Dataset Open Access
ITOP Dataset
Haque, Albert;
Peng, Boya;
Luo, Zelun;
Alahi, Alexandre;
Yeung, Serena;
Fei-Fei, Li
JSON Export
{
"files": [
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_side_test_depth_map.h5.gz"
},
"checksum": "md5:65f431c9f7540db6118d99bc9bae7576",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_side_test_depth_map.h5.gz",
"type": "gz",
"size": 245104261
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_side_test_images.h5.gz"
},
"checksum": "md5:1803c50e44746dca7ccf03c2d46c466e",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_side_test_images.h5.gz",
"type": "gz",
"size": 257980348
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_side_test_labels.h5.gz"
},
"checksum": "md5:7205b0ba47f76892742ded774754d7a1",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_side_test_labels.h5.gz",
"type": "gz",
"size": 3699135
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_side_test_point_cloud.h5.gz"
},
"checksum": "md5:3f5227d6f260011b19f325fffde08a65",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_side_test_point_cloud.h5.gz",
"type": "gz",
"size": 2061701631
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_side_train_depth_map.h5.gz"
},
"checksum": "md5:80736f716b0e83f7cc73ec85bb13effc",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_side_train_depth_map.h5.gz",
"type": "gz",
"size": 926228035
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_side_train_images.h5.gz"
},
"checksum": "md5:e325ed23ed962f86594b70f17c048a30",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_side_train_images.h5.gz",
"type": "gz",
"size": 1010377751
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_side_train_labels.h5.gz"
},
"checksum": "md5:e62a67678d5cddc13e07cfdd1eb0a176",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_side_train_labels.h5.gz",
"type": "gz",
"size": 16833112
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_side_train_point_cloud.h5.gz"
},
"checksum": "md5:6ca457e8471e7514222624e937e11a9c",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_side_train_point_cloud.h5.gz",
"type": "gz",
"size": 7840345186
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_top_test_depth_map.h5.gz"
},
"checksum": "md5:d8ad31ecbbcd13ee5e1f02874c0cb3d0",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_top_test_depth_map.h5.gz",
"type": "gz",
"size": 245493889
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_top_test_images.h5.gz"
},
"checksum": "md5:21f702e3ce0e5602340957e6cae6148a",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_top_test_images.h5.gz",
"type": "gz",
"size": 246678932
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_top_test_labels.h5.gz"
},
"checksum": "md5:6a9c5d7845dc7fdf6d168ee4dd356afd",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_top_test_labels.h5.gz",
"type": "gz",
"size": 9280299
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_top_test_point_cloud.h5.gz"
},
"checksum": "md5:3ac977488864e27ac13e8cf17d03f8c7",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_top_test_point_cloud.h5.gz",
"type": "gz",
"size": 2020245383
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_top_train_depth_map.h5.gz"
},
"checksum": "md5:159a8694f653f5b639252de84469f7b9",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_top_train_depth_map.h5.gz",
"type": "gz",
"size": 917859800
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_top_train_images.h5.gz"
},
"checksum": "md5:6e2daf5be0f0bf6eddf611913e718417",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_top_train_images.h5.gz",
"type": "gz",
"size": 923855225
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_top_train_labels.h5.gz"
},
"checksum": "md5:95776e7beeb9a769bef25eb336afb5bd",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_top_train_labels.h5.gz",
"type": "gz",
"size": 32165804
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/ITOP_top_train_point_cloud.h5.gz"
},
"checksum": "md5:f5fd64240296be0bfff5318beca19884",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "ITOP_top_train_point_cloud.h5.gz",
"type": "gz",
"size": 7620649272
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/sample_front.jpg"
},
