KITTI 3D目标检测离线评估工具包说明
本文是KITTI 3D目标检测离线评估工具包的使用说明和相关代码学习文件,从这里可以下载。更新于2018.09.20。
文章目录
- KITTI 3D目标检测离线评估工具包说明
- 工具包README文件
- 代码学习
- evaluate_object_3d_offline.cpp
- 主函数
- eval
- tBox\tGroundtruth\tDetection
- eval_class
- saveAndPlotPlots
- computeStatistics
工具包README文件
这个工具包是离线运行的,可以在使用者的电脑上评估验证集(从KITTI训练集中选出来的)。评估的指标包括:
- 重叠率:overlap on image (AP)
- 旋转重叠率:oriented overlap on image (AOS)
- 地面重叠率(鸟瞰视角):overlap on ground-plane (AP)
- 3D重叠率:overlap in 3D (AP)
首先在终端编译evaluate_object_3d_offline.cpp
文件,之后运行评估命令:
./evaluate_object_3d_offline groundtruth_dir result_dir
需要注意的是,使用者并不需要评估整个KITTI训练集。Evaluator只评估有结果存在的那些样本。
代码学习
这一部分主要是希望通过学习代码理解所得到的结果和图像,并不深究其中的语法。
总结:
- 这个函数主要用于评估实验结果,但是评估过程中并未评估所有的结果,而是挑选了置信概率最大的前几个结果(程序中默认取前41个),函数计算了precision和recall并画出二者的关系曲线(关于这两个算法评估概念可以参看这里的说明)。
- 评估算法是按照类别判断的,对于KITTI库分为3类(人、车、自行车),每个类别中有不同难度(简单、中等、困难),曲线是每个类别对应一个曲线图,图中包括三种难度下算法的评估结果曲线。
- 算法中还将评估分为2D评估、鸟瞰评估、3D评估三种不同角度,其中2D评估可以有带转角的评估AOS,另外两种则不评估此项。
- 结果或真值数据的存储格式应当遵从这个顺序:目标类型(人、车、自行车对应的字符串),是否截断(失效值-1),是否遮挡(无遮挡、部分遮挡、全部遮挡)(失效值-1),旋转角度(失效值-10),左上角坐标x1,左上角坐标y1,右下角坐标x2,右下角坐标y2,高,宽,长,box中心坐标t1,box中心坐标t2,box中心坐标t3,box朝向ry,阈值(score)。其中,真值数据不具有最后一项,结果数据是否截断、是否遮挡对应数据无效。
- t*在函数toPolygon中用到了,但是含义不清楚;ry的含义也不清楚。
evaluate_object_3d_offline.cpp
这一部分记录了evaluate_object_3d_offline.cpp文件的学习笔记,包括其中的主函数、用于评估总过程的eval函数、定义存储信息含义的结构体tBox\tGroundtruth\tDetection、具体实施按类评估的eval_class、和用于存储结果并画出图像的saveAndPlotPlots。
主函数
主导整个评估过程。
int32_t main (int32_t argc,char *argv[]) {
// 需要2或4个输入
//如果输入个数为3,显示用法并返回
if (argc!=3) {
cout << "Usage: ./eval_detection_3d_offline gt_dir result_dir" << endl;
return 1; return 1;
}
//读取输入
string gt_dir = argv[1]; //第一个输入是真值路径
string result_dir = argv[2]; //第二个输入是结果路径
//定义用于提示的邮件地址
Mail *mail;
mail = new Mail();
mail->msg("Thank you for participating in our evaluation!");
//运行评估过程
//如果评估过程成功,有邮箱地址就将结果链接发送到邮箱,没有就保存在本地plot下
//否则,返回错误信息并删除结果目录
if (eval(gt_dir, result_dir, mail)) {
mail->msg("Your evaluation results are available at:");
mail->msg(result_dir.c_str());
} else {
system(("rm -r " + result_dir + "/plot").c_str());
mail->msg("An error occured while processing your results.");
}
//发送邮件并退出
delete mail;
return 0;
}
eval
从主函数中可以看到,起评估作用的是eval函数,下面贴出eval函数和学习说明:
bool eval(string gt_dir, string result_dir, Mail* mail){
//设置全局变量CLASS_NAMES,其中包括car, pedestrain, cyclist
initGlobals();
// 真值和结果路径:
// string gt_dir = "data/object/label_2"; 真值路径
// string result_dir = "results/" + result_sha; 结果路径
//保存eval结果图的路径
string plot_dir = result_dir + "/plot";
// 按照上面定义的plot路径创建输出目录
system(("mkdir " + plot_dir).c_str());
//定义了两个二维数组groundtruth和detections,用于存储真值和检测结果
//定义了一个名为groundtruth的二维数组,其中每个位置上的数据类型是tGroundtruth,其中存有box的类型、两组对角坐标(左上、右下)、图像转角等信息。具体见tBox和tGroundtruth说明。
vector< vector<tGroundtruth> > groundtruth;
//参考上面真值定义
