Feel free to discuss any issues or ideas you might have about PeekingDuck in this forum!
PeekingDuck is an open-source, modular framework built to simplify Computer Vision inference workloads. We found that while the types of CV problems are very varied, many of these projects share repeated code, such as reading from a video or image. In some projects, even pre-trained CV models for object detection and pose estimation can be reused. To save development time for future projects, we decided to build PeekingDuck to simplify CV inference workloads. We have greatly benefited from PeekingDuck, and we have released it as an open-source project for the CV community to reap the benefits as well.
We just released v1.1 of PeekingDuck with privacy protection functionality, which automatically pixelates/blurs faces and license plates in videos, complying with privacy laws such as PDPA or GDPR! Check it out along with other new features in this article.
We just released v1.1.1 this week, and with it, a significant improvement in the way you can create custom nodes. There’s no need to manually create folders, Python scripts and config files any more – you can do it quickly and easily via CLI!