title: Optical sensors let "machine vision" enter thousands of households