Fisheye Camera
Fisheye cameras, characterized by their extremely wide field of view, are increasingly used in robotics, autonomous driving, and 3D scene reconstruction, demanding robust image processing techniques to handle their significant radial distortion. Current research focuses on developing accurate depth estimation models, efficient rendering methods (like Gaussian splatting adaptations), and improved object detection and segmentation algorithms specifically tailored for fisheye geometry, often employing convolutional neural networks and transformers. These advancements are crucial for enhancing the capabilities of various applications that benefit from panoramic vision, improving accuracy and reliability in challenging conditions.
Papers
Visual Gyroscope: Combination of Deep Learning Features and Direct Alignment for Panoramic Stabilization
Bruno Berenguel-Baeta, Antoine N. Andre, Guillaume Caron, Jesus Bermudez-Cameo, Jose J. Guerrero
Convolution kernel adaptation to calibrated fisheye
Bruno Berenguel-Baeta, Maria Santos-Villafranca, Jesus Bermudez-Cameo, Alejandro Perez-Yus, Jose J. Guerrero