bbox

目录 论文信息 前言 Introduction Network Architecture Network preparation Reverse Connection Reference Boxes Objectness Prior Detection and Bounding Box Regression Combining Objectness Prior with Detection Training and Testing Loss Function Joint Training and Testing Data augmentation Inference Results Ablation Analysis Do Multiple Layers Help? Objectness Prior Generating Region Proposals Conclusion 论文信息 Tao Kong, Fuchun Sun, Anbang Yao, Huaping Liu, Ming Lu, Yurong Chen. RON: Reverse Connection with Objectness Prior Networks for Object Detection. CVPR 2017. https://arxiv.org/abs/1707.01691 前言

需要准备三个路径： 1、一个是进行测试时所使用的那些图片，找到其路径 2、result.txt所在的路径 3、生成图像的存放路径 1 #!/usr/bin/env python 2 3 4 from __future__ import absolute_import 5 from __future__ import division 6 from __future__ import print_function 7 8 import _init_paths 9 from model.config import cfg 10 from model.test import im_detect 11 from model.nms_wrapper import nms 12 13 from utils.timer import Timer 14 import tensorflow as tf 15 import matplotlib.pyplot as plt 16 from PIL import Image 17 import numpy as np 18 import os, cv2 19 import argparse 20 21 22 from nets.vgg16 import vgg16 23 from nets.resnet_v1 import resnetv1 24 25

OE代码样例 /* -*-c++-*- */ /* osgEarth - Dynamic map generation toolkit for OpenSceneGraph * Copyright 2016 Pelican Mapping * http://osgearth.org * * osgEarth is free software; you can redistribute it and/or modify * it under the terms of the GNU Lesser General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND

官方给的模型可以检测80多个类别，这里我们只检测行人，就需要将代码进行稍微修改即可： 项目路径图： 查看./data/classes/coco.names 类别的索引： 这里person为第1个，即索引为0 更改： . / core / utils . py draw_bbox函数(将roi_index设置为你想要的索引即可，我这里为0)： def draw_bbox ( image , bboxes , classes = read_class_names ( cfg . YOLO . CLASSES ) , show_label = True ) : "" " bboxes : [ x_min , y_min , x_max , y_max , probability , cls_id ] format coordinates . "" " roi_index = 0 num_classes = len ( classes ) image_h , image_w , _ = image . shape hsv_tuples = [ ( 1.0 * x / num_classes , 1. , 1. ) for x in range ( num_classes ) ] colors = list ( map ( lambda x : colorsys . hsv_to_rgb (