vector< vector<tDetection> > detections;
//存储是否计算旋转重叠率AOS(在加载检测结果的时候可能被设成false),并记录本次提交都包含哪些labels
//默认计算AOS(仅对于2D评估)
bool compute_aos=true;
//定义eval_image,存储bool变量,默认值为false,长度为3
vector<bool> eval_image(NUM_CLASS, false);
vector<bool> eval_ground(NUM_CLASS, false);
vector<bool> eval_3d(NUM_CLASS, false);
// 读取所有图像的真值和检测结果
mail->msg("Loading detections...");
//存储所有有结果的图像编号
std::vector<int32_t> indices = getEvalIndices(result_dir + "/data/");
printf("number of files for evaluation: %d\n", (int)indices.size());
//对于所有图像,读取真值并检查是否都数据读取成功
for (int32_t i=0; i<indices.size(); i++) {
// 生成文件名
//定义一个长为256的字符串,叫file_name
char file_name[256];
sprintf(file_name,"%06d.txt",indices.at(i));
//读取真值和结果(result poses)
bool gt_success,det_success; //定义变量用于存储是否读取成功
//读取所有图片的真值,每个图片15个值(具体参见tGroundtruth),存入gt(用push_back一组接一组)
vector<tGroundtruth> gt = loadGroundtruth(gt_dir + "/" + file_name,gt_success);
//读取检测结果,共16个值(最后一个为score),如果转角的值(第4个)为-10,则不计算AOS
vector<tDetection> det = loadDetections(result_dir + "/data/" + file_name,
compute_aos, eval_image, eval_ground, eval_3d, det_success);
groundtruth.push_back(gt); //将gt存入groundtruth,也就是直到此时才给之前定义的goundtruth赋值
detections.push_back(det); //将det存入detections
//检查是否有读取失败,如果有,输出提示并返回
if (!gt_success) {
mail->msg("ERROR: Couldn't read: %s of ground truth. Please write me an email!", file_name);
return false;
}
if (!det_success) {
mail->msg("ERROR: Couldn't read: %s", file_name);
return false;
}
}
mail->msg(" done.");
// 定义指向结果文件的指针
FILE *fp_det=0, *fp_ori=0; //FILE是定义在C++标准库中的一个结构体,以指针的方式存储与内存中,其内容描述了一个文件
//对于所有类别评估2D窗口
for (int c = 0; c < NUM_CLASS; c++) {
CLASSES cls = (CLASSES)c; //找到序号对应的类别(此时cls的值为CAR、PEDESTRAIN或CYCLIST)
if (eval_image[c]) { //如果存在这一类别的图像(在loadDetections里面判断了)才计算
fp_det = fopen((result_dir + "/stats_" + CLASS_NAMES[c] + "_detection.txt").c_str(), "w"); //让fp_det指针指向用于存储结果的文件
if(compute_aos) //如果需要计算AOS,就让fp_ori指向用于存储AOS的文件(这里默认不计算)
fp_ori = fopen((result_dir + "/stats_" + CLASS_NAMES[c] + "_orientation.txt").c_str(),"w");
vector<double> precision[3], aos[3]; //定义两个长度为3的容器(对应简单、中等、困难三个级别),分别用于存储准确率和AOS
//如果有任意一个难度计算失败,则返回提示并退出(具体计算过程见eval_class说明)
if( !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, imageBoxOverlap, precision[0], aos[0], EASY, IMAGE)
|| !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, imageBoxOverlap, precision[1], aos[1], MODERATE, IMAGE)
|| !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, imageBoxOverlap, precision[2], aos[2], HARD, IMAGE)) {
mail->msg("%s evaluation failed.", CLASS_NAMES[c].c_str());
return false;
}
fclose(fp_det); //关闭detection的存储文件
saveAndPlotPlots(plot_dir, CLASS_NAMES[c] + "_detection", CLASS_NAMES[c], precision, 0); //画出曲线图(具体见saveAndPlotPlots说明)
if(compute_aos){ //如果需要计算AOS
saveAndPlotPlots(plot_dir, CLASS_NAMES[c] + "_orientation", CLASS_NAMES[c], aos, 1); //画出AOS曲线
fclose(fp_ori);
}
}
}
printf("Finished 2D bounding box eval.\n"); //结束2D评估
//对于鸟瞰图和3D box不要计算AOS
compute_aos = false;
//对于所有类别评估鸟瞰角度的bounding box
for (int c = 0; c < NUM_CLASS; c++) {
CLASSES cls = (CLASSES)c;
if (eval_ground[c]) { //如果存在该类型的图片才计算
fp_det = fopen((result_dir + "/stats_" + CLASS_NAMES[c] + "_detection_ground.txt").c_str(), "w"); //将指针指向用于存储鸟瞰结果的文件
vector<double> precision[3], aos[3]; //同2D,分别用于存储简单、中等和困难的情况
printf("Going to eval ground for class: %s\n", CLASS_NAMES[c].c_str());
//如果任意一个难度评估出错,提示并返回
if( !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, groundBoxOverlap, precision[0], aos[0], EASY, GROUND)
|| !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, groundBoxOverlap, precision[1], aos[1], MODERATE, GROUND)
|| !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, groundBoxOverlap, precision[2], aos[2], HARD, GROUND)) {
mail->msg("%s evaluation failed.", CLASS_NAMES[c].c_str());
return false;
}
fclose(fp_det);
saveAndPlotPlots(plot_dir, CLASS_NAMES[c] + "_detection_ground", CLASS_NAMES[c], precision, 0); //画出评估图像(具体参见saveAndPlotPlots说明)
}
}
printf("Finished Birdeye eval.\n"); //结束鸟瞰评估
//对于所有类别评估3D bounding boxes
for (int c = 0; c < NUM_CLASS; c++) {
CLASSES cls = (CLASSES)c;
if (eval_3d[c]) { //如果评估3D结果
fp_det = fopen((result_dir + "/stats_" + CLASS_NAMES[c] + "_detection_3d.txt").c_str(), "w"); //指针指向保存3D评估结果的文件
vector<double> precision[3], aos[3];
//如果任意一个难度评估出错,则提示并返回
printf("Going to eval 3D box for class: %s\n", CLASS_NAMES[c].c_str());
if( !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, box3DOverlap, precision[0], aos[0], EASY, BOX3D)
|| !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, box3DOverlap, precision[1], aos[1], MODERATE, BOX3D)
|| !eval_class(fp_det, fp_ori, cls, groundtruth, detections, compute_aos, box3DOverlap, precision[2], aos[2], HARD, BOX3D)) {
mail->msg("%s evaluation failed.", CLASS_NAMES[c].c_str());
return false;
}
fclose(fp_det);
saveAndPlotPlots(plot_dir, CLASS_NAMES[c] + "_detection_3d", CLASS_NAMES[c], precision, 0);
CLASS_NAMES[c], precision, 0);
}
}
printf("Finished 3D bounding box eval.\n");
// 成功完成评估,返回true
return true;
}
tBox\tGroundtruth\tDetection
tBox、tGroundtruth和tDetection结构体定义(用于存储真值和检测结果,eval代码中用到):
// holding bounding boxes for ground truth and detections
struct tBox {
string type; // 存储目标类型
double x1;
double y1; //与x1共同定位左上角坐标
double x2;
double y2; //与x2共同定位右下角坐标
double alpha; //图像转角
tBox (string type, double x1,double y1,double x2,double y2,double alpha) : //定义与结构体同名的构造函数,在调用时赋值
type(type),x1(x1),y1(y1),x2(x2),y2(y2),alpha(alpha) {}
};
//存储真值
struct tGroundtruth {
tBox box; //存储目标类型、box、朝向
