crosstyan/RapidPoseTriangulation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added flag for minimal group size.

Browse Source
This commit is contained in:
Daniel
2024-09-26 11:55:43 +02:00
parent f62d90f753
commit d2efb66767
6 changed files with 191 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

312
media/RESULTS.md
View File

@ -286,16 +286,16 @@ Results of the model in various experiments on different datasets.
"person_nums": { "person_nums": {
"total_frames": 301, "total_frames": 301,
"total_labels": 477, "total_labels": 477,
"total_preds": 888, "total_preds": 814,
"considered_empty": 0, "considered_empty": 0,
"valid_preds": 477, "valid_preds": 477,
"invalid_preds": 411, "invalid_preds": 337,
"missing": 0, "missing": 0,
"invalid_fraction": 0.46284, "invalid_fraction": 0.414,
"precision": 0.53716, "precision": 0.586,
"recall": 1.0, "recall": 1.0,
"f1": 0.6989, "f1": 0.73896,
"non_empty": 888 "non_empty": 814
}, },
"mpjpe": { "mpjpe": {
"count": 477, "count": 477,
@ -313,11 +313,11 @@ Results of the model in various experiments on different datasets.
"recall-0.5": 1.0, "recall-0.5": 1.0,
"num_labels": 477, "num_labels": 477,
"ap-0.025": 0.0, "ap-0.025": 0.0,
"ap-0.05": 0.340331, "ap-0.05": 0.345013,
"ap-0.1": 0.693196, "ap-0.1": 0.702867,
"ap-0.15": 0.704408, "ap-0.15": 0.714372,
"ap-0.25": 0.704408, "ap-0.25": 0.714372,
"ap-0.5": 0.704408 "ap-0.5": 0.714372
}, },
"head": { "head": {
"count": 477, "count": 477,
@ -1569,56 +1569,56 @@ Results of the model in various experiments on different datasets.
(10 cameras) (10 cameras)
```json ```json
{ {
"avg_time_2d": 0.20488240776992425, "avg_time_2d": 0.20779247690991656,
"avg_time_3d": 0.0016675780459148128, "avg_time_3d": 0.0016487220438515268,
"avg_fps": 4.841443082410108 "avg_fps": 4.774609794994247
} }
{ {
"person_nums": { "person_nums": {
"total_frames": 420, "total_frames": 420,
"total_labels": 1466, "total_labels": 1466,
"total_preds": 1735, "total_preds": 1527,
"considered_empty": 0, "considered_empty": 0,
"valid_preds": 1465, "valid_preds": 1465,
"invalid_preds": 270, "invalid_preds": 62,
"missing": 1, "missing": 1,
"invalid_fraction": 0.15562, "invalid_fraction": 0.0406,
"precision": 0.84438, "precision": 0.9594,
"recall": 0.99932, "recall": 0.99932,
"f1": 0.91534, "f1": 0.97895,
"non_empty": 1735 "non_empty": 1527
}, },
"mpjpe": { "mpjpe": {
"count": 1465, "count": 1465,
"mean": 0.037085, "mean": 0.037082,
"median": 0.032344, "median": 0.032321,
"std": 0.017223, "std": 0.017242,
"sem": 0.00045, "sem": 0.000451,
"min": 0.013848, "min": 0.013848,
"max": 0.136363, "max": 0.136363,
"recall-0.025": 0.186903, "recall-0.025": 0.188267,
"recall-0.05": 0.85266, "recall-0.05": 0.851978,
"recall-0.1": 0.989086, "recall-0.1": 0.989086,
"recall-0.15": 0.999318, "recall-0.15": 0.999318,
"recall-0.25": 0.999318, "recall-0.25": 0.999318,
"recall-0.5": 0.999318, "recall-0.5": 0.999318,
"num_labels": 1466, "num_labels": 1466,
"ap-0.025": 0.085997, "ap-0.025": 0.087846,
"ap-0.05": 0.802543, "ap-0.05": 0.807698,
"ap-0.1": 0.967268, "ap-0.1": 0.975275,
"ap-0.15": 0.978621, "ap-0.15": 0.986743,
"ap-0.25": 0.978621, "ap-0.25": 0.986743,
"ap-0.5": 0.978621 "ap-0.5": 0.986743
}, },
"nose": { "nose": {
"count": 1462, "count": 1462,
"mean": 0.012376, "mean": 0.012384,
"median": 0.010938, "median": 0.010912,
"std": 0.007779, "std": 0.007797,
"sem": 0.000204, "sem": 0.000204,
"min": 0.001275, "min": 0.001275,
"max": 0.124831, "max": 0.124831,
"recall-0.025": 0.957621, "recall-0.025": 0.956254,
"recall-0.05": 0.993165, "recall-0.05": 0.993165,
"recall-0.1": 0.998633, "recall-0.1": 0.998633,
"recall-0.15": 0.999316, "recall-0.15": 0.999316,
@ -1628,13 +1628,13 @@ Results of the model in various experiments on different datasets.
