Detecting objects in a video is a compute-intensive task. In this paper we
propose CaTDet, a system to speedup object detection by leveraging the temporal
correlation in video. CaTDet consists of two DNN models that form a cascaded
detector, and an additional tracker to predict regions of interests based on
historic detections. We also propose a new metric, mean Delay(mD), which is
designed for latency-critical video applications. Experiments on the KITTI
dataset show that CaTDet reduces operation count by 5.1-8.7x with the same mean
Average Precision(mAP) as the single-model Faster R-CNN detector and incurs
additional delay of 0.3 frame. On CityPersons dataset, CaTDet achieves 13.0x
reduction in operations with 0.8% mAP loss.

本文提出了一种名为 CaTDet 的系统，它通过利用视频中的时间相关性加快物体检测的速度。该系统由两个 DNN 模型和一个额外的跟踪器组成，用于预测历史检测的感兴趣区域，并使用设计用于延迟关键视频应用的新度量 mean Delay（mD）。实验结果表明，在 KITTI 数据集上，CaTDet 将操作次数降低了 5.1-8.7 倍，并具有与单模型 Faster R-CNN 检测器相同的平均精度（mAP），而额外的延迟仅为 0.3 帧。在 CityPersons 数据集上，CaTDet 减少了 13.0 倍的操作，并损失 0.8％的 mAP。