https://viametoolkit.org

VIAMEVIAME Skip to content InstallationWeb Annotator and DataKitwareContact Us A do-it-yourself AI system for analyzing imagery and video Learn More Contact Us Gold Medal Award for Scientific or Technical Achievement. The highest technical award within the US Department of Commerce was presented in 2019 to the NOAA members of the AIASI Steering Committee for developing VIAME and CoralNet. Learn more » Welcome to VIAME In cooperation with the National Oceanic and Atmospheric Administration’s (NOAA) Automated Image Analysis Strategic Initiative (AIASI), Kitware and its partners have developed Video and Image Analytics for Marine Environments (VIAME). VIAME is an open source computer vision software platform designed for do-it-yourself artificial intelligence (AI). It is an evolving toolkit that contains many workflows used to generate different object detectors, full-frame classifiers, image mosaics, rapid model generation, image and video search, and methods for stereo measurement. Originally targeting marine species analytics, it now contains many common algorithms and libraries, and is also useful as a generic computer vision library outside of underwater image and video. VIAME is available as a desktop or a web application. Install VIAME Support & Services Documentation Source Code VIAME in Action VIAME offers three (3) core detection training workflows dependent on user needs and available training data. Use Kitware’s Interactive Query Refinement (IQR) to rapidly generate models for new object classes with very little user effort. Feel the freedom to use VIAME web interface for basic object detection and annotation or download the desktop version for higher level analytics. Access VIAME’s specialized object detectors and functionalities specific to maritime and other domains of interest, including multiple general purpose detectors for wide applicability. VIAME users have access to multiple trackers that use different techniques, such as deep learning addressing multiple domains. Poor video quality or collection environments can be improved using VIAME’s image enhancement features. VIAME’s image registration and mosaicing can be used for multi-camera and multi-modality experiments in multiple domains. VIAME offers multiple types of annotation features down to the pixel-level to support object detection training workflows. We continue to conduct research and development using scene semantics and 3D reconstruction to improve object classification. VIAME uses knowledge-driven scene understanding using deep-learning techniques to segment a scene into object types with high accuracy. Latest News DIVE: Revolutionize Your AI Training with Advanced Video and Image Annotation High-quality labeled data powers every successful AI model, yet preparing large-scale video and image datasets remains one of the most costly and time-consuming stages in the machine learning pipeline. Kitware’s open source platform, DIVE, changes that. Built for speed, scalability, and accuracy, DIVE empowers teams to label and visualize imagery, then use those annotations to train and refine AI models – all within a single, versatile environment. Developed by Kitware, DIVE reflects our commitment to making open and accessible advanced AI tools, empowering organizations to turn raw data into insight with far less effort and cost. CVPR 2025 Kitware is proud to participate in the 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), one of the premier conferences for cutting-edge research in computer vision and machine learning. This year, Kitware’s leadership in the community is reflected through key service roles that help shape the conference itself. We’re also contributing original research and sharing practical tools that support real-world AI development. As always, our commitment to open science and collaborative innovation will be on full display at our booth (visit us at Booth 1617!) and in our technical sessions. Advancing Undersea Soundscape Awareness: Kitware’s Maritime Acoustic Recognition and Identification with Novel Algorithms (MARINA) Project The ocean’s acoustic environment is a complex tapestry of sounds originating from the natural environment (e.g. waves, currents), biological sources (e.g. marine mammals, fish), and humans (e.g. boats, drilling). Underwater soundscape awareness facilitates understanding and monitoring the acoustic environments in oceans and other bodies of water. Deep Dive on VIAME Interested in learning more about VIAME’s history, VIAME-related workshops, and publications that feature VIAME work? 
Here are some links that will help you dive deeper on VIAME History In cooperation with NOAA’s Automated Image Analysis Strategic Initiative (AIASI), Kitware and its partners developed this open source system that analyzes video and imagery for fisheries stock assessment and a variety of other applications. This computer vision application is designed for DIY AI and allows a user to perform object detection, object tracking, image/video annotation, image/video search, image mosaicing, stereo measurement, rapid model generation, and provides tools for the evaluation of different algorithms. Although it was originally designed to target marine species analytics, it now contains many common algorithms and libraries, and is also useful as a generic computer vision library. Built upon an established open source video analytics toolkit, Kitware Image and Video Exploitation and Retrieval (KWIVER), VIAME enables the rapid integration of new visual analytics, and