Video object detection for autonomous driving: Motion-aid feature calibration

Video object detection for autonomous driving: Motion-aid feature calibration
复制标题

自动驾驶视频目标检测:运动辅助特征校准

DOI:
10.1016/j.neucom.2020.05.027
复制
发表时间:
2020-10
期刊:
影响因子:
6
通讯作者:
Fan Bin
Fan Bin
中科院分区:
计算机科学2区
文献类型:
--
作者:
Liu Dongfang;Cui Yiming;Chen Yingjie;Zhang Jiyong;Fan Bin

文献摘要

参考文献

被引文献

相似文献

本文提出了一个端到端的深度学习框架,称为运动辅助特征校准网络(MFCN),用于视频对象检测。关键思想是利用视频特征的时间相干性,同时考虑它们的运动模式被光流捕获。为了提高检测准确性,该框架在像素和实例级别跨帧聚合校准特征,以实现改进的鲁棒性,尽管外观变化。基于集成光流网络高效自适应地进行聚合和校准。同时,所提出的方法的整个架构是端到端的,因此与用于视频对象检测的多阶段方法相比,显著提高了其训练和推理效率。在KITTI和ImageNet VID上的测试表明,MFCN可以将强静态图像检测器的结果分别提高11.2%和7.31%。MFCN还优于其他竞争对手的视频对象检测器,并在准确性和运行速度之间实现了更好的权衡,展示了其在自动驾驶系统中的应用潜力。(C)2020爱思唯尔B.V.保留所有权利。
This paper proposes an end-to-end deep learning framework, termed as motion-aid feature calibration network (MFCN), for video object detection. The key idea is to leverage on the temporal coherence of video features while considering their motion patterns as captured by optical flow. To boost detection accuracy, the framework aggregates the calibrated features both at pixel and instance levels across frames to achieve improved robustness despite appearance variations. The aggregation and calibration are efficiently and adaptively conducted based on an integrated optical flow network. Meanwhile, the entire architecture of the proposed method is end-to-end, thus significantly improving its training and inference efficiency when compared to multi-stage methods for video object detection. Evaluations on KITTI and ImageNet VID indicate that MFCN can improve the results of a strong still-image detector by 11.2% and 7.31% respectively. MFCN also outperforms other competitive video object detectors and achieves a better trade-off between accuracy and runtime speed, demonstrating its potential for use in autonomous driving systems. (C) 2020 Elsevier B.V. All rights reserved.
DOI: 10.1016/j.neucom.2018.08.034
发表时间: 2018-12-10
期刊: NEUROCOMPUTING
影响因子: 6
作者:
Adhikari, Shyam Prasad;Yang, Changju;Kim, Hyongsuk
通讯作者: Kim, Hyongsuk
DOI: 10.5220/0007575908330839
发表时间: 2019
期刊: --
影响因子: --
作者:
Yaqin Wang;Dongfang Liu;Hyewon Jeon;Zhiwei Chu;E. Matson
通讯作者: Yaqin Wang;Dongfang Liu;Hyewon Jeon;Zhiwei Chu;E. Matson
DOI: 10.1007/978-3-319-46487-9_44
发表时间: 2016-10
期刊: --
影响因子: --
作者:
Yu Li;Dongbo Min;M. Do;Jiangbo Lu
通讯作者: Yu Li;Dongbo Min;M. Do;Jiangbo Lu
DOI: 10.1007/s11263-015-0816-y
发表时间: 2015-12-01
影响因子: 19.5
作者:
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者: Fei-Fei, Li
DOI: 10.1007/978-3-030-01234-2_33
发表时间: 2018-09
期刊: --
影响因子: --
作者:
Tao Song;Leiyu Sun;Di Xie;Haiming Sun;Shiliang Pu
通讯作者: Tao Song;Leiyu Sun;Di Xie;Haiming Sun;Shiliang Pu