2019-09-06: Geometry-Aware Video Object Detection for Static Cameras https://arxiv.org/abs/1909.03140v1Extensive experiments on two challenging datasets demonstrate the superior performance of the proposed approach, and show the great advantage of using geometry in deep networks for the video object detection task
‹›
In this paper we propose a geometry-aware model for video object detection.
Specifically, we consider the setting that cameras can be well approximated as
static, e.g. in video surveillance scenarios, and scene pseudo depth maps can
therefore be inferred easily from the object scale on the image plane. We make
the following contributions: First, we extend the recent anchor-free detector
(CornerNet [17]) to video object detections. In order to exploit the
spatial-temporal information while maintaining high efficiency, the proposed
model accepts video clips as input, and only makes predictions for the starting
and the ending frames, i.e. heatmaps of object bounding box corners and the
corresponding embeddings for grouping. Second, to tackle the challenge from
scale variations in object detection, scene geometry information, e.g. derived
depth maps, is explicitly incorporated into deep networks for multi-scale
feature selection and for the network prediction. Third, we validate the
proposed architectures on an autonomous driving dataset generated from the
Carla simulator [5], and on a real dataset for human detection (DukeMTMC
dataset [28]). When comparing with the existing competitive single-stage or
two-stage detectors, the proposed geometry-aware spatio-temporal network
achieves significantly better results.