double truncation; // truncation 0..1 这个目前还不理解干什么用的
int32_t occlusion; // 是否遮挡,0代表无遮挡,1代表部分遮挡,2代表完全遮挡
double ry; //目前未知含义
double t1, t2, t3; //目前未知含义
double h, w, l; //高、宽、长
tGroundtruth () : //这是这个结构体内所包含的同名构造函数,在调用时赋值
box(tBox("invalild",-1,-1,-1,-1,-10)),truncation(-1),occlusion(-1) {}
tGroundtruth (tBox box,double truncation,int32_t occlusion) :
box(box),truncation(truncation),occlusion(occlusion) {}
tGroundtruth (string type,double x1,double y1,double x2,double y2,double alpha,double truncation,int32_t occlusion) :
box(tBox(type,x1,y1,x2,y2,alpha)),truncation(truncation),occlusion(occlusion) {}
};
//存储检测结果
struct tDetection {
tBox box; //存储目标类型、box、朝向
double thresh; //检测概率(detection score)
double ry; //目前未知含义
double t1, t2, t3; //目前未知含义
double h, w, l; //高、宽、长
tDetection (): //定义与结构体同名的构造函数,在调用时赋值
box(tBox("invalid",-1,-1,-1,-1,-10)),thresh(-1000) {}
tDetection (tBox box,double thresh) :
box(box),thresh(thresh) {}
tDetection (string type,double x1,double y1,double x2,double y2,double alpha,double thresh) :
box(tBox(type,x1,y1,x2,y2,alpha)),thresh(thresh) {}
};
总结:
基本存储内容和顺序为:类型、左上角x、左上角y、右下角x、右下角y、朝向(角度);如果是真值那么后面会加上:截断信息(truncation)、遮挡情况;如果是检测结果后面会加上:检测概率(score)。
eval_class
eval_class代码部分:
bool eval_class (FILE *fp_det, FILE *fp_ori, CLASSES current_class,
const vector< vector<tGroundtruth> > &groundtruth,
const vector< vector<tDetection> > &detections, bool compute_aos,
double (*boxoverlap)(tDetection, tGroundtruth, int32_t),
vector<double> &precision, vector<double> &aos,
DIFFICULTY difficulty, METRIC metric) {
assert(groundtruth.size() == detections.size());
// 初始化
int32_t n_gt=0; // 真值图像总数(recall的分母)
vector<double> v, thresholds; //用于存储检测得到的概率detection scores,对其评估的结果用于recall的离散化
vector< vector<int32_t> > ignored_gt, ignored_det; //用于存储对于当前类别/难度忽略的图像标号
vector< vector<tGroundtruth> > dontcare; //用于存储在真值中包含的不关心区域的编号
//对于所有待测试图像进行:
for (int32_t i=0; i<groundtruth.size(); i++){
//用于保存当前帧中的忽略的真值、检测结果和不关心区域
vector<int32_t> i_gt, i_det;
vector<tGroundtruth> dc;
//只评估当前类别下的目标(忽略遮挡、截断的目标)
cleanData(current_class, groundtruth[i], detections[i], i_gt, dc, i_det, n_gt, difficulty);
ignored_gt.push_back(i_gt);
ignored_det.push_back(i_det);
dontcare.push_back(dc);
//计算数据以得到recall的值
tPrData pr_tmp = tPrData(); //用于存储相似度、true positives、false positives和false negatives
pr_tmp = computeStatistics(current_class, groundtruth[i], detections[i], dc, i_gt, i_det, false, boxoverlap, metric); //具体分析见ComputeStatistics说明,输出为tPrData类型
//将所有图片的detection scores存入向量
for(int32_t j=0; j<pr_tmp.v.size(); j++)
v.push_back(pr_tmp.v[j]);
}
//获取对于recall离散化必须要评估的scores(当不再满足(r_recall-current_recall) < (current_recall-l_recall)时就退出,在退出前,每有一个满足的current_recall就加1/40(数值认人为规定)),返回的是排名前40的满足条件的scores。
thresholds = getThresholds(v, n_gt);
