GOTURN(Generic Object Tracking Using Regression Networks ＥＣＣＶ２０１６)

This tracker is able to track objects at 100 fps. This real-time speed is due to two factors.
First, most previous neural network trackers are trained online. However, training neural networks is a slow process, leading to slow tracking. In contrast, our tracker is trained offline to learn a generic relationship between appearance and motion, so no online training is required.
Second, most trackers take a classification-based approah, classifying many image patches to find the target object. In contrast, this tracker used a regression-based approach, requiring just a single feed-forward pass through the network to regresses directly to the location of the target object.
The combination of offline training and one-pass regression leads to a significant speed-up compared to previous approaches and allows it to track objects at real-time speeds.

下面这个是ｔｒａｉｎ使用的网络，跟ｄｅｐｌｏｙ有点不一样哦。

自己根据这个模型和网络实现的ｔｅｓｔ过程，使用的是ｖｏｔ２０１４的数据库进行的测试，在测试过程中，在序列检测的过程中使用除第一帧（使用ｇｏｕｎｄｉｎｇ　ｔｒｕｔｈ）外，其他都是使用前一帧的结果进行ｔａｒｇｅｔ的获取，这使用过程中，发现，ＧＯＴＵＲＮ回出现当相似的物体相遇之后，跟踪有时候回出现跳转到另外一个物体（分析：可以是在序列过程中误差的叠加造成ｆｏｒｗａｒｄ时候的ｔａｒｇｅｔ一些偏差导致跟踪错误），还有，对于可形变物体跟踪效果也不好。(使用的时候要注意，输出的结果要除以１０，才是得到的是左上角，和右下角相对于ｐａｔｃｈ的位置)。

#include <string>#include <vector>#include "boost/algorithm/string.hpp"#include "google/protobuf/text_format.h"#include <opencv2/opencv.hpp>#include "caffe/blob.hpp"#include "caffe/layer.hpp"#include "caffe/common.hpp"#include "caffe/net.hpp"#include "caffe/proto/caffe.pb.h"#include "caffe/util/db.hpp"#include "caffe/util/format.hpp"#include "caffe/util/io.hpp"#include <stdio.h>#include <malloc.h>#include <fstream>#include <boost/progress.hpp>#include <fstream>#include <stdio.h>#include <boost/math/special_functions/next.hpp>#include <boost/random.hpp>#include <limits>#include "caffe/common.hpp"#include "caffe/util/math_functions.hpp"#include "caffe/util/rng.hpp"//#include "caffe/util/math_functions.hpp"using caffe::Blob;using caffe::Caffe;using caffe::Datum;using caffe::Net;using caffe::Layer;using std::string;namespace db = caffe::db;void loaddata_target(boost::shared_ptr<Net<float> >& net, std::string image_path);void loaddata_image(boost::shared_ptr<Net<float> >& net, std::string image_path);void loaddata_target(boost::shared_ptr<Net<float> >& net, cv::Mat image);void loaddata_image(boost::shared_ptr<Net<float> >& net, cv::Mat image);//int lap(int x1_min,int x1_max,int x2_min,int x2_max);int main(int argc, char** argv){  Caffe::set_mode(Caffe::GPU);  boost::shared_ptr<Net<float> > net(new Net<float>(argv[1], caffe::TEST));  net->CopyTrainedLayersFromBinaryProto(argv[2]);  //argv[3]表示的是包含pictures的文件夹  cv::Mat target, image;  cv::Mat pre_image, cur_image;  cv::Point point1, point2;  float coord;  char* filepath = new char[100];  std::ifstream in;//;(string(string(argv[3])));  sprintf(filepath, "%s/groundtruth.txt",argv[3]);  in.open(filepath);  delete [] filepath;  in >> coord;  in >> coord;  in >> coord;  point1.x = int(coord);  in >> coord;  point1.y = int(coord);  in >> coord;  in >> coord;  in >> coord;  point2.x = int(coord);  in >> coord;  point2.y = int(coord);  in.close();  char* image_path = new char[100];  int count = 1;  int cols,rows;  int w,h;  while(1){      //std::cout << point1 << " " << point2 << std::endl;      sprintf(image_path,"%s/%.8d.jpg",argv[3],count++);      pre_image = cv::imread(image_path);      //std::cout << image_path << std::endl;      sprintf(image_path,"%s/%.8d.jpg",argv[3],count++);      cur_image = cv::imread(image_path);      cols = cur_image.cols;      rows = cur_image.rows;      if(cols == 0 || rows == 0) break;      w = point2.x - point1.x;      h = point2.y - point1.y;      //std::cout << w <<" h=" << h << std::endl;      point1.x = point1.x - w/2;      point1.y = point1.y - h/2;      point2.x = point2.x + w/2;      point2.y = point2.y + h/2;      //std::cout << point1 << " " << point2 << std::endl;      point1.x = point1.x < 0 ? 