3D Object Detection and Tracking Based on Streaming Data

Abstract

Recent approaches for 3D object detection have made tremendous progresses due to the development of deep learning. However, previous researches are mostly based on individual frames, leading to limited exploitation of information between frames. In this paper, we attempt to leverage the temporal information in streaming data and explore 3D streaming based object detection as well as tracking. Toward this goal, we set up a dual-way network for 3D object detection based on keyframes, and then propagate predictions to non-key frames through a motion based interpolation algorithm guided by temporal information. Our framework is not only shown to have significant improvements on object detection compared with frame-by-frame paradigm, but also proven to produce competitive results on KITTI Object Tracking Benchmark, with 76.68% in MOTA and 81.65% in MOTP respectively.

GridTrack: Detection and Tracking of Multiple Objects in Dynamic Occupancy Grids

“…Early work by Luo et al [18] used pointclouds from different frames similar to [10] and associated the outputs. In another similar study, Guo et al [14] used keyframes instead of using all frames. Recently, Center Point [29] is inspired from the success of center track [30].…”