//计算相关scores的TP、FP和FN
vector<tPrData> pr;
pr.assign(thresholds.size(),tPrData());
for (int32_t i=0; i<groundtruth.size(); i++){
//对于所有的scores/recall thresholds做如下操作:
for(int32_t t=0; t<thresholds.size(); t++){
tPrData tmp = tPrData();
tmp = computeStatistics(current_class, groundtruth[i], detections[i], dontcare[i],
ignored_gt[i], ignored_det[i], true, boxoverlap, metric,
compute_aos, thresholds[t], t==38); //具体分析见ComputeStatistics说明,输出为tPrData类型
//将当前帧下TP、FP、FN和AOS的数值加到当前阈值下的总评估中
pr[t].tp += tmp.tp;
pr[t].fp += tmp.fp;
pr[t].fn += tmp.fn;
if(tmp.similarity!=-1) //如果判断AOS
pr[t].similarity += tmp.similarity;
}
}
//计算recall、precision和AOS
vector<double> recall;
precision.assign(N_SAMPLE_PTS, 0);
if(compute_aos)
aos.assign(N_SAMPLE_PTS, 0);
double r=0;
for (int32_t i=0; i<thresholds.size(); i++)
r = pr[i].tp/(double)(pr[i].tp + pr[i].fn); //计算recall
recall.push_back(r);
precision[i] = pr[i].tp/(double)(pr[i].tp + pr[i].fp); //计算precision
if(compute_aos) //如果需要,计算AOS
aos[i] = pr[i].similarity/(double)(pr[i].tp + pr[i].fp);
}
//用最大值滤取precision和AOS(对i)
for (int32_t i=0; i<thresholds.size(); i++){
precision[i] = *max_element(precision.begin()+i, precision.end());
if(compute_aos)
aos[i] = *max_element(aos.begin()+i, aos.end());
}
//保存数据并返回计算成功
saveStats(precision, aos, fp_det, fp_ori); //在指针fp_det和fp_ori指向的文件中写入数据
return true;
}
saveAndPlotPlots
saveAndPlotPlots说明。
void saveAndPlotPlots(string dir_name,string file_name,string obj_type,vector<double> vals[],bool is_aos){
char command[1024];
//保存结果图像到指定路径
FILE *fp = fopen((dir_name + "/" + file_name + ".txt").c_str(),"w"); //保存在plot文件夹下对应类别的文件中
printf("save %s\n", (dir_name + "/" + file_name + ".txt").c_str());
//对于截取数量的样本,按正确率从高到低输出结果(格式:占40个样本的前百分之多少、简单类别、中等类别、困难类别分别对应的精度)
for (int32_t i=0; i<(int)N_SAMPLE_PTS; i++)
fprintf(fp,"%f %f %f %f\n",(double)i/(N_SAMPLE_PTS-1.0),vals[0][i],vals[1][i],vals[2][i]);
fclose(fp);
//求解三种难度下的精度之和,计算AP并显示
float sum[3] = {0, 0, 0};
for (int v = 0; v < 3; ++v)
for (int i = 0; i < vals[v].size(); i = i + 4)
sum[v] += vals[v][i];
printf("%s AP: %f %f %f\n", file_name.c_str(), sum[0] / 11 * 100, sum[1] / 11 * 100, sum[2] / 11 * 100);
//创建png + eps
for (int32_t j=0; j<2; j++) {
//打开文件
FILE *fp = fopen((dir_name + "/" + file_name + ".gp").c_str(),"w");
//保存gnuplot指令
if (j==0) {
fprintf(fp,"set term png size 450,315 font \"Helvetica\" 11\n");
fprintf(fp,"set output \"%s.png\"\n",file_name.c_str());
} else {
fprintf(fp,"set term postscript eps enhanced color font \"Helvetica\" 20\n");
fprintf(fp,"set output \"%s.eps\"\n",file_name.c_str());
}
//设置labels和范围
fprintf(fp,"set size ratio 0.7\n");
fprintf(fp,"set xrange [0:1]\n");
fprintf(fp,"set yrange [0:1]\n");
fprintf(fp,"set xlabel \"Recall\"\n");
if (!is_aos) fprintf(fp,"set ylabel \"Precision\"\n");
else fprintf(fp,"set ylabel \"Orientation Similarity\"\n");
obj_type[0] = toupper(obj_type[0]);
fprintf(fp,"set title \"%s\"\n",obj_type.c_str());
//线宽
int32_t lw = 5;
if (j==0) lw = 3;
//画error曲线
fprintf(fp,"plot ");
fprintf(fp,"\"%s.txt\" using 1:2 title 'Easy' with lines ls 1 lw %d,",file_name.c_str(),lw);
fprintf(fp,"\"%s.txt\" using 1:3 title 'Moderate' with lines ls 2 lw %d,",file_name.c_str(),lw);
fprintf(fp,"\"%s.txt\" using 1:4 title 'Hard' with lines ls 3 lw %d",file_name.c_str(),lw);
//关闭文件
fclose(fp);
//运行gnuplot以生成png + eps
sprintf(command,"cd %s; gnuplot %s",dir_name.c_str(),(file_name + ".gp").c_str());
system(command);
}
//生成pdf并截取
sprintf(command,"cd %s; ps2pdf %s.eps %s_large.pdf",dir_name.c_str(),file_name.c_str(),file_name.c_str());
system(command);
sprintf(command,"cd %s; pdfcrop %s_large.pdf %s.pdf",dir_name.c_str(),file_name.c_str(),file_name.c_str());
system(command);
sprintf(command,"cd %s; rm %s_large.pdf",dir_name.c_str(),file_name.c_str());
system(command);
}
computeStatistics
用于计算必要的数据,为recall的计算做准备:
tPrData computeStatistics(CLASSES current_class, const vector<tGroundtruth> >,
const vector<tDetection> &det, const vector<tGroundtruth> &dc,
const vector<int32_t> &ignored_gt, const vector<int32_t> &ignored_det,
bool compute_fp, double (*boxoverlap)(tDetection, tGroundtruth, int32_t),
METRIC metric, bool compute_aos=false, double thresh=0, bool debug=false){
tPrData stat = tPrData();
const double NO_DETECTION = -10000000;
vector<double> delta; //用于存储TP需要的角度的不同(AOS计算需要)
vector<bool> assigned_detection; //用于存储一个检测结果是被标注有效还是忽略
assigned_detection.assign(det.size(), false);
vector<bool> ignored_threshold;
ignored_threshold.assign(det.size(), false); //如果计算FP,用于存储低于阈值的检测结果
//在计算precision时,忽略低score的检测结果(需要FP)
if(compute_fp)
for(int32_t i=0; i<det.size(); i++)
if(det[i].thresh<thresh)
ignored_threshold[i] = true;
//评估所有真值boxes
for(int32_t i=0; i<gt.size(); i++){
//如果这个真值不属于当前或相似类别,则忽略
if(ignored_gt[i]==-1)
continue;
/*=======================================================================
find candidates (overlap with ground truth > 0.5) (logical len(det))
=======================================================================*/
int32_t det_idx = -1;
double valid_detection = NO_DETECTION;
double max_overlap = 0;
//寻找可能的检测结果
bool assigned_ignored_det = false;
for(int32_t j=0; j<det.size(); j++){
//如果这个检测结果不属于当前类别或已经存在或低于阈值,都被忽略
if(ignored_det[j]==-1)
continue;
if(assigned_detection[j])
continue;
if(ignored_threshold[j])
continue;
//找到候选目标对应的score最大值并获取响应的检测结果编号
double overlap = boxoverlap(det[j], gt[i], -1);
//为计算recall阈值,需要考虑拥有最高score的候选
if(!compute_fp && overlap>MIN_OVERLAP[metric][current_class] && det[j].thresh>valid_detection){
det_idx = j;