0 : point1.x;      point1.y = point1.y < 0 ? 0 : point1.y;      point2.x = point2.x > cols ? cols : point2.x;      point2.y = point2.y > rows ? rows : point2.y;     // std::cout << point1 << " " << point2 << std::endl;      target = pre_image(cv::Rect(point1,point2));      image  = cur_image(cv::Rect(point1,point2));      loaddata_target(net,target);      loaddata_image(net,image);      net->Forward();      Blob<float>* output_layer = net->output_blobs()[0];      std::vector<int> points;      points.push_back(int(image.cols*((output_layer->cpu_data()[0]/10))));      points.push_back(int(image.rows*((output_layer->cpu_data()[1]/10))));      points.push_back(int(image.cols*((output_layer->cpu_data()[2]/10))));      points.push_back(int(image.rows*((output_layer->cpu_data()[3]/10))));      point2.x = point1.x + points[2];      point2.y = point1.y+ points[3];      point1.x  += points[0];      point1.y  += points[1];      cv::rectangle(cur_image, cv::Rect(point1,point2),cv::Scalar(0,225,255),1);      cv::imshow("target",target);      cv::imshow("image",cur_image);      if(count == 3)          cv::waitKey(0);      cv::waitKey(33);      //std::cout << image_path << std::endl;      //target = pre_image();     // break;  }  delete [] image_path;  return 1;}void loaddata_target(boost::shared_ptr<Net<float> >& net, std::string image_path){  Blob<float>* input_layer = net->input_blobs()[0];  int width, height;  width = input_layer->width();  height = input_layer->height();  int size = width*height;  cv::Mat image = cv::imread(image_path,-1);  cv::Mat image_resized;  cv::resize(image, image_resized, cv::Size(height, width));  float* input_data = input_layer->mutable_cpu_data();  int temp,idx;  for(int i = 0; i < height; ++i){    uchar* pdata = image_resized.ptr<uchar>(i);    for(int j = 0; j < width; ++j){      temp = 3*j;      idx = i*width+j;      input_data[idx] = (pdata[temp+2]);      input_data[idx+size] = (pdata[temp+1]);      input_data[idx+2*size] = (pdata[temp+0]);    }  }  //cv::imshow("image",image_resized);}void loaddata_image(boost::shared_ptr<Net<float> >& net, std::string image_path){  Blob<float>* input_layer = net->input_blobs()[1];  int width, height;  width = input_layer->width();  height = input_layer->height();  int size = width*height;  cv::Mat image = cv::imread(image_path,-1);  cv::Mat image_resized;  cv::resize(image, image_resized, cv::Size(height, width));  float* input_data = input_layer->mutable_cpu_data();  int temp,idx;  for(int i = 0; i < height; ++i){    uchar* pdata = image_resized.ptr<uchar>(i);    for(int j = 0; j < width; ++j){      temp = 3*j;      idx = i*width+j;      input_data[idx] = (pdata[temp+2]);      input_data[idx+size] = (pdata[temp+1]);      input_data[idx+2*size] = (pdata[temp+0]);    }  }  //cv::waitKey(0);  //cv::imshow("image",image_resized);}void loaddata_target(boost::shared_ptr<Net<float> >& net, cv::Mat image){  Blob<float>* input_layer = net->input_blobs()[0];  int width, height;  width = input_layer->width();  height = input_layer->height();  int size = width*height;  //cv::Mat image = cv::imread(image_path,-1);  cv::Mat image_resized;  cv::resize(image, image_resized, cv::Size(height, width));  float* input_data = input_layer->mutable_cpu_data();  int temp,idx;  for(int i = 0; i < height; ++i){    uchar* pdata = image_resized.ptr<uchar>(i);    for(int j = 0; j < width; ++j){      