WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments

1 code implementation • 23 Dec 2023 • Kavisha Vidanapathirana, Joshua Knights, Stephen Hausler, Mark Cox, Milad Ramezani, Jason Jooste, Ethan Griffiths, Shaheer Mohamed, Sridha Sridharan, Clinton Fookes, Peyman Moghadam

Recent progress in semantic scene understanding has primarily been enabled by the availability of semantically annotated bi-modal (camera and LiDAR) datasets in urban environments.

3D Semantic Segmentation Domain Adaptation +1

What's in the Black Box? The False Negative Mechanisms Inside Object Detectors

1 code implementation • 15 Mar 2022 • Dimity Miller, Peyman Moghadam, Mark Cox, Matt Wildie, Raja Jurdak

Using this framework, we investigate why Faster R-CNN and RetinaNet fail to detect objects in benchmark vision datasets and robotics datasets.

Object object-detection +2

Non-rigid Reconstruction with a Single Moving RGB-D Camera

no code implementations • 29 May 2018 • Shafeeq Elanattil, Peyman Moghadam, Sridha Sridharan, Clinton Fookes, Mark Cox

Our approach uses camera pose estimated from the rigid background for foreground tracking.