Search Results for author: Jesper Haahr Christensen

Found 4 papers, 2 papers with code

Deep Learning based Segmentation of Fish in Noisy Forward Looking MBES Images

no code implementations16 Jun 2020 Jesper Haahr Christensen, Lars Valdemar Mogensen, Ole Ravn

In this work, we investigate a Deep Learning (DL) approach to fish segmentation in a small dataset of noisy low-resolution images generated by a forward-looking multibeam echosounder (MBES).

Segmentation Semantic Segmentation

BatVision with GCC-PHAT Features for Better Sound to Vision Predictions

1 code implementation14 Jun 2020 Jesper Haahr Christensen, Sascha Hornauer, Stella Yu

We improve on the previous model by introducing several changes to the model, which leads to a better depth and grayscale estimation, and increased perceptual quality.

Generative Adversarial Network

BatVision: Learning to See 3D Spatial Layout with Two Ears

1 code implementation15 Dec 2019 Jesper Haahr Christensen, Sascha Hornauer, Stella Yu

Inspired by bats' echolocation mechanism, we design a low-cost BatVision system that is capable of seeing the 3D spatial layout of space ahead by just listening with two ears.

Robot Navigation Vocal Bursts Valence Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.