搜索资源列表
rcnn-depth-master
- datasets for edge detection
caffe-ssd
- SSD和faster rcnn都是目前比较经典的基于caffe深度学习架构的一种方法,是目前比较先进的目标检测方法(SSD and faster RCNN are the most classic methods based on Caffe deep learning architecture, and they are more advanced target detection methods)
Faster-RCNN_TF-master (2)
- 机器学习 关于 faster r-cnn 进行object detection(This is an experimental Tensorflow implementation of Faster RCNN - a convnet for object detection with a region proposal network. For details about R-CNN please refer to the paper Faster R-CNN: Towards Real-Tim
py-faster-rcnn-master
- fast-rcnn源码,可用于快速目标检测，如行人识别 车辆识别 车标识别(This is an sourcecode for python fast-rcnn)
rcnn-depth-master
- 反锐化掩膜技术(Unsharp Masking,UM)又称为模糊蒙片处理，是一种经典的图像边缘增强算法，提高图像的高频分量部分来增强其视觉效果[18,19].反锐化掩模技术最早是应用于摄影技术中，以增强图像的边缘和细节。光学上的操作方法是将聚焦的正片和散焦的负片在底片上进行叠加，结果是增强了正片高频成份，从而增强了轮廓，散焦的负片相当于“模糊”模板（掩模），它与锐化的作用正好相反，因此，该方法被称为反锐化掩模法。(The sharpenmembrane Technology (Unsharp M
rcnn.tar
- 物体检测经典算法rcnn的实现，基于caffe平台(Object Detection algorithm RCNN implementation, based on caffe platform)