Made some thresholds dynamic.
This commit is contained in:
Daniel
288
media/RESULTS.md
288
media/RESULTS.md
@ -294,91 +294,91 @@ Results of the model in various experiments on different datasets. \
|
||||
|
||||
```json
|
||||
{
|
||||
"img_loading": 0.042184,
|
||||
"demosaicing": 0.000678806,
|
||||
"avg_time_2d": 0.0147901,
|
||||
"avg_time_3d": 0.000119385,
|
||||
"fps": 64.1505
|
||||
"img_loading": 0.0422866,
|
||||
"demosaicing": 0.000699368,
|
||||
"avg_time_2d": 0.014883,
|
||||
"avg_time_3d": 0.00011746,
|
||||
"fps": 63.6951
|
||||
}
|
||||
{
|
||||
"triangulator_calls": 301,
|
||||
"init_time": 2.93031e-06,
|
||||
"undistort_time": 1.43119e-05,
|
||||
"project_time": 2.3093e-06,
|
||||
"match_time": 8.56559e-06,
|
||||
"pairs_time": 4.58829e-06,
|
||||
"pair_scoring_time": 2.63603e-05,
|
||||
"grouping_time": 4.53817e-06,
|
||||
"full_time": 2.74936e-05,
|
||||
"merge_time": 1.15484e-05,
|
||||
"post_time": 6.9437e-06,
|
||||
"convert_time": 1.26757e-07,
|
||||
"total_time": 0.000109953
|
||||
"init_time": 2.91101e-06,
|
||||
"undistort_time": 1.43844e-05,
|
||||
"project_time": 2.16363e-06,
|
||||
"match_time": 8.39535e-06,
|
||||
"pairs_time": 4.6119e-06,
|
||||
"pair_scoring_time": 2.70302e-05,
|
||||
"grouping_time": 4.49531e-06,
|
||||
"full_time": 2.73468e-05,
|
||||
"merge_time": 1.2003e-05,
|
||||
"post_time": 5.09957e-06,
|
||||
"convert_time": 1.25462e-07,
|
||||
"total_time": 0.000108806
|
||||
}
|
||||
{
|
||||
"person_nums": {
|
||||
"total_frames": 301,
|
||||
"total_labels": 477,
|
||||
"total_preds": 832,
|
||||
"total_preds": 827,
|
||||
"considered_empty": 0,
|
||||
"valid_preds": 477,
|
||||
"invalid_preds": 355,
|
||||
"invalid_preds": 350,
|
||||
"missing": 0,
|
||||
"invalid_fraction": 0.42668,
|
||||
"precision": 0.57332,
|
||||
"invalid_fraction": 0.42322,
|
||||
"precision": 0.57678,
|
||||
"recall": 1.0,
|
||||
"f1": 0.7288,
|
||||
"non_empty": 832
|
||||
"f1": 0.7316,
|
||||
"non_empty": 827
|
||||
},
|
||||
"mpjpe": {
|
||||
"count": 477,
|
||||
"mean": 0.047771,
|
||||
"median": 0.04252,
|
||||
"std": 0.014668,
|
||||
"sem": 0.000672,
|
||||
"min": 0.029325,
|
||||
"max": 0.105412,
|
||||
"mean": 0.047577,
|
||||
"median": 0.042522,
|
||||
"std": 0.014987,
|
||||
"sem": 0.000687,
|
||||
"min": 0.028778,
|
||||
"max": 0.118939,
|
||||
"recall-0.025": 0.0,
|
||||
"recall-0.05": 0.702306,
|
||||
"recall-0.05": 0.72327,
|
||||
"recall-0.1": 0.987421,
|
||||
"recall-0.15": 1.0,
|
||||
"recall-0.25": 1.0,
|
||||
"recall-0.5": 1.0,
|
||||
"num_labels": 477,
|
||||
"ap-0.025": 0.0,
|
||||
"ap-0.05": 0.429122,
|
||||
"ap-0.1": 0.750799,
|
||||
"ap-0.15": 0.760584,
|
||||
"ap-0.25": 0.760584,
|
||||
"ap-0.5": 0.760584
|
||||
"ap-0.05": 0.45527,
|
||||
"ap-0.1": 0.751931,
|
||||
"ap-0.15": 0.761005,
|
||||
"ap-0.25": 0.761005,
|
||||
"ap-0.5": 0.761005
|
||||
},
|
||||
"head": {
|
||||
"count": 477,
|
||||
"mean": 0.053874,
|
||||
"median": 0.04981,
|
||||
"std": 0.024502,
|
||||
"sem": 0.001123,
|
||||
"min": 0.005023,
|
||||
"max": 0.171118,
|
||||
"recall-0.025": 0.090147,
|
||||
"recall-0.05": 0.505241,
|
||||
"recall-0.1": 0.939203,
|
||||
"recall-0.15": 0.997904,
|
||||
"mean": 0.052991,
|
||||
"median": 0.048986,
|
||||
"std": 0.025142,
|
||||
"sem": 0.001152,
|
||||
"min": 0.006559,
|
||||
"max": 0.183673,
|
||||
"recall-0.025": 0.106918,
|
||||
"recall-0.05": 0.522013,
|
||||
"recall-0.1": 0.937107,
|
||||
"recall-0.15": 0.993711,
|
||||
"recall-0.25": 1.0,
|
||||
"recall-0.5": 1.0,
|
||||
"num_labels": 477
|
||||
},
|
||||
"shoulder_left": {
|
||||
"count": 477,
|
||||
"mean": 0.042207,
|
||||
"median": 0.036661,
|
||||
"std": 0.020587,
|
||||
"sem": 0.000944,
|
||||
"mean": 0.041956,
|
||||
"median": 0.037041,
|
||||
"std": 0.02074,
|
||||
"sem": 0.000951,
|
||||
"min": 0.004368,
|
||||
"max": 0.136632,
|
||||
"recall-0.025": 0.165618,
|
||||
"recall-0.05": 0.740042,
|
||||
"recall-0.1": 0.983229,
|
||||
"max": 0.132918,
|
||||
"recall-0.025": 0.174004,
|
||||
"recall-0.05": 0.754717,
|
||||
"recall-0.1": 0.985325,
|
||||
"recall-0.15": 1.0,
|
||||
"recall-0.25": 1.0,
|
||||
"recall-0.5": 1.0,
|
||||
@ -386,14 +386,14 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"shoulder_right": {
|
||||
"count": 477,
|
||||
"mean": 0.049707,
|
||||
"median": 0.046776,
|
||||
"std": 0.022703,
|
||||
"sem": 0.001041,
|
||||
"mean": 0.049604,
|
||||
"median": 0.046469,
|
||||
"std": 0.022881,
|
||||
"sem": 0.001049,
|
||||
"min": 0.005334,
|
||||
"max": 0.149673,
|
||||
"recall-0.025": 0.096436,
|
||||
"recall-0.05": 0.551363,
|
||||
"max": 0.148157,
|
||||
"recall-0.025": 0.100629,
|
||||
"recall-0.05": 0.561845,
|
||||
"recall-0.1": 0.955975,
|
||||
"recall-0.15": 1.0,
|
||||
"recall-0.25": 1.0,
|
||||
@ -402,15 +402,15 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"elbow_left": {
|
||||
"count": 477,
|
||||
"mean": 0.040814,
|
||||
"median": 0.032286,
|
||||
"std": 0.029281,
|
||||
"sem": 0.001342,
|
||||
"min": 0.003459,
|
||||
"mean": 0.040574,
|
||||
"median": 0.03197,
|
||||
"std": 0.028864,
|
||||
"sem": 0.001323,
|
||||
"min": 0.003618,
|
||||
"max": 0.309844,
|
||||
"recall-0.025": 0.318658,
|
||||
"recall-0.05": 0.748428,
|
||||
"recall-0.1": 0.951782,
|
||||
"recall-0.025": 0.312369,
|
||||
"recall-0.05": 0.754717,
|
||||
"recall-0.1": 0.953878,
|
||||
"recall-0.15": 0.997904,
|
||||
"recall-0.25": 0.997904,
|
||||
"recall-0.5": 1.0,
|
||||
@ -418,31 +418,31 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"elbow_right": {
|
||||
"count": 477,
|
||||
"mean": 0.053474,
|
||||
"median": 0.045174,
|
||||
"std": 0.040287,
|
||||
"sem": 0.001847,
|
||||
"min": 0.00327,
|
||||
"max": 0.244516,
|
||||
"recall-0.025": 0.253669,
|
||||
"recall-0.05": 0.553459,
|
||||
"recall-0.1": 0.903564,
|
||||
"recall-0.15": 0.960168,
|
||||
"mean": 0.053198,
|
||||
"median": 0.043315,
|
||||
"std": 0.040536,
|
||||
"sem": 0.001858,
|
||||
"min": 0.003567,
|
||||
"max": 0.242994,
|
||||
"recall-0.025": 0.27044,
|
||||
"recall-0.05": 0.563941,
|
||||
"recall-0.1": 0.897275,
|
||||
"recall-0.15": 0.962264,
|
||||
"recall-0.25": 1.0,
|
||||
"recall-0.5": 1.0,
|
||||
"num_labels": 477
|
||||
},
|
||||
"wrist_left": {
|
||||
"count": 477,
|
||||
"mean": 0.060043,
|
||||
"median": 0.054688,
|
||||
"std": 0.038061,
|
||||
"sem": 0.001745,
|
||||
"mean": 0.059301,
|
||||
"median": 0.054034,
|
||||
"std": 0.038637,
|
||||
"sem": 0.001771,
|
||||
"min": 0.00164,
|
||||
"max": 0.323995,
|
||||
"recall-0.025": 0.134172,
|
||||
"recall-0.05": 0.396226,
|
||||
"recall-0.1": 0.907757,
|
||||
"max": 0.32449,
|
||||
"recall-0.025": 0.146751,
|
||||
"recall-0.05": 0.412998,
|
||||
"recall-0.1": 0.909853,
|
||||
"recall-0.15": 0.964361,
|
||||
"recall-0.25": 0.991614,
|
||||
"recall-0.5": 1.0,
|
||||
@ -450,47 +450,47 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"wrist_right": {
|
||||
"count": 477,
|
||||
"mean": 0.058016,
|
||||
"median": 0.054634,
|
||||
"std": 0.030706,
|
||||
"sem": 0.001407,
|
||||
"mean": 0.058286,
|
||||
"median": 0.053472,
|
||||
"std": 0.034178,
|
||||
"sem": 0.001567,
|
||||
"min": 0.008622,
|
||||
"max": 0.238817,
|
||||
"recall-0.025": 0.111111,
|
||||
"recall-0.05": 0.421384,
|
||||
"recall-0.1": 0.903564,
|
||||
"recall-0.15": 0.985325,
|
||||
"recall-0.25": 1.0,
|
||||
"max": 0.382984,
|
||||
"recall-0.025": 0.113208,
|
||||
"recall-0.05": 0.440252,
|
||||
"recall-0.1": 0.90566,
|
||||
"recall-0.15": 0.981132,
|
||||
"recall-0.25": 0.997904,
|
||||
"recall-0.5": 1.0,
|
||||
"num_labels": 477
|
||||
},
|
||||
"hip_left": {
|
||||
"count": 477,
|
||||
"mean": 0.048043,
|
||||
"mean": 0.047666,
|
||||
"median": 0.042435,
|
||||
"std": 0.025895,
|
||||
"sem": 0.001187,
|
||||
"min": 0.006314,
|
||||
"max": 0.173228,
|
||||
"recall-0.025": 0.159329,
|
||||
"recall-0.05": 0.624738,
|
||||
"recall-0.1": 0.955975,
|
||||
"recall-0.15": 0.997904,
|
||||
"std": 0.025966,
|
||||
"sem": 0.00119,
|
||||
"min": 0.008125,
|
||||
"max": 0.145941,
|
||||
"recall-0.025": 0.188679,
|
||||
"recall-0.05": 0.628931,
|
||||
"recall-0.1": 0.958071,
|
||||
"recall-0.15": 1.0,
|
||||
"recall-0.25": 1.0,
|
||||
"recall-0.5": 1.0,
|
||||
"num_labels": 477
|
||||
},
|
||||
"hip_right": {
|
||||
"count": 477,
|
||||
"mean": 0.057878,
|
||||
"median": 0.056579,
|
||||
"std": 0.023899,
|
||||
"mean": 0.057617,
|
||||
"median": 0.058504,
|
||||
"std": 0.023884,
|
||||
"sem": 0.001095,
|
||||
"min": 0.006301,
|
||||
"max": 0.132422,
|
||||
"recall-0.025": 0.098532,
|
||||
"recall-0.05": 0.352201,
|
||||
"recall-0.1": 0.9413,
|
||||
"recall-0.025": 0.102725,
|
||||
"recall-0.05": 0.354298,
|
||||
"recall-0.1": 0.943396,
|
||||
"recall-0.15": 1.0,
|
||||
"recall-0.25": 1.0,
|
||||
"recall-0.5": 1.0,
|
||||
@ -498,15 +498,15 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"knee_left": {
|
||||
"count": 477,
|
||||
"mean": 0.040068,
|
||||
"median": 0.036879,
|
||||
"std": 0.02442,
|
||||
"sem": 0.001119,
|
||||
"min": 0.005242,
|
||||
"mean": 0.040292,
|
||||
