object detection物体检测基本概念

Posted wordchao

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了object detection物体检测基本概念相关的知识,希望对你有一定的参考价值。

1.precision-recall

https://cn.mathworks.com/help/vision/ref/evaluatedetectionprecision.html?requestedDomain=www.mathworks.com#outputarg_precision

averagePrecision — Average precision
numeric scalar | vector

Average precision over all the detection results, returned as a numeric scalar or vector. Precision is a ratio of true positive instances to all positive instances of objects in the detector, based on the ground truth. For a multiclass detector, the average precision is a vector of average precision scores for each object class.

recall — Recall values from each detection
vector of numeric scalars | cell array

Recall values from each detection, returned as a vector of numeric scalars or as a cell array. Recall is a ratio of true positive instances to the sum of true positives and false negatives in the detector, based on the ground truth. For a multiclass detector, recalland precision are cell arrays, where each cell contains the data points for each object class.

precision — Precision values from each detection
vector of numeric scalars | cell array

Precision values from each detection, returned as a vector of numeric scalars or as a cell array. Precision is a ratio of true positive instances to all positive instances of objects in the detector, based on the ground truth. For a multi-class detector, recall and precision are cell arrays, where each cell contains the data points for each object class.

 

以上是关于object detection物体检测基本概念的主要内容,如果未能解决你的问题,请参考以下文章

物体检测object detection object recognition和coco数据集 动手学深度学习v2 pytorch

物体检测快速入门系列 | 01-基于Tensorflow2.x Object Detection API构建自定义物体检测器

手撕coreML之yolov2 object detection物体检测(含源代码)

20190311-object-detection-metrics

论文阅读CVPR 2019| PointPillars: 基于点云的快速编码目标检测框架(Fast Encoders for Object Detection from Point Clouds)(代

Object_detection-模型训练日志结果解析