{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:16:24Z","timestamp":1761808584871,"version":"build-2065373602"},"reference-count":38,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Event cameras measure scene changes with high temporal resolutions, making them well-suited for visual motion estimation. The activation of pixels results in an asynchronous stream of digital data (events), which rolls continuously over time without the discrete temporal boundaries typical of frame-based cameras (where a data packet or frame is emitted at a fixed temporal rate). As such, it is not trivial to define a priori how to group\/accumulate events in a way that is sufficient for computation. The suitable number of events can greatly vary for different environments, motion patterns, and tasks. In this paper, we use neural networks for rotational motion estimation as a scenario to investigate the appropriate selection of event batches to populate input tensors. Our results show that batch selection has a large impact on the results: training should be performed on a wide variety of different batches, regardless of the batch selection method; a simple fixed-time window is a good choice for inference with respect to fixed-count batches, and it also demonstrates comparable performance to more complex methods. Our initial hypothesis that a minimal amount of events is required to estimate motion (as in contrast maximization) is not valid when estimating motion with a neural network.<\/jats:p>","DOI":"10.3390\/s23073699","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T04:45:33Z","timestamp":1680497133000},"page":"3699","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Insights into Batch Selection for Event-Camera Motion Estimation"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7329-786X","authenticated-orcid":false,"given":"Juan L.","family":"Valerdi","sequence":"first","affiliation":[{"name":"Event-Driven Perception for Robotics, Istituto Italiano di Tecnologia, 16163 Genova, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3465-6449","authenticated-orcid":false,"given":"Chiara","family":"Bartolozzi","sequence":"additional","affiliation":[{"name":"Event-Driven Perception for Robotics, Istituto Italiano di Tecnologia, 16163 Genova, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4499-4070","authenticated-orcid":false,"given":"Arren","family":"Glover","sequence":"additional","affiliation":[{"name":"Event-Driven Perception for Robotics, Istituto Italiano di Tecnologia, 16163 Genova, Italy"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1109\/JSSC.2007.914337","article-title":"A 128x 128 120 db 15 \u03bcs latency asynchronous temporal contrast vision sensor","volume":"43","author":"Patrick","year":"2008","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhan, H., Garg, R., Weerasekera, C.S., Li, K., Agarwal, H., and Reid, I. (2018, January 18\u201323). Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00043"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, G., Ji, X., Xiang, Y., and Fox, D. (2018, January 8\u201314). DeepIM: Deep Iterative Matching for 6D Pose Estimation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, S., Clark, R., Wen, H., and Trigoni, N. (June, January 29). DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks. Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore.","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1109\/LRA.2016.2645143","article-title":"EVO: A Geometric Approach to Event-Based 6-DOF Parallel Tracking and Mapping in Real Time","volume":"2","author":"Rebecq","year":"2017","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Glover, A., and Bartolozzi, C. (2017, January 24\u201328). Robust visual tracking with a freely-moving event camera. Proceedings of the 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada.","DOI":"10.1109\/IROS.2017.8206226"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1109\/TIFS.2020.3023791","article-title":"NeuroAED: Towards Efficient Abnormal Event Detection in Visual Surveillance With Neuromorphic Vision Sensor","volume":"16","author":"Chen","year":"2021","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_8","unstructured":"Lucas, B.D., and Kanade, T. (1981, January 24\u201328). An iterative image registration technique with an application to stereo vision. Proceedings of the 7th International Joint Conference on Artificial Intelligence, Vancouver, BC, Canada."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Portz, T., Zhang, L., and Jiang, H. (2012, January 16\u201321). Optical flow in the presence of spatially-varying motion blur. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6247871"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1109\/TPAMI.2017.2769655","article-title":"Event-Based, 6-DOF Camera Tracking from Photometric Depth Maps","volume":"40","author":"Gallego","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1109\/LRA.2018.2793357","article-title":"Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High-Speed Scenarios","volume":"3","author":"Vidal","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Gallego, G., Rebecq, H., and Scaramuzza, D. (2018, January 18\u201323). A unifying contrast maximization framework for event cameras, with applications to motion, depth, and optical flow estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00407"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1109\/LRA.2016.2647639","article-title":"Accurate angular velocity estimation with an event camera","volume":"2","author":"Gallego","year":"2017","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6016","DOI":"10.1109\/LRA.2021.3088793","article-title":"Real-time rotational motion estimation with contrast maximization over globally aligned events","volume":"6","author":"Kim","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_15","first-page":"3479","article-title":"Globally-Optimal Contrast Maximisation for Event Cameras","volume":"44","author":"Peng","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhu, A.Z., Yuan, L., Chaney, K., and Daniilidis, K. (2019, January 15\u201320). Unsupervised event-based learning of optical flow, depth, and egomotion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00108"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ye, C., Mitrokhin, A., Ferm\u00fcller, C., Yorke, J.A., and Aloimonos, Y. (2020\u201324, January 24). Unsupervised Learning of Dense Optical Flow, Depth and Egomotion with Event-Based Sensors. Proceedings of the 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA.","DOI":"10.1109\/IROS45743.2020.9341224"},{"key":"ref_18","unstructured":"Tae-Kyun, K., Stefanos Zafeiriou, G.B., and Mikolajczyk, K. Real-time Visual-Inertial Odometry for Event Cameras using Keyframe-based Nonlinear Optimization. Proceedings of the British Machine Vision Conference (BMVC), London, UK."