"median": 0.037394,
|
||||
"std": 0.024591,
|
||||
"sem": 0.001127,
|
||||
"min": 0.00468,
|
||||
"max": 0.190112,
|
||||
"recall-0.025": 0.257862,
|
||||
"recall-0.05": 0.754717,
|
||||
"recall-0.1": 0.974843,
|
||||
"recall-0.025": 0.264151,
|
||||
"recall-0.05": 0.752621,
|
||||
"recall-0.1": 0.972746,
|
||||
"recall-0.15": 0.989518,
|
||||
"recall-0.25": 1.0,
|
||||
"recall-0.5": 1.0,
|
||||
@ -514,14 +514,14 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"knee_right": {
|
||||
"count": 477,
|
||||
"mean": 0.039748,
|
||||
"median": 0.035762,
|
||||
"std": 0.023,
|
||||
"sem": 0.001054,
|
||||
"min": 0.007276,
|
||||
"mean": 0.039685,
|
||||
"median": 0.035562,
|
||||
"std": 0.023057,
|
||||
"sem": 0.001057,
|
||||
"min": 0.005833,
|
||||
"max": 0.184978,
|
||||
"recall-0.025": 0.316562,
|
||||
"recall-0.05": 0.72956,
|
||||
"recall-0.025": 0.318658,
|
||||
"recall-0.05": 0.735849,
|
||||
"recall-0.1": 0.974843,
|
||||
"recall-0.15": 0.997904,
|
||||
"recall-0.25": 1.0,
|
||||
@ -530,13 +530,13 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"ankle_left": {
|
||||
"count": 477,
|
||||
"mean": 0.036387,
|
||||
"median": 0.028113,
|
||||
"std": 0.030604,
|
||||
"sem": 0.001403,
|
||||
"mean": 0.036424,
|
||||
"median": 0.027617,
|
||||
"std": 0.030554,
|
||||
"sem": 0.0014,
|
||||
"min": 0.004893,
|
||||
"max": 0.223793,
|
||||
"recall-0.025": 0.429769,
|
||||
"recall-0.025": 0.42348,
|
||||
"recall-0.05": 0.819706,
|
||||
"recall-0.1": 0.947589,
|
||||
"recall-0.15": 0.983229,
|
||||
@ -546,14 +546,14 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"ankle_right": {
|
||||
"count": 477,
|
||||
"mean": 0.040761,
|
||||
"median": 0.030879,
|
||||
"std": 0.037437,
|
||||
"sem": 0.001716,
|
||||
"min": 0.003316,
|
||||
"mean": 0.040909,
|
||||
"median": 0.030845,
|
||||
"std": 0.037585,
|
||||
"sem": 0.001723,
|
||||
"min": 0.003445,
|
||||
"max": 0.28852,
|
||||
"recall-0.025": 0.301887,
|
||||
"recall-0.05": 0.809224,
|
||||
"recall-0.05": 0.807128,
|
||||
"recall-0.1": 0.930818,
|
||||
"recall-0.15": 0.968553,
|
||||
"recall-0.25": 0.997904,
|
||||
@ -562,18 +562,18 @@ Results of the model in various experiments on different datasets. \
|
||||
},
|
||||
"joint_recalls": {
|
||||
"num_labels": 6201,
|
||||
"recall-0.025": 0.20916,
|
||||
"recall-0.05": 0.6149,
|
||||
"recall-0.1": 0.94356,
|
||||
"recall-0.15": 0.98774,
|
||||
"recall-0.25": 0.99887,
|
||||
"recall-0.025": 0.21609,
|
||||
"recall-0.05": 0.62329,
|
||||
"recall-0.1": 0.94291,
|
||||
"recall-0.15": 0.9871,
|
||||
"recall-0.25": 0.99871,
|
||||
"recall-0.5": 1.0
|
||||
}
|
||||
}
|
||||
{
|
||||
"total_parts": 6678,
|
||||
"correct_parts": 6621,
|
||||
"pcp": 0.991465
|
||||
"correct_parts": 6623,
|
||||
"pcp": 0.991764
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
@ -525,6 +525,7 @@ std::vector<std::vector<std::array<float, 4>>> TriangulatorInternal::triangulate
|
||||
}
|
||||
|
||||
// Convert inputs to internal formats
|
||||
this->num_cams = cameras.size();
