A water-obstacle separation and refinement network for unmanned surface vehicles

January 07, 2020 · Entered Twilight · 🏛 IEEE International Conference on Robotics and Automation

"No code URL or promise found in abstract"
"Code repo scraped from project page (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, Object.m, ObjectPart.m, README.md, _config.yml, description_images, evaluate_detections_modd2.m, extractTheLargestCurve.m, extractTheLargestRegion.m, filter_obstacles.m, filter_sea_edge.m, get_eval_params.m, get_extreme_conditions.m, get_paths.m, get_seq_details.m, mask_parts_of_usv.m, modd2_evaluate_all_sequences_raw.m, modd2_evaluate_all_sequences_rectified.m, modd2_generate_video.m, modd2_visualize_frame.m, perform_evaluation_on_sequence.m, postprocess_output_image.m, rectifyimages_fix.m, replacement_bwconncomp.m, suppressDetections.m, viz_images

Authors Borja Bovcon, Matej Kristan arXiv ID 2001.01921 Category cs.CV: Computer Vision Cross-listed cs.RO Citations 29 Venue IEEE International Conference on Robotics and Automation Repository https://github.com/bborja/modd ⭐ 58 Last Checked 6 days ago

Abstract

Obstacle detection by semantic segmentation shows a great promise for autonomous navigation in unmanned surface vehicles (USV). However, existing methods suffer from poor estimation of the water edge in the presence of visual ambiguities, poor detection of small obstacles and high false-positive rate on water reflections and wakes. We propose a new deep encoder-decoder architecture, a water-obstacle separation and refinement network (WaSR), to address these issues. Detection and water edge accuracy are improved by a novel decoder that gradually fuses inertial information from IMU with the visual features from the encoder. In addition, a novel loss function is designed to increase the separation between water and obstacle features early on in the network. Subsequently, the capacity of the remaining layers in the decoder is better utilised, leading to a significant reduction in false positives and increased true positives. Experimental results show that WaSR outperforms the current state-of-the-art by a large margin, yielding a 14% increase in F-measure over the second-best method.