"checksum": "md5:86d7be54b61841fe22b27949fffc042d",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "sample_front.jpg",
"type": "jpg",
"size": 20450
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/sample_front_labeled.jpg"
},
"checksum": "md5:25aaef40a70ad75f452438824a2bb71f",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "sample_front_labeled.jpg",
"type": "jpg",
"size": 22911
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/sample_top.jpg"
},
"checksum": "md5:0afbd5971faee803d14969e4c2a71267",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "sample_top.jpg",
"type": "jpg",
"size": 18689
},
{
"links": {
"self": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4/sample_top_labeled.jpg"
},
"checksum": "md5:5d6c045333e9f520c24d335f57e0422e",
"bucket": "aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"key": "sample_top_labeled.jpg",
"type": "jpg",
"size": 17461
}
],
"owners": [
84934
],
"doi": "10.5281/zenodo.3932973",
"stats": {
"version_unique_downloads": 588.0,
"unique_views": 284.0,
"views": 373.0,
"version_views": 373.0,
"unique_downloads": 588.0,
"version_unique_views": 284.0,
"volume": 16952105365186.0,
"version_downloads": 5334.0,
"downloads": 5334.0,
"version_volume": 16952105365186.0
},
"links": {
"thumb250": "https://zenodo.org/api/iiif/v2/aefee483-2fb7-4f1c-a24e-7fe82399c5f4:4a51cc97-6636-4825-b738-98139ef2588c:sample_front.jpg/full/250,/0/default.jpg",
"doi": "https://doi.org/10.5281/zenodo.3932973",
"thumbs": {
"10": "https://zenodo.org/record/3932973/thumb10",
"750": "https://zenodo.org/record/3932973/thumb750",
"50": "https://zenodo.org/record/3932973/thumb50",
"1200": "https://zenodo.org/record/3932973/thumb1200",
"100": "https://zenodo.org/record/3932973/thumb100",
"250": "https://zenodo.org/record/3932973/thumb250"
},
"conceptdoi": "https://doi.org/10.5281/zenodo.3932972",
"conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3932972.svg",
"latest_html": "https://zenodo.org/record/3932973",
"bucket": "https://zenodo.org/api/files/aefee483-2fb7-4f1c-a24e-7fe82399c5f4",
"badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3932973.svg",
"html": "https://zenodo.org/record/3932973",
"latest": "https://zenodo.org/api/records/3932973"
},
"conceptdoi": "10.5281/zenodo.3932972",
"created": "2020-07-07T19:19:39.659225+00:00",
"updated": "2020-07-31T06:24:25.797000+00:00",
"conceptrecid": "3932972",
"revision": 5,
"id": 3932973,
"metadata": {
"access_right_category": "success",
"doi": "10.5281/zenodo.3932973",
"description": "<p><strong>Summary</strong></p>\n\n<p>The ITOP dataset (Invariant Top View) contains 100K depth images from side and top views of a person in a scene. For each image, the location of 15 human body parts are labeled with 3-dimensional (x,y,z) coordinates, relative to the sensor's position. Read the full paper for more context [<a href=\"https://arxiv.org/pdf/1603.07076.pdf\">pdf</a>].</p>\n\n<p><strong>Getting Started</strong></p>\n\n<p>Download then decompress the h5.gz file.</p>\n\n<pre><code class=\"language-bash\">gunzip ITOP_side_test_depth_map.h5.gz</code></pre>\n\n<p>Using Python and <a href=\"https://www.h5py.org/\">h5py</a> (<em>pip install h5py</em> or <em>conda install h5py</em>), we can load the contents:</p>\n\n<pre><code class=\"language-python\">import h5py\nimport numpy as np\n\nf = h5py.File('ITOP_side_test_depth_map.h5', 'r')\ndata, ids = f.get('data'), f.get('id')\ndata, ids = np.asarray(data), np.asarray(ids)\n\nprint(data.shape, ids.shape)\n# (10501, 240, 320) (10501,)</code></pre>\n\n<p><strong>Note:</strong> For any of the <em>*_images.h5.gz</em> files, the underlying file is a tar file and not a h5 file. Please rename the file extension from <em>h5.gz</em> to <em>tar.gz</em> before opening. The following commands will work:</p>\n\n<pre><code class=\"language-bash\">mv ITOP_side_test_images.h5.gz ITOP_side_test_images.tar.gz\ntar xf ITOP_side_test_images.tar.gz</code></pre>\n\n<p><strong>Metadata</strong></p>\n\n<p>File sizes for images, depth maps, point clouds, and labels refer to the uncompressed size.