Cycle A six week period of time where teams work uninterruptedly on shaped projects. Cool-down A two-week break between cycles to do ad-hoc tasks, fix bugs, and hold a betting table. Cleanup mode The last phase of building a new product, where we don’t shape or bet on any particular projects but instead allocate unstructured time to fix whatever is needed before launch. Circuit breaker A risk management technique: Cancel projects that don’t ship in one cycle by default instead of extending them by default. Breadboard A UI concept that defines affordances and their connections without visual styling. Big batch One project that occupies a team for a whole cycle and ships at the end. Betting table A meeting during cool-down when stakeholders decide which pitches to bet on in the next cycle. Bet The decision to commit a team to a project for one cycle with no interruptions and an expectation to finish. Baseline What customers are doing without the thing we’re currently building. Affordances before pixel-perfect screensĪppetite The amount of time we want to spend on a project, as opposed to an estimate.In: Proceedings of 2017 IEEE International Geoscience and Remote Sensing Symposium, pp. Zakharov, I., Puestow, T., Fleming, A., Deepakumara, J., Power, D.: Detection and discrimination of icebergs and ships using satellite altimetry. Zakharov, I., Power, D., Howell, M., Warren, S.: Improved detection of icebergs in sea ice with RADARSAT-2 polarimetric data. Jin, J., Fu, K., Zhang, C.: Traffic sign recognition with hinge loss trained convolutional neural networks. In: Proceedings of 2004 IEEE International Geoscience and Remote Sensing Symposium, pp. Howell, C., Youden, J., Lane, K., Power, D., Randell, C., Flett, D.: Iceberg and ship discrimination with ENVISAT multipolarization ASAR. 41(5), 363–379 (2015)Įriksen, T., Høye, G., Narheim, B., Meland, B.J.: Maritime traffic monitoring using a space-based AIS receiver. 51(1), 591–600 (2013)ĭenbina, M., Collins, M.J., Atteia, G.: On the detection and discrimination of ships and icebergs using simulated dual-polarized radarsat constellation data. 1–4 (2016)Ĭollins, M.J., Denbina, M., Atteia, G.: On the reconstruction of quad-pol SAR data from compact polarimetry data for ocean target detection. In: Proceedings of 11th European Conference on Synthetic Aperture Radar, pp. Keywordsīentes, C., Frost, A., Velotto, D., Tings, B.: Ship-iceberg discrimination with convolutional neural networks in high resolution SAR images. Experiment on another real image data set also confirm the effectiveness of the proposed ensemble loss. The ensemble loss trained CNNs model for the distinction between ship and iceberg is evaluated on a real-world SAR data set, which can get a higher classification accuracy to 90.15%. In this work, we propose a novel loss function called ensemble loss to train convolutional neural networks (CNNs), which is a convex function and incorporates the traits of cross entropy and hinge loss. At present, compared with the object detection of ship or iceberg, the task of ship and iceberg distinction in SAR images is still in challenge. Synthetic aperture radar (SAR) has been widely used in ship and iceberg monitoring for maritime surveillance and safety in the Arctic waters. With the phenomenon of global warming, more new shipping routes will be open and utilized by more and more ships in the polar regions, particularly in the Arctic.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |