computer vision

U-Net with hierarchical bottleneck attention for landmark detection in fundus images of the degenerated retina

We propose HBA-U-Net: a U-Net backbone with hierarchical bottleneck attention to highlight retinal abnormalities that may be important for fovea and optic disc segmentation in the degenerated retina.

Deep learning-based scene simplification for bionic vision

We combined deep learning-based scene simplification strategies with a psychophysically validated computational model of the retina to generate realistic predictions of simulated prosthetic vision.

How can we design more effective stimulation strategies?

Rather than predicting perceptual distortions, one needs to solve the inverse problem: What is the best stimulus to generate a desired visual percept?

Vision-based robust road lane detection in urban environments

This paper presents an integrative approach to ego-lane detection that aims to be as simple as possible to enable real-time computation while being able to adapt to a variety of urban and rural traffic scenarios. The approach at hand combines and extends a road segmentation method in an illumination-invariant color image, lane markings detection using a ridge operator, and road geometry estimation using RANdom SAmple Consensus (RANSAC). The power and robustness of this algorithm has been demonstrated in a car simulation system as well as in the challenging KITTI data base of real-world urban traffic scenarios.