Video to Events: Recycling Video Datasets for Event Cameras

被引:121
作者
Gehrig, Daniel [1 ]
Gehrig, Mathias
Hidalgo-Carrio, Javier
Scaramuzza, Davide
机构
[1] Univ Zurich, Dept Informat, Zurich, Switzerland
来源
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2020年
基金
瑞士国家科学基金会;
关键词
VISION;
D O I
10.1109/CVPR42600.2020.00364
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with respect to conventional cameras: high dynamic range (HDR), high temporal resolution, and no motion blur. Recently, novel learning approaches operating on event data have achieved impressive results. Yet, these methods require a large amount of event data for training, which is hardly available due the novelty of event sensors in computer vision research. In this paper, we present a method that addresses these needs by converting any existing video dataset recorded with conventional cameras to synthetic event data. This unlocks the use of a virtually unlimited number of existing video datasets for training networks designed for real event data. We evaluate our method on two relevant vision tasks, i.e., object recognition and semantic segmentation, and show that models trained on synthetic events have several benefits: (i) they generalize well to real event data, even in scenarios where standard-camera images are blurry or overexposed, by inheriting the outstanding properties of event cameras; (ii) they can be used for fine-tuning on real data to improve over state-of-the-art for both classification and semantic segmentation.
引用
收藏
页码:3583 / 3592
页数:10
相关论文
共 42 条
[1]  
Alonso Inigo, 2019, IEEE C COMP VIS PATT
[2]   A Low Power, Fully Event-Based Gesture Recognition System [J].
Amir, Arnon ;
Taba, Brian ;
Berg, David ;
Melano, Timothy ;
McKinstry, Jeffrey ;
Di Nolfo, Carmelo ;
Nayak, Tapan ;
Andreopoulos, Alexander ;
Garreau, Guillaume ;
Mendoza, Marcela ;
Kusnitz, Jeff ;
Debole, Michael ;
Esser, Steve ;
Delbruck, Tobi ;
Flickner, Myron ;
Modha, Dharmendra .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :7388-7397
[3]   Graph-Based Object Classification for Neuromorphic Vision Sensing [J].
Bi, Yin ;
Chadha, Aaron ;
Abbas, Alhabib ;
Bourtsoulatze, Eirina ;
Andreopoulos, Yiannis .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :491-501
[4]  
Bi Y, 2017, IEEE IMAGE PROC, P1990, DOI 10.1109/ICIP.2017.8296630
[5]  
Binas Jonathan, 2017, ICML WORKSH MACH LEA
[6]   A 240 x 180 130 dB 3 μs Latency Global Shutter Spatiotemporal Vision Sensor [J].
Brandli, Christian ;
Berner, Raphael ;
Yang, Minhao ;
Liu, Shih-Chii ;
Delbruck, Tobi .
IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2014, 49 (10) :2333-2341
[7]  
Calabrese E., 2019, IEEE C COMP VIS PATT
[8]   Xception: Deep Learning with Depthwise Separable Convolutions [J].
Chollet, Francois .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1800-1807
[9]   The Cityscapes Dataset for Semantic Urban Scene Understanding [J].
Cordts, Marius ;
Omran, Mohamed ;
Ramos, Sebastian ;
Rehfeld, Timo ;
Enzweiler, Markus ;
Benenson, Rodrigo ;
Franke, Uwe ;
Roth, Stefan ;
Schiele, Bernt .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :3213-3223
[10]   What is a good evaluation measure for semantic segmentation? [J].
Csurka, Gabriela ;
Larlus, Diane ;
Perronnin, Florent .
PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2013, 2013,