What's new with IBM Maximo Visual Inspection
Enterprise-grade suite of tools for labeling raw datasets for training, creating, and deploying deep learning-based vision models
IBM Maximo Visual Inspection 1.3.0
Overview
IBM Maximo Visual Inspection, formerly PowerAI Vision, is a video/image analysis platform that offers built-in deep learning models that learn to analyze images and video streams for classification and object detection.
IBM Maximo Visual Inspection includes tools and interfaces that allow anyone with limited skills in deep learning technologies to get up and running quickly and easily. And because IBM Visual Insights is built on open source frameworks for modeling and managing containers it delivers a highly available platform that includes application life-cycle support, centralized management and monitoring, and support from IBM.
What's new?
IBM Visual Insights is now IBM Maximo Visual Inspection
IBM Visual Insights has been renamed IBM Maximo Visual Inspection to reflect its central role in the IBM AI Applications family. IBM Maximo Visual Inspection is part of the Maximo product family, delivering insights and AI-infused capabilities for smarter assets in the field.
Technology updates and features
- Updated URL: After you upgrade to Version 1.3.0, use the updated URL to access IBM Maximo Visual Inspection: https://hostname/visual-inspection/, where hostname is the system on which you installed IBM Maximo Visual Inspection.
- Improved support for transfer learning with base models: YOLO v3 and Detectron models support selecting a previously trained model as a base model for training a new model. For more information, see Advanced settings in Training a model.
- Integrated support for IBM Maximo Asset Monitor: Runtime containers, which connect to a Maximo Asset Monitor deployment and provide data on image inferences, is now included. For more information, see Integrating IBM Maximo Visual Inspection with Maximo Asset Monitor.
- New security policies: Users will now be logged out of the user interface after 60 minutes of inactivity. On new installations, user accounts are locked if there are too many failed logins. For more information, see Managing users.
- User interface improvements: The user interface include various improvements.
For all the details, see the What’s New topic in the IBM Knowledge Center.
Key features
- Streamlined model training
Use existing models that are already trained as starting point to reduce the time required to train models and improve trained results. - Single-click model deployment
After you create a training model, deploy an API with one click. You can then develop applications based on the model that you deployed. - Data set management and labeling
Manage both raw and labeled data. - Video object detection and labeling assistance
Videos that you import can be scanned for objects and the objects can be automatically labeled. - Supported hardware
- POWER8 S822LC (8335-GTB) or POWER9 AC922 with at least one NVIDIA NVLink capable GPU
- POWER9 IC922 with at least one NVIDIA T4 GPU
- x86 system with at least one NVIDIA Pascal, Volta, or Turing-architecture GPU
- 64 GB of memory
- Supported operating systems
- Red Hat Enterprise Linux (RHEL) RHEL 7.6 ALT (little endian) for POWER9™
- Ubuntu 18.04 or later
- RHEL 7.7 for x86
- Planning information and considerations
- Install information
- Training and working with models
IBM Maximo Visual Inspection code patterns, tutorials, and learning paths
Check out these real world examples and tutorials that highlight IBM Maximo Visual Inspection in action.
- Automate your video analysis
- Automate visual recognition model training
- Load IBM Maximo Visual Inspection inference results in a dashboard
- Build an object detection model to identify license plates from images of cars
- Develop analytical dashboards for AI projects with IBM Maximo Visual Inspection
- Build and deploy an IBM Maximo Visual Inspection model and use it in an iOS app
- Moving AI from the Data Center to Edge or Fog Computing
- Detect objects with IBM Maximo Visual Inspection
- Vision TensorRT inference samples
- Introduction to computer vision using IBM Maximo Visual Inspection
- Vision TensorRT inference samples
- Enabling distributed AI for quality inspection in manufacturing with edge computing
- Building out the edge in the application layer and device layer
- Introduction to computer vision
- Implementing an edge computing architecture
- Learning path: Getting started with IBM Maximo Visual Inspection
Requesting enhancements for IBM Maximo Visual Inspection
The IBM Request for Enhancement (RFE) tool is now available for you to submit formal enhancement requests to the IBM Maximo Visual Inspection development team. One of the benefits of using the RFE tool is that other clients can vote on submitted requirements, which helps IBM to prioritize requests.
Get started
Go here get started: ibm.biz/vision-rfe
The RFE for IBM Visual Insights pages are part of IBM Developer and require that you sign in with an IBM ID to submit or vote on a request. You should make sure that your IBM ID profile includes your current company and your email address to ensure that we can contact you if we have questions.
Search first
Once on the RFE page, click on the “Search” tab to view existing requests before you submit a new request. It is much more useful to vote for a previously submitted request than to submit a duplicate request.
Previous releases
We recommend that you install the most current release of IBM Maximo Visual Inspection, however, if you have an earlier version of PowerAI Vision installed, you can find release information in the IBM Knowledge Center: