One approach is to use a camera mounted on the side of the truck to capture video footage of the area around the vehicle. The video footage can then be analyzed in real-time using Artificial Intelligence algorithms that are trained to detect pedestrians and cyclists. These algorithms can be based on a variety of techniques, such as object detection, segmentation, and tracking.

Object detection algorithms use deep learning models to recognize different types of objects in an image or video frame. They can be trained on large datasets of labelled images containing pedestrians and cyclists to accurately detect them in real-time video footage. Zen Corner scan uses Segmentation algorithms to separate objects in an image or video frame, making it easier to detect and track pedestrians and cyclists. Also uses Tracking algorithms to track the movement of these objects over time, which can be useful for predicting their future paths and avoiding collisions.

The Corner scan has Real-time viewing of the video footage which is achieved using a display screen inside the truck cabin. The screen can show the live video feed from the camera, along with visual cues that highlight the detected pedestrians and cyclists. The cues can be in the form of bounding boxes, labels, or other visual indicators that help the driver to be aware of the presence of pedestrians and cyclists around the truck.

Overall, the combination of Artificial intelligence algorithms, real-time video analysis, and visual cues can help to improve pedestrian and cyclist detection in trucks from the side and enhance road safety for all road users.