FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving
This addresses collision risk estimation for near-range objects in autonomous vehicles, but it is incremental as it builds on existing MOD methods with a focus on fisheye-specific challenges.
The authors tackled moving object detection in fisheye surround-view cameras for autonomous driving by proposing a lightweight CNN architecture, achieving 40% IoU and 69.5% mIoU accuracy at 15 fps on an embedded system.
Moving Object Detection (MOD) is an important task for achieving robust autonomous driving. An autonomous vehicle has to estimate collision risk with other interacting objects in the environment and calculate an optional trajectory. Collision risk is typically higher for moving objects than static ones due to the need to estimate the future states and poses of the objects for decision making. This is particularly important for near-range objects around the vehicle which are typically detected by a fisheye surround-view system that captures a 360° view of the scene. In this work, we propose a CNN architecture for moving object detection using fisheye images that were captured in autonomous driving environment. As motion geometry is highly non-linear and unique for fisheye cameras, we will make an improved version of the current dataset public to encourage further research. To target embedded deployment, we design a lightweight encoder sharing weights across sequential images. The proposed network runs at 15 fps on a 1 teraflops automotive embedded system at accuracy of 40% IoU and 69.5% mIoU.