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"117734","DOI":"10.1016\/j.eswa.2022.117734","article-title":"A Survey of State-of-the-Art on Visual SLAM","volume":"205","author":"Kazerouni","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wagner, D., Mulloni, A., Langlotz, T., and Schmalstieg, D. (2010, January 20\u201324). Real-time panoramic mapping and tracking on mobile phones. Proceedings of the 2010 IEEE Virtual Reality Conference (VR), Boston, MA, USA.","DOI":"10.1109\/VR.2010.5444786"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/MRA.2011.943233","article-title":"Visual Odometry [Tutorial]","volume":"18","author":"Scaramuzza","year":"2011","journal-title":"IEEE Robot. Autom. Mag."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chng, C.K., Parra, A., Chin, T.J., and Latif, Y. (December, January 9). Monocular Rotational Odometry with Incremental Rotation Averaging and Loop Closure. Proceedings of the 2020 Digital Image Computing: Techniques and Applications (DICTA), Melbourne, Australia.","DOI":"10.1109\/DICTA51227.2020.9363388"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Forster, C., Pizzoli, M., and Scaramuzza, D. (June, January 31). SVO: Fast semi-direct monocular visual odometry. Proceedings of the 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China.","DOI":"10.1109\/ICRA.2014.6906584"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1109\/TCI.2020.2964255","article-title":"Robust motion compensation for event cameras with smooth constraint","volume":"6","author":"Xu","year":"2020","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zihao Zhu, A., Atanasov, N., and Daniilidis, K. (2017, January 21\u201326). Event-based visual inertial odometry. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.616"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, D., Parra, A., and Chin, T.J. (2020, January 13\u201319). Globally optimal contrast maximisation for event-based motion estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00638"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Gallego, G., Gehrig, M., and Scaramuzza, D. (2019, January 15\u201320). Focus is all you need: Loss functions for event-based vision. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01256"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2822","DOI":"10.1109\/LRA.2021.3060707","article-title":"Combining Events and Frames Using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction","volume":"6","author":"Gehrig","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hidalgo-Carri\u00f3, J., Gehrig, D., and Scaramuzza, D. (2020, January 25\u201328). Learning monocular dense depth from events. Proceedings of the 2020 International Conference on 3D Vision (3DV), Fukuoka, Japan.","DOI":"10.1109\/3DV50981.2020.00063"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Mostafavi, M., Yoon, K.J., and Choi, J. (2021, January 10\u201317). Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00422"},{"key":"ref_31","unstructured":"Stoffregen, T., Gallego, G., Drummond, T., Kleeman, L., and Scaramuzza, D. (November, January 27). Event-based motion segmentation by motion compensation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhu, A.Z., Yuan, L., Chaney, K., and Daniilidis, K. (2018, January 26\u201330). EV-FlowNet: Self-supervised optical flow estimation for event-based cameras. Proceedings of the Robotics: Science and Systems, Pittsburgh, PA, USA.","DOI":"10.15607\/RSS.2018.XIV.062"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Alonso, I., and Murillo, A.C. (2019, January 16\u201317). EV-SegNet: Semantic segmentation for event-based cameras. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00205"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4919","DOI":"10.1109\/TIP.2021.3077136","article-title":"Learning From Images: A Distillation Learning Framework for Event Cameras","volume":"30","author":"Deng","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Pan, L., Liu, M., and Hartley, R. (2020, January 13\u201319). Single image optical flow estimation with an event camera. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00174"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Stoffregen, T., and Kleeman, L. (2019, January 15\u201320). Event cameras, contrast maximization and reward functions: An analysis. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01258"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Qiu, W., Zhong, F., Zhang, Y., Qiao, S., Xiao, Z., Kim, T.S., Wang, Y., and Yuille, A. (2017, January 23\u201327). UnrealCV: Virtual Worlds for Computer Vision. Proceedings of the 25th ACM International Conference on Multimedia, Mountain View, CA, USA.","DOI":"10.1145\/3123266.3129396"},{"key":"ref_38","first-page":"969","article-title":"ESIM: An Open Event Camera Simulator","volume":"87","author":"Rebecq","year":"2018","journal-title":"Conf. Robot. Learn. (CoRL)"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/7\/3699\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:08:57Z","timestamp":1760123337000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/7\/3699"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,3]]},"references-count":38,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23073699"],"URL":"https:\/\/doi.org\/10.3390\/s23073699","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,4,3]]}}}