Патент США № | 10878276 |
---|---|
Автор(ы) | Martin и др. |
Дата выдачи | 29 декабря 2020 г. |
Described is a system for detecting change of context in a video stream on an autonomous platform. The system extracts salient patches from image frames in the video stream. Each salient patch is translated to a concept vector. A recurrent neural network is enervated with the concept vector, resulting in activations of the recurrent neural network. The activations are classified, and the classified activations are mapped onto context classes. A change in context class is detected in the image frames, and the system causes the autonomous platform to perform an automatic operation to adapt to the change of context class.
Авторы: | Charles E. Martin (Santa Monica, CA), Nigel D. Stepp (Santa Monica, CA), Soheil Kolouri (Agoura Hills, CA), Heiko Hoffmann (Simi Valley, CA) | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
Патентообладатель: |
|
||||||||||
Заявитель: | HRL Laboratories, LLC (Malibu, CA) |
||||||||||
ID семейства патентов | 68693622 | ||||||||||
Номер заявки: | 16/415,942 | ||||||||||
Дата регистрации: | 17 мая 2019 г. |
Document Identifier | Publication Date | |
---|---|---|
US 20190370598 A1 | Dec 5, 2019 | |
Application Number | Filing Date | Patent Number | Issue Date | ||
---|---|---|---|---|---|
62680966 | Jun 5, 2018 | ||||
Класс патентной классификации США: | 1/1 |
Класс совместной патентной классификации: | G06K 9/72 (20130101); G06N 3/0454 (20130101); G06K 9/6232 (20130101); G06K 9/6273 (20130101); G06K 9/6267 (20130101); G06N 3/0445 (20130101); G06N 3/08 (20130101); G06N 3/049 (20130101); G06K 9/4676 (20130101) |
Класс международной патентной классификации (МПК): | G06K 9/00 (20060101); G06K 9/62 (20060101); G06K 9/46 (20060101); G06N 3/08 (20060101) |
9571628 | February 2017 | Bostick |
2017/0083772 | March 2017 | Kim et al. |
2017/0124447 | May 2017 | Chang |
2017/0262995 | September 2017 | Li et al. |
2018/0033144 | February 2018 | Risman et al. |
2018/0120843 | May 2018 | Berntorp et al. |
2018/0144208 | May 2018 | Lu et al. |
2019/0028707 | January 2019 | Yu |
Yang, Video Captioning by Adversarial LSTM, Nov. 2018, IEEE Transactions on Image Processing, vol. 27, No. 11 (Year: 2018). cited by examiner . Notification of Transmittal of International Search Report and the Written Opinion of the International Searching Authority for PCT/US2019/033326; dated Sep. 11, 2019. cited by applicant . International Search Report of the International Searching Authority for PCT/US2019/033326; dated Sep. 11, 2019. cited by applicant . Written Opinion of the International Searching Authority for PCT/US2019/033326; dated Sep. 11, 2019. cited by applicant . Maass, W., Matschlager, T., & Markram, H. (2002). Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput., 14, pp. 2531-2560. cited by applicant . Maass, W., & Sontag, E. D. (2000). Neural systems as nonlinear filters. Neural Computation, 12(8), pp. 1743-1772. cited by applicant . Stepp, N., Plenz, D. & Srinivasa, N. (2015). Synaptic Plasticity Enables Adaptive Self-Tuning Critical Networks. PLOS Computational Biology 11(1): e1004043, pp. 1-28. cited by applicant . Yu, A. J. (2006). Optimal Change-Detection and Spiking Neurons. In NIPS, pp. 1545-1552. cited by applicant . Milan, K. et al. (2016). The Forget-Me-Not Process. 30th Conference on Neural Information Processing Systems, pp. 1-9. cited by applicant . Melamud, O. et al. (2016). Context2Vec: Learning Generic Context Embedding with Bidirectional LSTM, pp. 1-11. cited by applicant . Kanerva, P. (2009). Hyperdimensional Computing: An Introduction to Computing In Distributed Representation with High-Dimensional Random Vectors. Cognitive Computing, vol. 1, pp. 139-159. cited by applicant. |