}, },
"shoulder_left": { "shoulder_left": {
"count": 1465, "count": 1465,
"mean": 0.018742, "mean": 0.018746,
"median": 0.016661, "median": 0.016641,
"std": 0.00976, "std": 0.009717,
"sem": 0.000255, "sem": 0.000254,
"min": 0.001103, "min": 0.001103,
"max": 0.11138, "max": 0.11138,
"recall-0.025": 0.800136, "recall-0.025": 0.798772,
"recall-0.05": 0.991132, "recall-0.05": 0.991132,
"recall-0.1": 0.998636, "recall-0.1": 0.998636,
"recall-0.15": 0.999318, "recall-0.15": 0.999318,
@ -1644,13 +1644,13 @@ Results of the model in various experiments on different datasets.
}, },
"shoulder_right": { "shoulder_right": {
"count": 1464, "count": 1464,
"mean": 0.02051, "mean": 0.020464,
"median": 0.019186, "median": 0.019186,
"std": 0.008943, "std": 0.008812,
"sem": 0.000234, "sem": 0.00023,
"min": 0.002013, "min": 0.002013,
"max": 0.093441, "max": 0.087963,
"recall-0.025": 0.768601, "recall-0.025": 0.769966,
"recall-0.05": 0.990444, "recall-0.05": 0.990444,
"recall-0.1": 0.999317, "recall-0.1": 0.999317,
"recall-0.15": 0.999317, "recall-0.15": 0.999317,
@ -1660,15 +1660,15 @@ Results of the model in various experiments on different datasets.
}, },
"elbow_left": { "elbow_left": {
"count": 1464, "count": 1464,
"mean": 0.020864, "mean": 0.021041,
"median": 0.018441, "median": 0.018392,
"std": 0.011938, "std": 0.012619,
"sem": 0.000312, "sem": 0.00033,
"min": 0.002104, "min": 0.002104,
"max": 0.095363, "max": 0.147682,
"recall-0.025": 0.711945, "recall-0.025": 0.709215,
"recall-0.05": 0.974744, "recall-0.05": 0.972696,
"recall-0.1": 0.999317, "recall-0.1": 0.998635,
"recall-0.15": 0.999317, "recall-0.15": 0.999317,
"recall-0.25": 0.999317, "recall-0.25": 0.999317,
"recall-0.5": 0.999317, "recall-0.5": 0.999317,
@ -1676,14 +1676,14 @@ Results of the model in various experiments on different datasets.
}, },
"elbow_right": { "elbow_right": {
"count": 1462, "count": 1462,
"mean": 0.019564, "mean": 0.019468,
"median": 0.017384, "median": 0.017347,
"std": 0.011529, "std": 0.011368,
"sem": 0.000302, "sem": 0.000297,
"min": 0.001927, "min": 0.001927,
"max": 0.132247, "max": 0.132247,
"recall-0.025": 0.802461, "recall-0.025": 0.805878,
"recall-0.05": 0.970608, "recall-0.05": 0.971975,
"recall-0.1": 0.997949, "recall-0.1": 0.997949,
"recall-0.15": 0.999316, "recall-0.15": 0.999316,
"recall-0.25": 0.999316, "recall-0.25": 0.999316,
@ -1692,13 +1692,13 @@ Results of the model in various experiments on different datasets.
}, },
"wrist_left": { "wrist_left": {
"count": 1433, "count": 1433,
"mean": 0.020859, "mean": 0.020901,
"median": 0.015088, "median": 0.015088,
"std": 0.021069, "std": 0.021121,
"sem": 0.000557, "sem": 0.000558,
"min": 0.001506, "min": 0.001506,
"max": 0.194344, "max": 0.194344,
"recall-0.025": 0.767085, "recall-0.025": 0.763598,
"recall-0.05": 0.937936, "recall-0.05": 0.937936,
"recall-0.1": 0.982566, "recall-0.1": 0.982566,
"recall-0.15": 0.994421, "recall-0.15": 0.994421,
@ -1708,14 +1708,14 @@ Results of the model in various experiments on different datasets.
}, },
"wrist_right": { "wrist_right": {
"count": 1456, "count": 1456,
"mean": 0.020392, "mean": 0.020303,
"median": 0.0137, "median": 0.013717,
"std": 0.020859, "std": 0.020686,
"sem": 0.000547, "sem": 0.000542,
"min": 0.000284, "min": 0.000284,
"max": 0.212342, "max": 0.212342,
"recall-0.025": 0.770604, "recall-0.025": 0.773352,
"recall-0.05": 0.933379, "recall-0.05": 0.934753,
"recall-0.1": 0.984203, "recall-0.1": 0.984203,
"recall-0.15": 0.997253, "recall-0.15": 0.997253,
"recall-0.25": 1.0, "recall-0.25": 1.0,
@ -1724,15 +1724,15 @@ Results of the model in various experiments on different datasets.
}, },
"hip_left": { "hip_left": {
"count": 1464, "count": 1464,
"mean": 0.050256, "mean": 0.050265,
"median": 0.048397, "median": 0.048338,
"std": 0.01907, "std": 0.019008,
"sem": 0.000499, "sem": 0.000497,
"min": 0.008094, "min": 0.008094,
"max": 0.148516, "max": 0.148516,
"recall-0.025": 0.049829, "recall-0.025": 0.049147,
"recall-0.05": 0.546075, "recall-0.05": 0.54744,
"recall-0.1": 0.975427, "recall-0.1": 0.976109,
"recall-0.15": 0.999317, "recall-0.15": 0.999317,
"recall-0.25": 0.999317, "recall-0.25": 0.999317,
"recall-0.5": 0.999317, "recall-0.5": 0.999317,
@ -1740,14 +1740,14 @@ Results of the model in various experiments on different datasets.
}, },
"hip_right": { "hip_right": {
"count": 1465, "count": 1465,
"mean": 0.050045, "mean": 0.050041,
"median": 0.048856, "median": 0.048863,
"std": 0.016859, "std": 0.016842,
"sem": 0.000441, "sem": 0.00044,
"min": 0.007258, "min": 0.007258,
"max": 0.138747, "max": 0.138747,
"recall-0.025": 0.051842, "recall-0.025": 0.05116,
"recall-0.05": 0.521146, "recall-0.05": 0.520464,
"recall-0.1": 0.988404, "recall-0.1": 0.988404,
"recall-0.15": 0.999318, "recall-0.15": 0.999318,
"recall-0.25": 0.999318, "recall-0.25": 0.999318,
@ -1756,13 +1756,13 @@ Results of the model in various experiments on different datasets.
}, },
"knee_left": { "knee_left": {
"count": 1464, "count": 1464,
"mean": 0.038364, "mean": 0.038353,
"median": 0.032286, "median": 0.032352,
"std": 0.027217, "std": 0.027187,
"sem": 0.000712, "sem": 0.000711,
"min": 0.002051, "min": 0.002051,
"max": 0.275419, "max": 0.275419,
"recall-0.025": 0.333106, "recall-0.025": 0.331058,
"recall-0.05": 0.759727, "recall-0.05": 0.759727,
"recall-0.1": 0.970648, "recall-0.1": 0.970648,
"recall-0.15": 0.990444, "recall-0.15": 0.990444,
@ -1772,59 +1772,59 @@ Results of the model in various experiments on different datasets.
}, },
"knee_right": { "knee_right": {
"count": 1458, "count": 1458,
"mean": 0.041819, "mean": 0.041659,
"median": 0.035897, "median": 0.035863,
"std": 0.026627, "std": 0.026298,
"sem": 0.000698, "sem": 0.000689,
"min": 0.004598, "min": 0.004598,
"max": 0.242773, "max": 0.242773,
"recall-0.025": 0.242632, "recall-0.025": 0.243317,
"recall-0.05": 0.731323, "recall-0.05": 0.732008,
"recall-0.1": 0.963674, "recall-0.1": 0.964359,
"recall-0.15": 0.989034, "recall-0.15": 0.990404,
"recall-0.25": 0.999315, "recall-0.25": 0.999315,
"recall-0.5": 0.999315, "recall-0.5": 0.999315,
"num_labels": 1459 "num_labels": 1459
}, },
"ankle_left": { "ankle_left": {
"count": 1457, "count": 1457,
"mean": 0.085272, "mean": 0.085318,
"median": 0.043075, "median": 0.04279,
"std": 0.101395, "std": 0.101384,
"sem": 0.002657, "sem": 0.002657,
"min": 0.000814, "min": 0.000814,
"max": 0.494931, "max": 0.494931,
"recall-0.025": 0.346548, "recall-0.025": 0.347915,
"recall-0.05": 0.545455, "recall-0.05": 0.546138,
"recall-0.1": 0.712919, "recall-0.1": 0.712235,
"recall-0.15": 0.828435, "recall-0.15": 0.827751,
"recall-0.25": 0.917293, "recall-0.25": 0.917293,
"recall-0.5": 0.995899, "recall-0.5": 0.995899,
"num_labels": 1463 "num_labels": 1463
}, },
"ankle_right": { "ankle_right": {
"count": 1447, "count": 1447,
"mean": 0.077062, "mean": 0.077143,
"median": 0.042773, "median": 0.042829,
"std": 0.096671, "std": 0.096759,
"sem": 0.002542, "sem": 0.002545,
"min": 0.001957, "min": 0.001957,
"max": 0.49866, "max": 0.49866,
"recall-0.025": 0.315753, "recall-0.025": 0.315068,
"recall-0.05": 0.560274, "recall-0.05": 0.560274,
"recall-0.1": 0.793151, "recall-0.1": 0.791781,
"recall-0.15": 0.850685, "recall-0.15": 0.85137,
"recall-0.25": 0.908219, "recall-0.25": 0.908904,
"recall-0.5": 0.991096, "recall-0.5": 0.991096,
"num_labels": 1460 "num_labels": 1460
}, },
"joint_recalls": { "joint_recalls": {
"num_labels": 18990, "num_labels": 18990,
"recall-0.025": 0.53133, "recall-0.025": 0.53102,
"recall-0.05": 0.80379, "recall-0.05": 0.80395,
"recall-0.1": 0.95082, "recall-0.1": 0.95061,
"recall-0.15": 0.97241, "recall-0.15": 0.97241,
"recall-0.25": 0.98562, "recall-0.25": 0.98568,
"recall-0.5": 0.99816 "recall-0.5": 0.99816
} }
} }
@ -2119,23 +2119,23 @@ Results of the model in various experiments on different datasets.
"person_nums": { "person_nums": {
"total_frames": 210, "total_frames": 210,
"total_labels": 630, "total_labels": 630,
"total_preds": 632, "total_preds": 631,
"considered_empty": 0, "considered_empty": 0,
"valid_preds": 630, "valid_preds": 630,
"invalid_preds": 2, "invalid_preds": 1,
"missing": 0, "missing": 0,
"invalid_fraction": 0.00316, "invalid_fraction": 0.00158,
"precision": 0.99684, "precision": 0.99842,
"recall": 1.0, "recall": 1.0,
"f1": 0.99842, "f1": 0.99921,
"non_empty": 632 "non_empty": 631
}, },
"mpjpe": { "mpjpe": {
"count": 630, "count": 630,
"mean": 0.056116, "mean": 0.056111,
"median": 0.051456, "median": 0.051456,
"std": 0.018382, "std": 0.018368,
"sem": 0.000733, "sem": 0.000732,
"min": 0.028965, "min": 0.028965,
"max": 0.14306, "max": 0.14306,
"recall-0.025": 0.0, "recall-0.025": 0.0,
@ -2146,18 +2146,18 @@ Results of the model in various experiments on different datasets.
"recall-0.5": 1.0, "recall-0.5": 1.0,
"num_labels": 630, "num_labels": 630,
"ap-0.025": 0.0, "ap-0.025": 0.0,
"ap-0.05": 0.223916, "ap-0.05": 0.223683,
"ap-0.1": 0.928562, "ap-0.1": 0.928267,
"ap-0.15": 0.999816, "ap-0.15": 0.999816,
"ap-0.25": 0.999816, "ap-0.25": 0.999816,
"ap-0.5": 0.999816 "ap-0.5": 0.999816
}, },
"head": { "head": {
"count": 598, "count": 598,
"mean": 0.040794, "mean": 0.040764,
"median": 0.039496, "median": 0.039496,
"std": 0.01381, "std": 0.01374,
"sem": 0.000565, "sem": 0.000562,
"min": 0.011364, "min": 0.011364,
"max": 0.102955, "max": 0.102955,
"recall-0.025": 0.125418, "recall-0.025": 0.125418,
@ -2170,15 +2170,15 @@ Results of the model in various experiments on different datasets.
}, },
"shoulder_left": { "shoulder_left": {
"count": 630, "count": 630,
"mean": 0.062854, "mean": 0.062839,
"median": 0.060457, "median": 0.060457,
"std": 0.01943, "std": 0.019404,
"sem": 0.000775, "sem": 0.000774,
"min": 0.018922, "min": 0.018922,
"max": 0.132634, "max": 0.132634,
"recall-0.025": 0.003175, "recall-0.025": 0.003175,
"recall-0.05": 0.273016, "recall-0.05": 0.273016,
"recall-0.1": 0.974603, "recall-0.1": 0.97619,
"recall-0.15": 1.0, "recall-0.15": 1.0,
"recall-0.25": 1.0, "recall-0.25": 1.0,
"recall-0.5": 1.0, "recall-0.5": 1.0,
@ -2202,10 +2202,10 @@ Results of the model in various experiments on different datasets.
}, },
"elbow_left": { "elbow_left": {
"count": 630, "count": 630,
"mean": 0.052412, "mean": 0.05237,
"median": 0.049508, "median": 0.049508,
"std": 0.020244, "std": 0.020206,
"sem": 0.000807, "sem": 0.000806,
"min": 0.010131, "min": 0.010131,
"max": 0.140634, "max": 0.140634,
"recall-0.025": 0.05873, "recall-0.025": 0.05873,
@ -2234,10 +2234,10 @@ Results of the model in various experiments on different datasets.
}, },
"wrist_left": { "wrist_left": {
"count": 630, "count": 630,
"mean": 0.048082, "mean": 0.048071,
"median": 0.041989, "median": 0.041989,
"std": 0.026744, "std": 0.026751,
"sem": 0.001066, "sem": 0.001067,
"min": 0.007895, "min": 0.007895,
"max": 0.191578, "max": 0.191578,
"recall-0.025": 0.134921, "recall-0.025": 0.134921,
@ -2250,7 +2250,7 @@ Results of the model in various experiments on different datasets.
}, },
"wrist_right": { "wrist_right": {
"count": 625, "count": 625,
"mean": 0.05271, "mean": 0.052705,
"median": 0.047416, "median": 0.047416,
"std": 0.025887, "std": 0.025887,
"sem": 0.001036, "sem": 0.001036,
@ -2266,10 +2266,10 @@ Results of the model in various experiments on different datasets.
}, },
"hip_left": { "hip_left": {
"count": 630, "count": 630,
"mean": 0.057316, "mean": 0.057311,
"median": 0.054171, "median": 0.054171,
"std": 0.020591, "std": 0.020577,
"sem": 0.000821, "sem": 0.00082,
"min": 0.014001, "min": 0.014001,
"max": 0.17071, "max": 0.17071,
"recall-0.025": 0.025397, "recall-0.025": 0.025397,
@ -2282,9 +2282,9 @@ Results of the model in various experiments on different datasets.
}, },
"hip_right": { "hip_right": {
"count": 629, "count": 629,
"mean": 0.055242, "mean": 0.055245,
"median": 0.050996, "median": 0.050996,
"std": 0.02309, "std": 0.023089,
"sem": 0.000921, "sem": 0.000921,
"min": 0.004999, "min": 0.004999,
"max": 0.145424, "max": 0.145424,
@ -2298,9 +2298,9 @@ Results of the model in various experiments on different datasets.
