The recently adopted image coding standard JPEG AI uses neural networks to encode images efficiently. In doing so, it achieves a comparatively low bitrate while maintaining high image quality. Both in classical and learning-based coding, it has been shown that techniques that adaptively respond to image content enable higher compression rates.
Description
The majority of the plastic waste produced is thermally recycled, i.e. incinerated. The reason for this is that the plastics often cannot be properly identified. Multispectral imaging enables clear classification. So-called camera arrays are used for this purpose; filters in different wa...
Description
Detecting objects in front of a self-driving vehicle is critical for safety but poses significant challenges. The range of potential objects on the road includes rare and unknown entities—such as wild animals, debris, or litter—which are underrepresented in existing datasets. The wide v...
Recent advances in computation power along with the availability of vast amount of data is a key enabler towardstraining the next generation of large deep neural networks comprising billions of learnable parameters. This category of networks is commonly known as foundation models. Foundation models ...
Description
Lower limb prostheses support individuals with lower limb amputations in daily tasks, including walking, stairs climbing or running. For adaptation to the current gait situation, it is beneficial to sense the surrounding environment, e.g., with visual sensors. The obtained situation awa...
