技术标签: opencv实例源码演示 OpenCV dnn 目标检测 # Caffe tensorflow ssd opencv objection
opencv的dnn模块读取models.yml文件中包含的目标检测模型有5种,这里实例TensorFlow implementation of SSD model 网络。
https://github.com/tensorflow/models/tree/master/research/object_detection
ssd_tf:
model: “ssd_mobilenet_v1_coco_2017_11_17.pb”
config: “ssd_mobilenet_v1_coco_2017_11_17.pbtxt”
mean: [0, 0, 0]
scale: 1.0
width: 300
height: 300
rgb: true
classes: “object_detection_classes_coco.txt”
sample: “object_detection”
整体代码和前面相同,仅配置不同
#include <fstream>
#include <sstream>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace dnn;
float confThreshold, nmsThreshold;
std::vector<std::string> classes;
void postprocess(Mat& frame, const std::vector<Mat>& out, Net& net);
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
int main(int argc, char** argv)
{
// 根据选择的检测模型文件进行配置
confThreshold = 0.5;
nmsThreshold = 0.4;
float scale = 1.0;
Scalar mean = {
0, 0, 0 };
bool swapRB = true;
int inpWidth = 300;
int inpHeight = 300;
String modelPath = "../../data/testdata/dnn/ssd_mobilenet_v1_coco_2017_11_17.pb";
String configPath = "../../data/testdata/dnn/ssd_mobilenet_v1_coco_2017_11_17.pbtxt";
String framework = "";
int backendId = cv::dnn::DNN_BACKEND_OPENCV;
int targetId = cv::dnn::DNN_TARGET_CPU;
String classesFile = R"(../../data/dnn/object_detection_classes_coco.txt)";
// Open file with classes names.
if (!classesFile.empty()) {
const std::string& file = classesFile;
std::ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError, "File " + file + " not found");
std::string line;
while (std::getline(ifs, line)) {
classes.push_back(line);
}
}
// Load a model.
Net net = readNet(modelPath, configPath, framework);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
std::vector<String> outNames = net.getUnconnectedOutLayersNames();
// Create a window
static const std::string kWinName = "Deep learning object detection in OpenCV";
// Open a video file or an image file or a camera stream.
VideoCapture cap;
cap.open(0);
// Process frames.
Mat frame, blob;
while (waitKey(1) < 0) {
cap >> frame;
if (frame.empty()) {
waitKey();
break;
}
// Create a 4D blob from a frame.
Size inpSize(inpWidth > 0 ? inpWidth : frame.cols,
inpHeight > 0 ? inpHeight : frame.rows);
blobFromImage(frame, blob, scale, inpSize, mean, swapRB, false);
// Run a model.
net.setInput(blob);
if (net.getLayer(0)->outputNameToIndex("im_info") != -1) // Faster-RCNN or R-FCN
{
resize(frame, frame, inpSize);
Mat imInfo = (Mat_<float>(1, 3) << inpSize.height, inpSize.width, 1.6f);
net.setInput(imInfo, "im_info");
}
std::vector<Mat> outs;
net.forward(outs, outNames);
postprocess(frame, outs, net);
// Put efficiency information.
std::vector<double> layersTimes;
double freq = getTickFrequency() / 1000;
double t = net.getPerfProfile(layersTimes) / freq;
std::string label = format("Inference time: %.2f ms", t);
putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
imshow(kWinName, frame);
}
return 0;
}
void postprocess(Mat& frame, const std::vector<Mat>& outs, Net& net)
{
static std::vector<int> outLayers = net.getUnconnectedOutLayers();
static std::string outLayerType = net.getLayer(outLayers[0])->type;
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
if (net.getLayer(0)->outputNameToIndex("im_info") != -1) // Faster-RCNN or R-FCN
{
// Network produces output blob with a shape 1x1xNx7 where N is a number of
// detections and an every detection is a vector of values
// [batchId, classId, confidence, left, top, right, bottom]
CV_Assert(outs.size() == 1);
float* data = (float*)outs[0].data;
for (size_t i = 0; i < outs[0].total(); i += 7) {
float confidence = data[i + 2];
if (confidence > confThreshold) {
int left = (int)data[i + 3];
int top = (int)data[i + 4];
int right = (int)data[i + 5];
int bottom = (int)data[i + 6];
int width = right - left + 1;
int height = bottom - top + 1;
classIds.push_back((int)(data[i + 1]) - 1); // Skip 0th background class id.
