Through its Open Innovation Program, the Algeciras Port Authority (APBA) has successfully finalized a proof of concept whose challenge was to expand the control and monitoring network of cargo traffic within the port facilities using the existing network of cameras.
The challenge was achieved by the start-up AllRead MLT, which has based its solution on computer vision technology and artificial intelligence. AllRead MLT has developed a smart reading software that is able to spot and read in real-time any text and alphanumeric code from images or videos captured by any device (mobile, security camera, etc.) even when it is damaged, dirty or out of focus.
Its innovative and patented technology is based on the use of a convolutional neural network (a common Deep Learning technique), which allows the system to learn from its mistakes in a similar way to the human brain, achieving rational deductions when reading codes and text.
Unlike other market players, AllRead MLT´s solution is focused on the software, leaning on the benefits of Deep Learning, and not on hardware devices. In fact, hardware is becoming a commodity and, therefore, the importance of this innovative solution that is based on a hardware-agnostic system.
In addition, the AllRead MLT’s solution can identify the location and typology of a license plate (container, trailer, tractor, etc.), by understanding the framework and elements included in an image. This fact makes this solution unique and disruptive from the traditional OCR that reads characters without considering the context.
The scope of the proof of concept was the development and implementation of a minimum viable product (MVP) focused on processing the images captured by the existing cameras, in order to deliver the transit-related information in a structured way of the following items containers IDs, platforms, trucks, trailers and semi-trailers and all types of license plates of vehicles (mainly European and Moroccan origin).
The Port of Algeciras, due to its uniqueness and geographical position, receives a large flow of vehicles with multiple origins and destinations, constituting a complex scenario for reading license plates
The solution provided by AllRead MLT, whose neural network can be trained and adapted to the different operating scenarios, will allow the APBA to increase accuracy rates in vehicle identification, reducing the number of false readings, and all this without the need to deploy new video and civil infrastructure or dedicated gates providing greater flexibility and coverage of the vehicle monitoring system.
After the validation of the proof of concept, the next objective of the APBA is to expand the solution to key operational areas within the port, monitoring not only light and heavy traffic vehicles but also the cargo transported by rail.
The following link shows a video demonstration of the developed prototype:
ABOUT ALLREAD MLT:
AllRead MLT emerged from the Computer Vision Center of Catalonia, (Autonomous University of Barcelona – UAB) and the The Collider Venture Building program (Mobile World Capital Barcelona). AllRead MLT develops intelligent reading software for operational environments. Its goal is to streamline logistic processes that require rapid and accurate tracking and identification of assets, using computer vision and machine learning techniques to detect and digitize any alphanumeric text.