includes user interfaces, databases and evaluation/scoring capabilities. Algorithms from multiple NOAA Fisheries Science Centers (FSCs) are integrated, such as length measurement from the Alaska FSC. More significantly, VIAME includes the capability for scientists to create new analytics, specific to their problems, through user interfaces without any programming or knowledge of deep learning. Through image search and interactive query refinement, users can quickly build a complete detection and classification capability for a novel problem by providing only positive/negative feedback on examples suggested by the system, and then run it on any amount of imagery or video. For more challenging problems, users can manually annotate images and then train a deep learning detection and classification capability. VIAME has been successfully applied to many problems within the maritime and airborne domains including: scallop detection, plankton classification, fish classification, seal detection, sea lion detection, and image registration. Both a desktop and web version of VIAME exist for ease-of-use and convenience in different types of environments. In 2019, the US Department of Commerce presented members of the AIASI Steering Committee with a Gold Medal Award for “Scientific or Technical Achievement” for the development of VIAME and CoralNet, another open source software toolkit. This is the highest technical award within the DOC. Workshops, Presentations, and News VIAME Team Receives SBIR Award to Aid With Monitoring Bat Populations around Wind Turbines Date: 07/12/2023 Invited to Pew Foundation Summit Targeting AI Use for Electronic Monitoring Onboard Vessels Date: 01/22/2023 VIAME will be presented at a United Nations FAO Summit - Artificial Intelligence for a Digital Blue Planet Date: 06/28/2021 Tutorial on VIAME presented at NAML (Annual Workshop on Naval Applications of Machine Learning) Date: 03/25/2021 The Marine Alliance for Science and Technology for Scotland (MASTS) Annual Science Meeting 2020 Date: 10/06/2020 27 AUG NOAA Workshop on Leveraging AI in Environmental Sciences (VIAME Overview) Date: 09/27/2020 NOAA Workshop on Leveraging AI in Environmental Sciences (VIAME Tutorial) Date: 09/22/2020 An Open-Source System for Do-It-Yourself AI in the Marine Environment | A Hoogs, MD Dawkins, B Rich Date: 02/20/2020 Moving Towards Machine Learning for the Analysis of Deep-Sea Imagery Collected by Autonomous Underwater Vehicle | A Powell, ME Clarke, MD Dawkins, B Richards, A Hoogs Date: 02/20/2020 Advanced Camera Technologies and Artificial Intelligence to Improve Marine Resource Surveys | B Richards, A Hoogs, MD Dawkins, J Taylor, SG Smith, JS Ault, MP Seki Date: 02/17/2020 VIAME: Video and Image Analytics in Marine Environments | MD Dawkins, L Sherrill, J Crall, A Hoogs, D Zhang, B Richards, L Prasad, ... Date: 02/12/2018 Publications J. Prior, M. Campbell, M. Dawkins, P. Mickle, R. Moorhead, S. Alaba, C. Shah, J. Salisbury, K. Rademacher, A. Felts, and F. Wallace, "Estimating precision and accuracy of automated video post-processing: A step towards implementation of AI/ML for optics-based fish sampling," Frontiers in Marine Science, no. 10, pp. p.1150651, Apr. 2023. M. Dawkins, J. Crall, M. Leotta, T. O’Hara, and L. Siemann, "Towards Depth Fusion into Object Detectors for Improved Benthic Species Classification," in ICPR CVAUI 2022, 2022. K. Ovchinnikova, M. James, T. Mendo, M. Dawkins, J. Crall, and K. Boswarva, "Exploring the potential to use low cost imaging and an open source convolutional neural network detector to support stock assessment of the king scallop (Pecten maximus)," Ecological Informatics, no. 62, pp. p.101233, 2021. A. Hoogs, M. Dawkins, B. Richards, G. Cutter, D. Hart, and M. Clarke, "An Open-Source System for Do-It-Yourself AI in the Marine Environment," in Ocean Sciences Meeting 2020, 2020. B. Richards, O. Beijbom, M. Campbell, M. Clarke, G. Cutter, M. Dawkins, D. Edington, D. Hart, M. Hill, A. Hoogs, D. Kriegman, E. Moreland, T. Oliver, W. Michaels, M. Placentino, A. Rollo, C. Thompson, F. Wallace, I. Williams, and K. Williams, "Automated Analysis of Underwater Imagery: Accomplishments, Products, and Vision," NOAA technical memorandum NMFS PIFSC, 2019. [URL] M. Dawkins, L. Sherrill, K. Fieldhouse, A. Hoogs, B. Richards, D. Zhang, L. Prasad, K. Williams, N. Lauffenburger, and G. Wang, "An open-source platform for underwater image and video analytics," in Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2017. Winner, Best Paper Honorable Mention. [URL] M. Dawkins, C. Stewart, S. Gallager, and A. York, "Automatic scallop detection in benthic environments," in Proceedings of the IEEE Workshop on Applications of Computer Vision, 2013. [URL] M. Dawkins and C. Stewart, "Scallop detection in multiple maritime environments," Rensselaer Polytechnic Institute, 2011. Bibliography generated 2023-07-20-13:18:06 (6150) About Kitware Founded in 1998, Kitware is a global leader in developing advanced state-of-the-art AI and scientific research and development solutions. As early adopters of deep learning, this plays an essential role in everything we do. We are dedicated to researching and creating innovative techniques and technologies valuable to the computer vision community and our customers. Learn more about Kitware’s advanced computer vision solutions. Visit our Computer Vision page Developed in cooperation with: NOAA’s Automated Image Analysis Strategic Initiative (AIASI), Kitware and it’s partners.enusen-UShttps://viametoolkit.org

Modifier votre site ?

Que fais-tu?