|
||||
std::vector<std::vector<std::vector<std::array<float, 3>>>> i_poses_2d = poses_2d;
|
||||
std::vector<CameraInternal> internal_cameras;
|
||||
for (size_t i = 0; i < cameras.size(); ++i)
|
||||
@ -1809,6 +1810,7 @@ std::vector<std::array<float, 4>> TriangulatorInternal::merge_group(
|
||||
// Use only those triangulations with a high score
|
||||
std::vector<std::array<float, 4>> sum_poses(num_joints, {0.0, 0.0, 0.0, 0.0});
|
||||
std::vector<float> sum_mask1(num_joints, 0);
|
||||
float offset1 = (1.0 - min_score) / 2.0;
|
||||
for (size_t i = 0; i < num_poses; ++i)
|
||||
{
|
||||
const auto &pose = poses_3d[i];
|
||||
@ -1816,7 +1818,7 @@ std::vector<std::array<float, 4>> TriangulatorInternal::merge_group(
|
||||
for (size_t j = 0; j < num_joints; ++j)
|
||||
{
|
||||
float score = pose[j][3];
|
||||
if (score > min_score)
|
||||
if (score > min_score - offset1)
|
||||
{
|
||||
float weight = std::pow(score, 2);
|
||||
sum_poses[j][0] += pose[j][0] * weight;
|
||||
@ -1847,7 +1849,7 @@ std::vector<std::array<float, 4>> TriangulatorInternal::merge_group(
|
||||
for (size_t j = 0; j < num_joints; ++j)
|
||||
{
|
||||
float score = initial_pose_3d[j][3];
|
||||
if (score > min_score)
|
||||
if (score > min_score - offset1)
|
||||
{
|
||||
jmask[j] = true;
|
||||
center[0] += initial_pose_3d[j][0];
|
||||
@ -1875,7 +1877,7 @@ std::vector<std::array<float, 4>> TriangulatorInternal::merge_group(
|
||||
}
|
||||
|
||||
// Drop joints with low scores and filter outlying joints using distance threshold
|
||||
float offset = 0.1;
|
||||
float offset2 = (1.0 - min_score) * 2.0;
|
||||
float max_dist_sq = 1.2 * 1.2;
|
||||
std::vector<std::vector<bool>> mask(num_poses, std::vector<bool>(num_joints, false));
|
||||
std::vector<std::vector<float>> distances(num_poses, std::vector<float>(num_joints, 0.0));
|
||||
@ -1891,7 +1893,7 @@ std::vector<std::array<float, 4>> TriangulatorInternal::merge_group(
|
||||
distances[i][j] = dist_sq;
|
||||
|
||||
float score = pose[j][3];
|
||||
if (dist_sq <= max_dist_sq && score > (min_score - offset))
|
||||
if (dist_sq <= max_dist_sq && score > (min_score - offset2))
|
||||
{
|
||||
mask[i][j] = true;
|
||||
}
|
||||
@ -1899,7 +1901,7 @@ std::vector<std::array<float, 4>> TriangulatorInternal::merge_group(
|
||||
}
|
||||
|
||||
// Select the best-k proposals for each joint that are closest to the initial pose
|
||||
int keep_best = std::max(3, (int)num_poses / 3);
|
||||
int keep_best = std::max((int)std::ceil(this->num_cams / 2.0), (int)std::ceil(num_poses / 3.0));
|
||||
std::vector<std::vector<bool>> best_k_mask(num_poses, std::vector<bool>(num_joints, false));
|
||||
for (size_t j = 0; j < num_joints; ++j)
|
||||
{
|
||||
|
||||
@ -54,6 +54,7 @@ public:
|
||||
private:
|
||||
float min_match_score;
|
||||
float min_group_size;
|
||||
size_t num_cams;
|
||||
|
||||
const std::vector<std::string> core_joints = {
|
||||
"shoulder_left",
|
||||
|
||||
Reference in New Issue
Block a user