Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic Cameras
作者： R. Wes Baldwin , Mohammed Almatrafi , Vijayan Asari , Keigo Hirakawa
DOI: 10.1109/CVPR42600.2020.00177
关键词:
摘要: This paper presents a novel method for labeling real-world neuromorphic camera sensor data by calculating the likelihood of generating an event at each pixel within short time window, which we refer to as “event probability mask” or EPM. Its applications include (i) objective benchmarking denoising performance, (ii) training convolutional neural networks noise removal called network” (EDnCNN), and (iii) estimating internal parameters. We provide first dataset (DVSNOISE20) labeled events removal.
arxiv.org
harvard.edu
sci-hub.st 参考文章(45)
Tobias Delbrück, Frame-free dynamic digital vision Delbruck, T (2008). Frame-free dynamic digital vision. In: International Symposium on Secure-Life Electronics, Tokyo, Japan, 6 March 2008 - 7 March 2008, 21-26.. ,vol. 1, pp. 21- 26 ,(2008) , 10.5167/UZH-17620
Hongjie Liu, Christian Brandli, Chenghan Li, Shih-Chii Liu, Tobi Delbruck, Design of a spatiotemporal correlation filter for event-based sensors international symposium on circuits and systems. ,vol. 2, pp. 722- 725 ,(2015) , 10.1109/ISCAS.2015.7168735
Ryad Benosman, Charles Clercq, Xavier Lagorce, Sio-Hoi Ieng, Chiara Bartolozzi, Event-Based Visual Flow IEEE Transactions on Neural Networks. ,vol. 25, pp. 407- 417 ,(2014) , 10.1109/TNNLS.2013.2273537
Ryad Benosman, Sio-Hoi Ieng, Charles Clercq, Chiara Bartolozzi, Mandyam Srinivasan, Asynchronous frameless event-based optical flow Neural Networks. ,vol. 27, pp. 32- 37 ,(2012) , 10.1016/J.NEUNET.2011.11.001
Patrick Lichtsteiner, Christoph Posch, Tobi Delbruck, A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor IEEE Journal of Solid-State Circuits. ,vol. 43, pp. 566- 576 ,(2008) , 10.1109/JSSC.2007.914337
Garrick Orchard, Cedric Meyer, Ralph Etienne-Cummings, Christoph Posch, Nitish Thakor, Ryad Benosman, HFirst: A Temporal Approach to Object Recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 37, pp. 2028- 2040 ,(2015) , 10.1109/TPAMI.2015.2392947
Xavier Lagorce, Sio-Hoi Ieng, Xavier Clady, Michael Pfeiffer, Ryad B. Benosman, Spatiotemporal features for asynchronous event-based data Frontiers in Neuroscience. ,vol. 9, pp. 46- 46 ,(2015) , 10.3389/FNINS.2015.00046
David Weikersdorfer, Raoul Hoffmann, Jörg Conradt, Simultaneous localization and mapping for event-based vision systems international conference on computer vision systems. pp. 133- 142 ,(2013) , 10.1007/978-3-642-39402-7_14
Bodo Rueckauer, Tobi Delbruck, Evaluation of Event-Based Algorithms for Optical Flow with Ground-Truth from Inertial Measurement Sensor Frontiers in Neuroscience. ,vol. 10, pp. 176- 176 ,(2016) , 10.3389/FNINS.2016.00176
Souptik Barua, Yoshitaka Miyatani, Ashok Veeraraghavan, Direct face detection and video reconstruction from event cameras workshop on applications of computer vision. pp. 1- 9 ,(2016) , 10.1109/WACV.2016.7477561