The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV). Three challenges categories are considered: (i) UAV-based Maritime Object Tracking with Re-identification, (ii) USV-based Maritime Obstacle Segmentation and Detection, (iii) USV-based Maritime Boat Tracking. The USV-based Maritime Obstacle Segmentation and Detection features three sub-challenges, including a new embedded challenge addressing efficicent inference on real-world embedded devices. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 195 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi24.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation LaRS eWaSR F1 58.9 # 13
μ 67.8 # 18
mIoU 96.0 # 7
Q 56.5 # 13
Semantic Segmentation LaRS Mari-Mask2Former (Mask2Former) F1 77.3 # 3
μ 78.4 # 5
mIoU 97.8 # 1
Q 75.7 # 3
Semantic Segmentation LaRS TransMari (Mask2Former) F1 80.2 # 1
μ 79.6 # 2
mIoU 97.1 # 4
Q 77.8 # 2
Semantic Segmentation LaRS SWIM^2 (Mask2Former) F1 79.9 # 2
μ 79.7 # 1
mIoU 97.8 # 1
Q 78.1 # 1

Methods


No methods listed for this paper. Add relevant methods here