</p>\n\n<pre><code>+-------+--------+---------+---------+----------+------------+--------------+---------+\n| View | Split | Frames | People | Images | Depth Map | Point Cloud | Labels |\n+-------+--------+---------+---------+----------+------------+--------------+---------+\n| Side | Train | 39,795 | 16 | 1.1 GiB | 5.7 GiB | 18 GiB | 2.9 GiB |\n| Side | Test | 10,501 | 4 | 276 MiB | 1.6 GiB | 4.6 GiB | 771 MiB |\n| Top | Train | 39,795 | 16 | 974 MiB | 5.7 GiB | 18 GiB | 2.9 GiB |\n| Top | Test | 10,501 | 4 | 261 MiB | 1.6 GiB | 4.6 GiB | 771 MiB |\n+-------+--------+---------+---------+----------+------------+--------------+---------+</code></pre>\n\n<p><strong>Data Schema</strong></p>\n\n<p>Each file contains several HDF5 datasets at the root level. Dimensions, attributes, and data types are listed below. The key refers to the (HDF5) dataset name. Let <span class=\"math-tex\">\\(n\\)</span> denote the number of images.<br>\n<br>\n<strong>Transformation</strong></p>\n\n<p>To convert from point clouds to a <span class=\"math-tex\">\\(240 \\times 320\\)</span> image, the following transformations were used. Let <span class=\"math-tex\">\\(x_{\\textrm{img}}\\)</span> and <span class=\"math-tex\">\\(y_{\\textrm{img}}\\)</span> denote the <span class=\"math-tex\">\\((x,y)\\)</span> coordinate in the image plane. Using the raw point cloud <span class=\"math-tex\">\\((x,y,z)\\)</span> real world coordinates, we compute the depth map as follows: <span class=\"math-tex\">\\(x_{\\textrm{img}} = \\frac{x}{Cz} + 160\\)</span> and <span class=\"math-tex\">\\(y_{\\textrm{img}} = -\\frac{y}{Cz} + 120\\)</span> where <span class=\"math-tex\">\\(C\\approx 3.50\u00d710^{\u22123} = 0.0035\\)</span> is the intrinsic camera calibration parameter. This results in the depth map: <span class=\"math-tex\">\\((x_{\\textrm{img}}, y_{\\textrm{img}}, z)\\)</span>.</p>\n\n<p><strong>Joint ID (Index) Mapping</strong></p>\n\n<pre><code>joint_id_to_name = {\n 0: 'Head', 8: 'Torso',\n 1: 'Neck', 9: 'R Hip',\n 2: 'R Shoulder', 10: 'L Hip',\n 3: 'L Shoulder', 11: 'R Knee',\n 4: 'R Elbow', 12: 'L Knee',\n 5: 'L Elbow', 13: 'R Foot',\n 6: 'R Hand', 14: 'L Foot',\n 7: 'L Hand',\n}</code></pre>\n\n<p><strong>Depth Maps</strong></p>\n\n<ul>\n\t<li><em>Key:</em> id\n\n\t<ul>\n\t\t<li><em>Dimensions:</em> <span class=\"math-tex\">\\((n,)\\)</span></li>\n\t\t<li><em>Data Type:</em> uint8</li>\n\t\t<li><em>Description:</em> Frame identifier in the form XX_YYYYY where XX is the person's ID number and YYYYY is the frame number.</li>\n\t</ul>\n\t</li>\n\t<li><em>Key: </em>data\n\t<ul>\n\t\t<li><em>Dimensions: </em><span class=\"math-tex\">\\((n,240,320)\\)</span></li>\n\t\t<li><em>Data Type:</em> float16</li>\n\t\t<li><em>Description:</em> Depth map (i.e. mesh) corresponding to a single frame. Depth values are in real world meters (m).</li>\n\t</ul>\n\t</li>\n</ul>\n\n<p><strong>Point Clouds</strong></p>\n\n<ul>\n\t<li><em>Key:</em> id\n\n\t<ul>\n\t\t<li><em>Dimensions:</em> <span class=\"math-tex\">\\((n,)\\)</span></li>\n\t\t<li><em>Data Type:</em> uint8</li>\n\t\t<li><em>Description:</em> Frame identifier in the form XX_YYYYY where XX is the person's ID number and YYYYY is the frame number.</li>\n\t</ul>\n\t</li>\n\t<li><em>Key: </em>data\n\t<ul>\n\t\t<li><em>Dimensions: </em><span class=\"math-tex\">\\((n,76800,3)\\)</span></li>\n\t\t<li><em>Data Type: float16</em></li>\n\t\t<li><em>Description:</em> Point cloud containing 76,800 points (240x320). Each point is represented by a 3D tuple measured in real world meters (m).</li>\n\t</ul>\n\t</li>\n</ul>\n\n<p><strong>Labels</strong></p>\n\n<ul>\n\t<li><em>Key: </em>id\n\n\t<ul>\n\t\t<li><em>Dimensions: </em><span class=\"math-tex\">\\((n,)\\)</span></li>\n\t\t<li><em>Data Type: </em>uint8</li>\n\t\t<li><em>Description:</em> Frame identifier in the form XX_YYYYY where XX is the person's ID number and YYYYY is the frame number.</li>\n\t</ul>\n\t</li>\n\t<li><em>Key: </em>is_valid\n\t<ul>\n\t\t<li><em>Dimensions: </em><span class=\"math-tex\">\\((n,)\\)</span></li>\n\t\t<li><em>Data Type: </em>uint8</li>\n\t\t<li><em>Description:</em> Flag corresponding to the result of the human labeling effort. This is a boolean value (represented by an integer) where a one (1) denotes clean, human-approved data. A zero (0) denotes noisy human body part labels. If is_valid is equal to zero, you should not use any of the provided human joint locations for the particular frame.