目标检测
1. requirements
Cloud based or device based deployment
2. data collection
3. feature
4. model
2-stage: region proposal and object classification
generates a set of potential object bounding boxes
takes the proposed regions from the RPN and classifies them into different object categories
1-stage
perform both region proposal and object classification in a single step
5. metrics
Precision
calculated based on IOU threshold
AP: avg. across various IOU thresholds
mAP: mean of AP over C classes
问答
过杀和漏检:基于遗传算法的帕累托优化
Reference
Last updated