3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks
This addresses efficiency issues in 3D object detection for domains like autonomous vehicles and robotics, though it is incremental as it builds on existing sensor fusion methods.
The paper tackles the problem of slow 3D object detection in sensor fusion networks by proposing 3D-FFS, which uses point cloud properties to constrain the search space, resulting in up to 62.80% faster training, 58.96% faster inference, and 58.53% lower memory usage while slightly improving accuracy on the KITTI dataset.
In this work we propose 3D-FFS, a novel approach to make sensor fusion based 3D object detection networks significantly faster using a class of computationally inexpensive heuristics. Existing sensor fusion based networks generate 3D region proposals by leveraging inferences from 2D object detectors. However, as images have no depth information, these networks rely on extracting semantic features of points from the entire scene to locate the object. By leveraging aggregated intrinsic properties (e.g. point density) of point cloud data, 3D-FFS can substantially constrain the 3D search space and thereby significantly reduce training time, inference time and memory consumption without sacrificing accuracy. To demonstrate the efficacy of 3D-FFS, we have integrated it with Frustum ConvNet (F-ConvNet), a prominent sensor fusion based 3D object detection model. We assess the performance of 3D-FFS on the KITTI dataset. Compared to F-ConvNet, we achieve improvements in training and inference times by up to 62.80% and 58.96%, respectively, while reducing the memory usage by up to 58.53%. Additionally, we achieve 0.36%, 0.59% and 2.19% improvements in accuracy for the Car, Pedestrian and Cyclist classes, respectively. 3D-FFS shows a lot of promise in domains with limited computing power, such as autonomous vehicles, drones and robotics where LiDAR-Camera based sensor fusion perception systems are widely used.