boxes.push_back(Rect(left, top, width, height));
confidences.push_back(confidence);
}
}
}
else if (outLayerType == "DetectionOutput") {
// Network produces output blob with a shape 1x1xNx7 where N is a number of
// detections and an every detection is a vector of values
// [batchId, classId, confidence, left, top, right, bottom]
CV_Assert(outs.size() == 1);
float* data = (float*)outs[0].data;
for (size_t i = 0; i < outs[0].total(); i += 7) {
float confidence = data[i + 2];
if (confidence > confThreshold) {
int left = (int)(data[i + 3] * frame.cols);
int top = (int)(data[i + 4] * frame.rows);
int right = (int)(data[i + 5] * frame.cols);
int bottom = (int)(data[i + 6] * frame.rows);
int width = right - left + 1;
int height = bottom - top + 1;
classIds.push_back((int)(data[i + 1]) - 1); // Skip 0th background class id.
boxes.push_back(Rect(left, top, width, height));
confidences.push_back(confidence);
}
}
}
else if (outLayerType == "Region") {
for (size_t i = 0; i < outs.size(); ++i) {
// Network produces output blob with a shape NxC where N is a number of
// detected objects and C is a number of classes + 4 where the first 4
// numbers are [center_x, center_y, width, height]
float* data = (float*)outs[i].data;
for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols) {
Mat scores = outs[i].row(j).colRange(5, outs[i].cols);
Point classIdPoint;
double confidence;
minMaxLoc(scores, 0, &confidence, 0, &classIdPoint);
if (confidence > confThreshold) {
int centerX = (int)(data[0] * frame.cols);
int centerY = (int)(data[1] * frame.rows);
int width = (int)(data[2] * frame.cols);
int height = (int)(data[3] * frame.rows);
int left = centerX - width / 2;
int top = centerY - height / 2;
classIds.push_back(classIdPoint.x);
confidences.push_back((float)confidence);
boxes.push_back(Rect(left, top, width, height));
}
}
}
}
else
CV_Error(Error::StsNotImplemented, "Unknown output layer type: " + outLayerType);
std::vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
for (size_t i = 0; i < indices.size(); ++i) {
int idx = indices[i];
Rect box = boxes[idx];
drawPred(classIds[idx], confidences[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame);
}
}
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
{
rectangle(frame, Point(left, top), Point(right, bottom), Scalar(0, 255, 0));
std::string label = format("%.2f", conf);
if (!classes.empty()) {
CV_Assert(classId < (int)classes.size());
label = classes[classId] + ": " + label;
}
int baseLine;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
top = max(top, labelSize.height);
rectangle(frame, Point(left, top - labelSize.height),
Point(left + labelSize.width, top + baseLine), Scalar::all(255), FILLED);
putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.5, Scalar());
}
CPU: 40ms,cpu 70%, mem 180M, gpu 4.5%