valid_detection = det[j].thresh;
}
//为计算precision曲线值,需要考虑拥有最大重叠率的候选
//如果该候选是一个被忽略的检测(min_height),启用重叠率检测
else if(compute_fp && overlap>MIN_OVERLAP[metric][current_class] && (overlap>max_overlap || assigned_ignored_det) && ignored_det[j]==0){
max_overlap = overlap;
det_idx = j;
valid_detection = 1;
assigned_ignored_det = false;;
}
else if(compute_fp && overlap>MIN_OVERLAP[metric][current_class] && valid_detection==NO_DETECTION && ignored_det[j]==1){
det_idx = j;
valid_detection = 1;
assigned_ignored_det = true;
}
}
/*=======================================================================
compute TP, FP and FN compute TP, FP and FN
=======================================================================
//如果没有给当前有效的真值分配任何东西
if(valid_detection==NO_DETECTION && ignored_gt[i]==0) {
stat.fn++;
}
//只评估有效真值等同于 detection assignments (considering difficulty level)
else if(valid_detection!=NO_DETECTION && (ignored_gt[i]==1 || ignored_det[det_idx]==1))
assigned_detection[det_idx] = true;
//找到一个有效的true positive
else if(valid_detection!=NO_DETECTION){
//向阈值向量写入最高的
stat.tp++;
stat.v.push_back(det[det_idx].thresh);
//真值和检测结果之间的计算角度差异(如果提供了有效的角度检测)
if(compute_aos)
delta.push_back(gt[i].box.alpha - det[det_idx].box.alpha);
//清空
assigned_detection[det_idx] = true;
}
}
//如果需要计算FP are requested,则考虑stuff area
if(compute_fp){
//计数fp
for(int32_t i=0; i<det.size(); i++){
//如果需要,对所有的false positives计数(高度小于规定的被忽略(ignored_det==1))
if(!(assigned_detection[i] || ignored_det[i]==-1 || ignored_det[i]==1 || ignored_threshold[i]))
stat.fp++;
}
//不考虑与 stuff area重叠的检测结果
int32_t nstuff = 0;
for(int32_t i=0; i<dc.size(); i++){
for(int32_t j=0; j<det.size(); j++){
//忽略不属于当前类别的检测结果、已经处理过的检测结果、阈值或最小高度很低的检测结果
if(assigned_detection[j])
continue;
if(ignored_det[j]==-1 || ignored_det[j]==1)
continue;
if(ignored_threshold[j])
continue;
//计算重叠率,如果重叠率超过给定数值就分配给stuff area
double overlap = boxoverlap(det[j], dc[i], 0);
if(overlap>MIN_OVERLAP[metric][current_class]){
assigned_detection[j] = true;
nstuff++;
}
}
}
// FP = 所有未分配真值的点的个数(no. of all not to ground truth assigned detections) - 分配到stuff area的点的个数(detections assigned to stuff areas)
stat.fp -= nstuff;
//如果所有角度值有效则计算AOS
if(compute_aos){
vector<double> tmp;
// FP have a similarity of 0, for all TP compute AOS
tmp.assign(stat.fp, 0);
for(int32_t i=0; i<delta.size(); i++)
tmp.push_back((1.0+cos(delta[i]))/2.0);
// be sure, that all orientation deltas are computed
assert(tmp.size()==stat.fp+stat.tp);
assert(delta.size()==stat.tp);
// get the mean orientation similarity for this image
if(stat.tp>0 || stat.fp>0)
stat.similarity = accumulate(tmp.begin(), tmp.end(), 0.0);
// there was neither a FP nor a TP, so the similarity is ignored in the evaluation
else
stat.similarity = -1;
}
}
return stat;
}