从卷积神经网络回顾传统数字图像处理中的目标检测算法

最新推荐文章于 2023-09-17 20:39:40 发布

Gallant Hu

最新推荐文章于 2023-09-17 20:39:40 发布

阅读量285

点赞数

分类专栏：计算机视觉

本文链接：https://blog.csdn.net/weixin_42108090/article/details/108315419

版权

计算机视觉专栏收录该内容

43 篇文章 1 订阅

订阅专栏

OverFeat :Integrated Recognition, Localization and Detection using Convolutional Networks
用不同大小的窗口滑动浏览整张图片，然后尝试用 CNN 对它们进行分类。
OverFeat adopted a strategy similar to early neural network face detectors by applying a ConvNet as a sliding window detector on an image pyramid.
OverFeat 是单阶段目标检测器的先驱。
Hand-engineered features and early neural networks.
SIFT features [25] were originally extracted at scale-space extrema and used for feature point matching. HOG features [5], and later SIFT features as well, were computed densely over entire image pyramids. These HOG and SIFT pyramids have been used in numerous works for image classification, object detection, human pose estimation, and more. There has also been significant interest in computing featurized image pyramids quickly.