}, },
"knee_left": { "knee_left": {
"count": 628, "count": 628,
"mean": 0.045694, "mean": 0.045693,
"median": 0.034743, "median": 0.034743,
"std": 0.04608, "std": 0.046075,
"sem": 0.00184, "sem": 0.00184,
"min": 0.003593, "min": 0.003593,
"max": 0.364064, "max": 0.364064,
@ -2314,14 +2314,14 @@ Results of the model in various experiments on different datasets.
}, },
"knee_right": { "knee_right": {
"count": 629, "count": 629,
"mean": 0.053707, "mean": 0.053711,
"median": 0.036065, "median": 0.036065,
"std": 0.072302, "std": 0.072301,
"sem": 0.002885, "sem": 0.002885,
"min": 0.002669, "min": 0.002669,
"max": 0.496679, "max": 0.496679,
"recall-0.025": 0.252782, "recall-0.025": 0.252782,
"recall-0.05": 0.73132, "recall-0.05": 0.72973,
"recall-0.1": 0.934817, "recall-0.1": 0.934817,
"recall-0.15": 0.952305, "recall-0.15": 0.952305,
"recall-0.25": 0.958665, "recall-0.25": 0.958665,
@ -2330,10 +2330,10 @@ Results of the model in various experiments on different datasets.
}, },
"ankle_left": { "ankle_left": {
"count": 619, "count": 619,
"mean": 0.065828, "mean": 0.065864,
"median": 0.050491, "median": 0.050491,
"std": 0.072587, "std": 0.072779,
"sem": 0.00292, "sem": 0.002928,
"min": 0.012793, "min": 0.012793,
"max": 0.493666, "max": 0.493666,
"recall-0.025": 0.035541, "recall-0.025": 0.035541,
@ -2346,7 +2346,7 @@ Results of the model in various experiments on different datasets.
}, },
"ankle_right": { "ankle_right": {
"count": 601, "count": 601,
"mean": 0.054042, "mean": 0.054043,
"median": 0.047411, "median": 0.047411,
"std": 0.042559, "std": 0.042559,
"sem": 0.001737, "sem": 0.001737,
@ -2363,8 +2363,8 @@ Results of the model in various experiments on different datasets.
"joint_recalls": { "joint_recalls": {
"num_labels": 8129, "num_labels": 8129,
"recall-0.025": 0.09583, "recall-0.025": 0.09583,
"recall-0.05": 0.52749, "recall-0.05": 0.52737,
"recall-0.1": 0.95079, "recall-0.1": 0.95092,
"recall-0.15": 0.98155, "recall-0.15": 0.98155,
"recall-0.25": 0.98905, "recall-0.25": 0.98905,
"recall-0.5": 0.99742 "recall-0.5": 0.99742

11
scripts/test_skelda_dataset.py
View File

@ -333,13 +333,22 @@ def main():
"koarob": 0.91, "koarob": 0.91,
} }
minscore = minscores.get(dataset_use, 0.95) minscore = minscores.get(dataset_use, 0.95)
min_group_sizes = {
# If the number of cameras is high, and the views are not occluded, use a higher value
"panoptic": 1,
"shelf": 2,
"tsinghua": 2,
}
min_group_size = min_group_sizes.get(dataset_use, 1)
if dataset_use == "panoptic" and len(datasets["panoptic"]["cams"]) == 10:
min_group_size = 5
print("\nRunning predictions ...") print("\nRunning predictions ...")
all_poses = [] all_poses = []
all_ids = [] all_ids = []
all_paths = [] all_paths = []
times = [] times = []
triangulator = spt.Triangulator(min_score=minscore) triangulator = spt.Triangulator(min_score=minscore, min_group_size=min_group_size)
old_scene = "" old_scene = ""
for label in tqdm.tqdm(labels): for label in tqdm.tqdm(labels):
images_2d = [] images_2d = []

4
spt/interface.cpp
View File

@ -4,9 +4,9 @@
// ================================================================================================= // =================================================================================================
// ================================================================================================= // =================================================================================================
Triangulator::Triangulator(float min_score) Triangulator::Triangulator(float min_score, size_t min_group_size)
{ {
this->triangulator = new TriangulatorInternal(min_score); this->triangulator = new TriangulatorInternal(min_score, min_group_size);
} }
// ================================================================================================= // =================================================================================================

4
spt/interface.hpp
View File

@ -20,9 +20,11 @@ public:
* *
* *
* @param min_score Minimum score to consider a triangulated joint as valid. * @param min_score Minimum score to consider a triangulated joint as valid.
