AI-supported loading documentation increases efficiency in the logistics process

Automated loading documentation during ongoing operations

At the center of the application is a forklift truck, with the camera mounted on its cabin. While the vehicle is in motion, the camera continuously captures the area in front of it. The process begins with recording the delivery note and covers every step of the loading sequence. This includes maneuvering, picking up and setting down every single pallet, as well as the final load securing after parking the forklift. For drivers, this results in a significant reduction in workload: The interruptions previously required for manual documentation are eliminated entirely. At the same time, the system generates consistent and traceable image data, creating full transparency throughout the whole process.

Intelligent image analysis in real time

A key component of the solution is the intelligent evaluation of the captured image data. Via a standardized USB Video Class (UVC) interface, the camera transmits images directly to an on-board vehicle terminal without requiring additional drivers. From there, the data is sent to a local AI server, where it is analyzed in real time. First, an AI-based image classification evaluates every frame regarding content and relevance. More than 99 per cent of the captured images are filtered out at this stage, ensuring that only genuinely relevant information is processed further. For the remaining data, specialized models from DENKweit's DENKnet system are employed. A combination of object recognition and optical character recognition (OCR) identifies delivery notes as well as pallet structures. The tour number is read out and serves as the central reference for assigning the images. In this way, all relevant images are structured, assigned to a tour, and stored centrally. At the same time, the system can determine how many pallets appear in an image and identify their dimensions.

High image quality at changing distances

The flexibility of the solution is particularly evident in the dynamic adjustment of image acquisition. The uEye XC autofocus camera automatically adjusts between different focal distances. "For capturing a delivery note, the focus is set to a distance of around 35 centimeters. For documenting the loading process, however, the field of view is between 2 and 3 meters," explains Thomas Fuchs, Team Leader AIoT at CANCOM. "This ensures sharp, usable images in every situation, even when lighting conditions vary."

The camera used features a 13-megapixel sensor and offers functions such as automatic white balance, color correction and individually adjustable parameters for brightness, contrast and sharpness. Thanks to the UVC interface, it can be operated like a standard webcam without additional drivers. In combination with Windows IoT on the vehicle terminals, this simplifies integration significantly. Devices are detected automatically and can be managed centrally through a device management system.

Scalable AI infrastructure from edge to data center

The particular strength of the application lies in the interaction between the camera and artificial intelligence. In the solution implemented by CANCOM, containerized AI models from DENKweit are used. They can be flexibly scaled from the edge to the data center and operated in Kubernetes environments, with GPU acceleration available where required. Initial working models can be created using a relatively small number of training images. However, their performance improves significantly as data quality and diversity increase.

Compared with traditional machine vision systems, this approach greatly reduces development effort. Complex rule-based vision pipelines are replaced by learning-based methods that can be implemented more quickly and adapted more easily to changing requirements. At the same time, users benefit from the rapid advances in available computing power, so that even integrated GPU solutions are sufficient for many applications.