Computer Vision

INFORMATION GATHERING

In order to generate meaning, we have to collect data. Cameras equipped with Internet of Things generate visual content that enable us to assess a situation. Assessing a situation has many aspects such as determining how much water a field needs 1, collecting data around parking sensors 2, sales excellence through distant shelf tracking 3, creating an identity record of objects with a single barcode 4 and baggage management 5.

1 Smart Agriculture

It has been a long time since large agricultural areas were monitored via images taken by aircrafts and satellites. With drones and different image processing techniques, it is now possible to monitor how much water the field needs, when to apply pesticide and monitor yield growth. In this way, data collection is both very fast and cost-effective. Moreover, getting more accurate results by normalizing the shots taken in different seasons or day times increases the reliability of the application.

PROJECT DETAIL

2 Parking

Parking using rearview mirrors may soon become history. Initially developed for the visually impaired, sensors are on the rise. Along with ultrasonic sensors installed in bumpers and cameras on all four sides, the vehicle detects its surroundings and measures the distance to nearby obstacles. By perceiving objects more clearly, computer vision can distinguish not only sidewalks but also the lines on the road. Very soon your car will be able to park on its own.

PROJECT DETAIL

3 Smart Shelves

Thanks to thermal cameras that can detect body heat, a missing person wandering into a cornfield was found without injury.

Public safety cameras are a sine qua non in large open spaces. If there is a missing child reported to security, one of the first things to be done is to enter detailed information about the child in the system and ensure computer vision focus. It is important to be able to identify children with red coats and 130 cm height when there are hundreds of people moving or standing in the street. Our brains’ constant unconscious focusing process in everyday life, is actually the first step in solving complex structures.

PROJECT DETAIL PROJECT DETAIL

4 Differentiating Products in Unorganized Places

The job of traditional robotic arms is quite easer in fully automated factories. One-size products, like military units, come in front of robotic arms in a single line. Thus, the same process (such as printing labels) can be applied to all products easily. We need computer vision in places where the work environment is not so organized. For example, when we need to identify objects of different sizes and packages - such as socks, tablecloths, shirts in their packs - it is also possible to train robots on the basis of self-learning algorithms, both for classification and which product to "hold".

PROJECT DETAIL

5 Journey of Suitcases

You have probably watched the journey of your suitcase, how it is labeled and moved away after you have given it to the airport officer. Luckily, we do not see the transfer of tens of thousands of suitcases to hundreds of different carriers. In modern airports, barcodes on each suitcase are read many times and suitcases are delivered to the cargo box of the right airplane through a complex pallet and scissors system without human touch.