OPENCL: 120ms, cpu 40%, mem 197M, gpu 0.7%
文章浏览阅读1.5w次,点赞10次,收藏129次。文章目录目录模型评估评价指标1.分类评价指标acc、recall、F1、混淆矩阵、分类综合报告1.准确率方式一:accuracy_score方式二:metrics2.召回率3.F1分数4.混淆矩阵5.分类报告6.kappa scoreROC1.ROC计算2.ROC曲线3.具体实例2.回归评价指标3.聚类评价指标1.Adjusted Rand index 调整兰德系数2.Mutual Informa..._model.score
文章浏览阅读344次。因工作需要,在Apache上使用,重新学习配置mod_jk1. 分别安装Apache和Tomcat:2. 编辑httpd-vhosts.conf: LoadModule jk_module modules/mod_jk.so #加载mod_jk模块 JkWorkersFile conf/workers.properties #添加worker信息 JkLogFil_apache mod_jk 虚拟
文章浏览阅读335次。待老夫kotlin大成,扩展:MotionLayout 与 CoordinatorLayout,DrawerLayout,ViewPager 的 交互众所周知,MotionLayout 的 动画是有完成度的 即Progress ,他在0-1之间变化,一.CoordinatorLayout 与AppBarLayout 交互时,其实就是监听 offsetliner 这个 偏移量的变化 同样..._android onoffsetchanged
文章浏览阅读8.3k次,点赞3次,收藏19次。【转】多核处理器的工作原理及优缺点《处理器关于多核概念与区别 多核处理器工作原理及优缺点》原文传送门 摘要:目前关于处理器的单核、双核和多核已经得到了普遍的运用,今天我们主要说说关于多核处理器的一些相关概念,它的工作与那里以及优缺点而展开的分析。1、多核处理器 多核处理器是指在一枚处理器中集成两个或多个完整的计算引擎(内核),此时处理器能支持系统总线上的多个处理器,由总..._多核处理器怎么工作
文章浏览阅读306次。1. eclipse配置lombok 拷贝lombok.jar到eclipse.ini同级文件夹下,编辑eclipse.ini文件,添加: -javaagent:lombok.jar2. myeclipse配置lombok myeclipse像eclipse配置后,定义对象后,直接访问方法,可能会出现飘红的报错。 如果出现报错,可按照以下方式解决。 ..._eclispe每次运行个新项目都需要重新配置lombok吗
文章浏览阅读1.2w次,点赞31次,收藏126次。#注意:笔者在2021/11/11当天调试过这个代码是可用的,由于pdfminer版本的更新,网络上大多数的语法没有更新,我也是找了好久的文章才修正了我的代码,仅供学习参考。1、把pdf文件移动到本代码文件的同一个目录下,笔者是在pycharm里面运行的项目,下图中的x1文件夹存储了我需要转换成文本文件的所有pdf文件。然后要在此目录下创建一个存放转换后的txt文件的文件夹,如图中的txt文件夹。2、编写代码 (1)导入所需库# coding:utf-8import ..._python批量读取文字并批量保存
文章浏览阅读1.4k次。http://blog.csdn.net/pipisorry/article/details/52902234Scala 访问修饰符Scala 访问修饰符基本和Java的一样,分别有:private,protected,public。如果没有指定访问修饰符符,默认情况下,Scala对象的访问级别都是 public。Scala 中的 private 限定符,比 Java 更严格,在嵌套类情况下,外层_scala ===运算符
文章浏览阅读2.6k次,点赞7次,收藏19次。ER图导出为PDF或图片格式_数据库怎么导出er图
文章浏览阅读655次。CREATE OR REPLACE TRIGGER Trg_ReimFactBEFORE UPDATEON BP_OrderFOR EACH ROWDECLAREPRAGMA AUTONOMOUS_TRANSACTION;--自制事务fc varchar2(255);BEGINIF ( :NEW.orderstate = 2AND :NEW.TransState = 1 ) THENBEG..._oracle触发器更新同一张表
文章浏览阅读513次。目录概念debouncethrottle实现debouncethrottle应用场景debouncethrottle场景举例debouncethrottle概念debounce字面理解是“防抖”,何谓“防抖”,就是连续操作结束后再执行,以网页滚动为例,debounce要等到用户停止滚动后才执行,将连续多次执行合并为一次执行。throttle字面理解是“节流”,何谓“节流”,就是确保一段时..._throttle和debounce应用在哪些场景
文章浏览阅读526次。regex() $regex 正则表达式用于模式匹配,基本上是用于文档中的发现字符串 (下面有例子)注意:若未加 @Field("名称") ,则识别mongdb集合中的key名为实体类属性名。也可以对数组进行索引,如果被索引的列是数组时,MongoDB会索引这个数组中的每一个元素。也可以对整个Document进行索引,排序是预定义的按插入BSON数据的先后升序排列。save: 若新增数据的主键已经存在,则会对当前已经存在的数据进行修改操作。_java 操作mongodb
文章浏览阅读1k次。今天push代码到github仓库时出现这个报错TACKCHEN-MB0:tc-image tackchen$ git pushremote: Support for password authentication was removed on August 13, 2021. Please use a personal access token instead.remote: Please see https://github.blog/2020-12-15-token-authentication_git push remote: support for password authentication was removed on august 1