</li>\n\t</ul>\n\t</li>\n\t<li><em>Key: </em>visible_joints\n\t<ul>\n\t\t<li><em>Dimensions: </em><span class=\"math-tex\">\\((n,15)\\)</span></li>\n\t\t<li><em>Data Type: </em>int16</li>\n\t\t<li><em>Description:</em> Binary mask indicating if each human joint is visible or occluded. This is denoted by <span class=\"math-tex\">\\(\\alpha\\)</span> in the paper. If <span class=\"math-tex\">\\(\\alpha_j=1\\)</span> then the <span class=\"math-tex\">\\(j^{th}\\)</span> joint is visible (i.e. not occluded). Otherwise, if <span class=\"math-tex\">\\(\\alpha_j = 0\\)</span> then the <span class=\"math-tex\">\\(j^{th}\\)</span> joint is occluded.</li>\n\t</ul>\n\t</li>\n\t<li><em>Key: </em>image_coordinates\n\t<ul>\n\t\t<li><em>Dimensions: </em><span class=\"math-tex\">\\((n,15,2)\\)</span></li>\n\t\t<li><em>Data Type: </em>int16</li>\n\t\t<li><em>Description:</em> Two-dimensional <span class=\"math-tex\">\\((x,y)\\)</span> points corresponding to the location of each joint in the depth image or depth map.</li>\n\t</ul>\n\t</li>\n\t<li><em>Key: </em>real_world_coordinates\n\t<ul>\n\t\t<li><em>Dimensions: </em><span class=\"math-tex\">\\((n,15,3)\\)</span></li>\n\t\t<li><em>Data Type: </em>float16</li>\n\t\t<li><em>Description:</em> Three-dimensional <span class=\"math-tex\">\\((x,y,z)\\)</span> points corresponding to the location of each joint in real world meters (m).</li>\n\t</ul>\n\t</li>\n\t<li><em>Key: </em>segmentation\n\t<ul>\n\t\t<li><em>Dimensions: </em><span class=\"math-tex\">\\((n,240,320)\\)</span></li>\n\t\t<li><em>Data Type: </em><em>int8</em></li>\n\t\t<li><em>Description:</em> Pixel-wise assignment of body part labels. The background class (i.e. no body part) is denoted by −1.</li>\n\t</ul>\n\t</li>\n</ul>\n\n<p><strong>Citation</strong></p>\n\n<p>If you would like to cite our work, please use the following.</p>\n\n<p><strong>Haque A, Peng B, Luo Z, Alahi A, Yeung S, Fei-Fei L. (2016). Towards Viewpoint Invariant 3D Human Pose Estimation. European Conference on Computer Vision. Amsterdam, Netherlands. Springer.</strong></p>\n\n<pre>@inproceedings{haque2016viewpoint,\n title={Towards Viewpoint Invariant 3D Human Pose Estimation},\n author={Haque, Albert and Peng, Boya and Luo, Zelun and Alahi, Alexandre and Yeung, Serena and Fei-Fei, Li},\n booktitle = {European Conference on Computer Vision},\n month = {October},\n year = {2016}\n}</pre>\n\n<ul>\n</ul>",
"language": "eng",
"title": "ITOP Dataset",
"license": {
"id": "CC-BY-4.0"
},
"relations": {
"version": [
{
"count": 1,
"index": 0,
"parent": {
"pid_type": "recid",
"pid_value": "3932972"
},
"is_last": true,
"last_child": {
"pid_type": "recid",
"pid_value": "3932973"
}
}
]
},
"version": "1.0",
"keywords": [
"depth sensor",
"human pose estimation",
"computer vision",
"3D vision"
],
"publication_date": "2016-10-08",
"creators": [
{
"orcid": "0000-0001-6769-6370",
"affiliation": "Stanford University",
"name": "Haque, Albert"
},
{
"affiliation": "Stanford University",
"name": "Peng, Boya"
},
{
"affiliation": "Stanford University",
"name": "Luo, Zelun"
},
{
"affiliation": "Stanford University",
"name": "Alahi, Alexandre"
},
{
"orcid": "0000-0003-0529-0628",
"affiliation": "Stanford University",
"name": "Yeung, Serena"
},
{
"orcid": "0000-0002-7481-0810",
"affiliation": "Stanford University",
"name": "Fei-Fei, Li"
}
],
"access_right": "open",
"resource_type": {
"type": "dataset",
"title": "Dataset"
},
"related_identifiers": [
{
"scheme": "arxiv",
"identifier": "arXiv:1603.07076",
"relation": "cites",
"resource_type": "publication-preprint"
},
{
"scheme": "doi",
"identifier": "10.5281/zenodo.3932972",
"relation": "isVersionOf"
}
]
}
}
373
5,334
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 373 | 373 |
| Downloads | 5,334 | 5,334 |
| Data volume | 17.0 TB | 17.0 TB |
| Unique views | 284 | 284 |
| Unique downloads | 588 | 588 |
Indexed in
- Publication date:
- October 8, 2016
- DOI:
-
- Keyword(s):
- depth sensor human pose estimation computer vision 3D vision
- Related identifiers:
- Cites
- arXiv:1603.07076 (Preprint)
- License (for files):
- Creative Commons Attribution 4.0 International