temp = 3*j;      idx = i*width+j;      input_data[idx] = (pdata[temp+2])-104;      input_data[idx+size] = (pdata[temp+1])-117;      input_data[idx+2*size] = (pdata[temp+0])-123;    }  }  //cv::imshow("image",image_resized);}void loaddata_image(boost::shared_ptr<Net<float> >& net, cv::Mat image){  Blob<float>* input_layer = net->input_blobs()[1];  int width, height;  width = input_layer->width();  height = input_layer->height();  int size = width*height;  //cv::Mat image = cv::imread(image_path,-1);  cv::Mat image_resized;  cv::resize(image, image_resized, cv::Size(height, width));  float* input_data = input_layer->mutable_cpu_data();  int temp,idx;  for(int i = 0; i < height; ++i){    uchar* pdata = image_resized.ptr<uchar>(i);    for(int j = 0; j < width; ++j){      temp = 3*j;      idx = i*width+j;      input_data[idx] = (pdata[temp+2])-104;      input_data[idx+size] = (pdata[temp+1])-117;      input_data[idx+2*size] = (pdata[temp+0])-123;    }  }  //cv::waitKey(0);  //cv::imshow("image",image_resized);}

ｄｅｐｌｏｙ.prototxt

name: "CaffeNet"input: "target"input: "image"#targetinput_dim: 1input_dim: 3input_dim: 227input_dim: 227#imageinput_dim: 1input_dim: 3input_dim: 227input_dim: 227layer {  name: "conv1"  type: "Convolution"  bottom: "target"  top: "conv1"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 96    kernel_size: 11    stride: 4    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu1"  type: "ReLU"  bottom: "conv1"  top: "conv1"}layer {  name: "pool1"  type: "Pooling"  bottom: "conv1"  top: "pool1"  pooling_param {    pool: MAX    kernel_size: 3    stride: 2  }}layer {  name: "norm1"  type: "LRN"  bottom: "pool1"  top: "norm1"  lrn_param {    local_size: 5    alpha: 0.0001    beta: 0.75  }}layer {  name: "conv2"  type: "Convolution"  bottom: "norm1"  top: "conv2"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 256    pad: 2    kernel_size: 5    group: 2    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu2"  type: "ReLU"  bottom: "conv2"  top: "conv2"}layer {  name: "pool2"  type: "Pooling"  bottom: "conv2"  top: "pool2"  pooling_param {    pool: MAX    kernel_size: 3    stride: 2  }}layer {  name: "norm2"  type: "LRN"  bottom: "pool2"  top: "norm2"  lrn_param {    local_size: 5    alpha: 0.0001    beta: 0.75  }}layer {  name: "conv3"  type: "Convolution"  bottom: "norm2"  top: "conv3"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 384    pad: 1    kernel_size: 3    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu3"  type: "ReLU"  bottom: "conv3"  top: "conv3"}layer {  name: "conv4"  type: "Convolution"  bottom: "conv3"  top: "conv4"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 384    pad: 1    kernel_size: 3    group: 2    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu4"  type: "ReLU"  bottom: "conv4"  top: "conv4"}layer {  name: "conv5"  type: "Convolution"  bottom: "conv4"  top: "conv5"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 256    pad: 1    kernel_size: 3    group: 2    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu5"  type: "ReLU"  bottom: "conv5"  top: "conv5"}layer {  name: "pool5"  type: "Pooling"  bottom: "conv5"  top: "pool5"  pooling_param {    pool: MAX    kernel_size: 3    stride: 2  }}layer {  name: "conv1_p"  type: "Convolution"  bottom: "image"  top: "conv1_p"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 96    kernel_size: 11    stride: 4    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu1_p"  type: "ReLU"  bottom: "conv1_p"  top: "conv1_p"}layer {  name: "pool1_p"  type: "Pooling"  bottom: "conv1_p"  top: "pool1_p"  pooling_param {    pool: MAX    kernel_size: 3    stride: 2  }}layer {  name: "norm1_p"  type: "LRN"  bottom: "pool1_p"  top: "norm1_p"  lrn_param {    local_size: 5    alpha: 0.0001    beta: 0.75  }}layer {  name: "conv2_p"  type: "Convolution"  bottom: "norm1_p"  top: "conv2_p"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 256    pad: 2    kernel_size: 5    group: 2    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu2_p"  type: "ReLU"  bottom: "conv2_p"  top: "conv2_p"}layer {  name: "pool2_p"  type: "Pooling"  bottom: "conv2_p"  top: "pool2_p"  pooling_param {    pool: MAX    kernel_size: 3    stride: 2  }}layer {  name: "norm2_p"  type: "LRN"  bottom: "pool2_p"  top: "norm2_p"  lrn_param {    local_size: 5    alpha: 0.0001    beta: 0.75  }}layer {  name: "conv3_p"  type: "Convolution"  bottom: "norm2_p"  top: "conv3_p"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 384    pad: 1    kernel_size: 3    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu3_p"  type: "ReLU"  bottom: "conv3_p"  top: "conv3_p"}layer {  name: "conv4_p"  type: "Convolution"  bottom: "conv3_p"  top: "conv4_p"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 384    pad: 1    kernel_size: 3    group: 2    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu4_p"  type: "ReLU"  bottom: "conv4_p"  top: "conv4_p"}layer {  name: "conv5_p"  type: "Convolution"  bottom: "conv4_p"  top: "conv5_p"  param {    lr_mult: 0    decay_mult: 1  }  param {    lr_mult: 0    decay_mult: 0  }  convolution_param {    num_output: 256    pad: 1    kernel_size: 3    group: 2    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu5_p"  type: "ReLU"  bottom: "conv5_p"  top: "conv5_p"}layer {  name: "pool5_p"  type: "Pooling"  bottom: "conv5_p"  top: "pool5_p"  pooling_param {    pool: MAX    kernel_size: 3    stride: 2  }}layer {  name: "concat"  type: "Concat"  bottom: "pool5"  bottom: "pool5_p"  top: "pool5_concat"  concat_param {    axis: 1  }}layer {  name: "fc6-new"  type: "InnerProduct"  bottom: "pool5_concat"  top: "fc6"  param {    lr_mult: 10    decay_mult: 1  }  param {    lr_mult: 20    decay_mult: 0  }  inner_product_param {    num_output: 4096    weight_filler {      type: "gaussian"      std: 0.005    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu6"  type: "ReLU"  bottom: "fc6"  top: "fc6"}layer {  name: "drop6"  type: "Dropout"  bottom: "fc6"  top: "fc6"  dropout_param {    dropout_ratio: 0.5  }}layer {  name: "fc7-new"  type: "InnerProduct"  bottom: "fc6"  top: "fc7"  param {    lr_mult: 10    decay_mult: 1  }  param {    lr_mult: 20    decay_mult: 0  }  inner_product_param {    num_output: 4096    weight_filler {      type: "gaussian"      std: 0.005    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu7"  type: "ReLU"  bottom: "fc7"  top: "fc7"}layer {  name: "drop7"  type: "Dropout"  bottom: "fc7"  top: "fc7"  dropout_param {    dropout_ratio: 0.5  }}layer {  name: "fc7-newb"  type: "InnerProduct"  bottom: "fc7"  top: "fc7b"  param {    lr_mult: 10    decay_mult: 1  }  param {    lr_mult: 20    decay_mult: 0  }  inner_product_param {    num_output: 4096    weight_filler {      type: "gaussian"      std: 0.005    }    bias_filler {      type: "constant"      value: 1    }  }}layer {  name: "relu7b"  type: "ReLU"  bottom: "fc7b"  top: "fc7b"}layer {  name: "drop7b"  type: "Dropout"  bottom: "fc7b"  top: "fc7b"  dropout_param {    dropout_ratio: 0.5  }}layer {  name: "fc8-shapes"  type: "InnerProduct"  bottom: "fc7b"  top: "fc8"  param {    lr_mult: 10    decay_mult: 1  }  param {    lr_mult: 20    decay_mult: 0  }  inner_product_param {    num_output: 4    weight_filler {      type: "gaussian"      std: 0.01    }    bias_filler {      type: "constant"      value: 0    }  }}