Solution

Machine vision

1. Project background

As the artificial intelligence industry heats up, the machine vision industry is expected to move to a new stage of development, and the market size will accelerate expansion. By 2021, it will exceed 10 billion, with broad prospects. Machine vision uses machines instead of human eyes to make measurements and judgments. Machine vision is an image analysis technology that uses optical systems, industrial digital cameras, and image processing tools to simulate human vision, make corresponding decisions, and ultimately execute those decisions by directing specific devices.

2. Overview

The real realization of industrial automation requires intelligent industrial robots to replace some of the work of humans. If you want intelligent robots to replace human work, "vision" is the key. The machine vision product, the image capture device, converts the captured target into an image signal and transmits it to a dedicated image processing system to obtain the morphological information of the captured target. According to the pixel distribution, brightness, color and other information, it is converted into a digital signal. The image system performs various operations on the signal to extract the target characteristics, and then controls the action of the field equipment according to the discrimination results.

3. System introduction

Four functions of machine vision:

1, guidance and positioning: visual positioning, quickly and accurately find the measured part and confirm its position, loading and unloading using machine vision to locate, guide the robot arm to grasp accurately.

2, appearance detection: detection of product quality problems on the production line, this link is to replace the most manual link. Its main detection includes size detection, bottle appearance defect detection, bottle shoulder defect detection, bottle mouth detection and so on.

3, high-precision detection: the product precision is high, reaching 0.01~0.02m or even u level, the human eye can not detect, must use the machine to complete.

4, recognition: the use of machine vision for image processing, analysis and understanding, to identify a variety of different patterns of targets and objects. To achieve data traceability and collection, automotive parts, food, medicine and other applications.

4. Application scenarios

Our embedded industrial computer: BOX PC, shelf, compact three types, has been widely used in industrial automation, CNC machine tools, machine vision, intelligent manufacturing, intelligent logistics, transportation, remote monitoring, industrial control, new energy, environmental monitoring and other industries.

AI security

1. Project background

Since the rise of road monitoring system in the world, the current urban monitoring construction in the world is about to enter the stage of expansion and structural change, under this demand change, security monitoring system will need more diversified and artificial intelligence of the overall solution. Modern public safety is no longer limited to the unlimited expansion of image monitoring coverage density, breadth and the pursuit of ultra-high-definition resolution, but through these artificial intelligence means and tools, so that the traditional security era further, to focus on data acquisition, application and management of artificial intelligence security era.

2. Advantage Selling point

Applicable to the overall solution of the intelligent board

① Low power consumption, power 2w

(2) With face recognition function, find one or more faces with the highest similarity to the face to be retrieved in the large-scale face database.

③ Linkage enterprise office/home, community, police intelligent alarm, strong anti-interference, accurate and reliable alarm.

④ Infrared night view, can see every corner very clearly at night. Array type infrared light, according to the change of light Chengdu switch night white.

⑤ Mobile phone real-time view and screen intelligent playback, support Micro SD card, hard disk box cloud storage

It can carry out deep learning, which mimics the behavioral thinking mechanism of the human brain to interpret data, such as multi-feature and multi-posture recognition of image content, sound and data itself.

3. Application scenarios

Classroom, convenience store, living room, restaurant, shop, community, bank hall, home, etc.