* @param min_group_size Minimum number of camera pairs that need to see a person.
*/ */
Triangulator( Triangulator(
float min_score = 0.95); float min_score = 0.95,
size_t min_group_size = 1);
/** /**
* Calculate a triangulation. * Calculate a triangulation.

30
spt/triangulator.cpp
View File

@ -102,9 +102,10 @@ void CameraInternal::update_projection_matrix()
// ================================================================================================= // =================================================================================================
// ================================================================================================= // =================================================================================================
TriangulatorInternal::TriangulatorInternal(float min_score) TriangulatorInternal::TriangulatorInternal(float min_score, size_t min_group_size)
{ {
this->min_score = min_score; this->min_score = min_score;
this->min_group_size = min_group_size;
} }
// ================================================================================================= // =================================================================================================
@ -443,20 +444,13 @@ std::vector<std::vector<std::array<float, 4>>> TriangulatorInternal::triangulate
stime = std::chrono::high_resolution_clock::now(); stime = std::chrono::high_resolution_clock::now();
// Drop low scoring poses // Drop low scoring poses
std::vector<size_t> drop_indices; size_t num_poses = all_scored_poses.size();
for (size_t i = 0; i < all_scored_poses.size(); ++i) for (size_t i = num_poses; i > 0; --i)
{ {
if (all_scored_poses[i].second < min_score) if (all_scored_poses[i - 1].second < min_score)
{ {
drop_indices.push_back(i); all_scored_poses.erase(all_scored_poses.begin() + i - 1);
} all_pairs.erase(all_pairs.begin() + i - 1);
}
if (!drop_indices.empty())
{
for (size_t i = drop_indices.size(); i > 0; --i)
{
all_scored_poses.erase(all_scored_poses.begin() + drop_indices[i - 1]);
all_pairs.erase(all_pairs.begin() + drop_indices[i - 1]);
} }
} }
@ -464,6 +458,16 @@ std::vector<std::vector<std::array<float, 4>>> TriangulatorInternal::triangulate
std::vector<std::tuple<cv::Point3d, cv::Mat, std::vector<int>>> groups; std::vector<std::tuple<cv::Point3d, cv::Mat, std::vector<int>>> groups;
groups = calc_grouping(all_pairs, all_scored_poses, min_score); groups = calc_grouping(all_pairs, all_scored_poses, min_score);
// Drop groups with too few matches
size_t num_groups = groups.size();
for (size_t i = num_groups; i > 0; --i)
{
if (std::get<2>(groups[i - 1]).size() < this->min_group_size)
{
groups.erase(groups.begin() + i - 1);
}
}
elapsed = std::chrono::high_resolution_clock::now() - stime; elapsed = std::chrono::high_resolution_clock::now() - stime;
grouping_time += elapsed.count(); grouping_time += elapsed.count();
stime = std::chrono::high_resolution_clock::now(); stime = std::chrono::high_resolution_clock::now();

4
spt/triangulator.hpp
View File

@ -31,7 +31,7 @@ public:
class TriangulatorInternal class TriangulatorInternal
{ {
public: public:
TriangulatorInternal(float min_score); TriangulatorInternal(float min_score, size_t min_group_size);
std::vector<std::vector<std::array<float, 4>>> triangulate_poses( std::vector<std::vector<std::array<float, 4>>> triangulate_poses(
const std::vector<std::vector<std::vector<std::array<float, 3>>>> &poses_2d, const std::vector<std::vector<std::vector<std::array<float, 3>>>> &poses_2d,
@ -44,6 +44,8 @@ public:
private: private:
float min_score; float min_score;
float min_group_size;
const std::vector<std::string> core_joints = { const std::vector<std::string> core_joints = {
"shoulder_left", "shoulder_left",
"shoulder_right", "shoulder_right",