简体   繁体   English

如何为图像检测绘制多边形数据标注形状?

[英]How to draw a polygon shaped data annotation shape for image detection?

I am training some images using imageAI object detection.我正在使用 imageAI object 检测来训练一些图像。 What i want to do is draw a polygon shaped data annotation around the objects in an image.我想要做的是在图像中的对象周围绘制一个多边形数据注释。 Not a square box.不是方盒子。 Even though I ca draw the shape, the imageAI class doesn't consider polygon shapes.即使我可以绘制形状,imageAI class 也不考虑多边形形状。 If some one can help me to find if is there is some model where polygon shapes are allowed in image training, that would be great.如果有人可以帮助我找出是否有一些 model 允许在图像训练中使用多边形形状,那就太好了。

ImageAI only supports PascalVOC image annotation format, which is upright rectangular bounding boxes. ImageAI 仅支持 PascalVOC 图像标注格式,即直立矩形边界框。 You would need to change frameworks for this to work.您需要更改框架才能使其正常工作。 For a workaround, consider using an image editing tool to get rid of the background and then provide a square bounding box.作为解决方法,请考虑使用图像编辑工具去除背景,然后提供方形边界框。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM