Changes
On August 4, 2023 at 8:46:26 AM UTC, admin:
-
No fields were updated. See the metadata diff for more details.
f | 1 | { | f | 1 | { |
2 | "author": "Max Coenen", | 2 | "author": "Max Coenen", | ||
3 | "author_email": "m.coenen@baustof.uni-hannover.de", | 3 | "author_email": "m.coenen@baustof.uni-hannover.de", | ||
4 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | 4 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | ||
5 | "doi": "10.25835/61y9peiq", | 5 | "doi": "10.25835/61y9peiq", | ||
6 | "doi_date_published": "2022-11-23", | 6 | "doi_date_published": "2022-11-23", | ||
7 | "doi_publisher": "LUIS", | 7 | "doi_publisher": "LUIS", | ||
8 | "doi_status": "true", | 8 | "doi_status": "true", | ||
9 | "domain": "https://data.uni-hannover.de", | 9 | "domain": "https://data.uni-hannover.de", | ||
10 | "groups": [], | 10 | "groups": [], | ||
11 | "have_copyright": "Yes", | 11 | "have_copyright": "Yes", | ||
12 | "id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | 12 | "id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | ||
13 | "isopen": false, | 13 | "isopen": false, | ||
14 | "license_id": "CC-BY-NC-3.0", | 14 | "license_id": "CC-BY-NC-3.0", | ||
15 | "license_title": "CC-BY-NC-3.0", | 15 | "license_title": "CC-BY-NC-3.0", | ||
16 | "maintainer": "Max Coenen", | 16 | "maintainer": "Max Coenen", | ||
17 | "maintainer_email": "m.coenen@baustoff.uni-hannover.de", | 17 | "maintainer_email": "m.coenen@baustoff.uni-hannover.de", | ||
18 | "metadata_created": "2023-01-12T13:14:11.720857", | 18 | "metadata_created": "2023-01-12T13:14:11.720857", | ||
n | 19 | "metadata_modified": "2023-05-02T07:05:19.324628", | n | 19 | "metadata_modified": "2023-08-04T08:46:26.290084", |
20 | "name": "luh-deep-granulometry", | 20 | "name": "luh-deep-granulometry", | ||
21 | "notes": "This repository contains the data related to the paper ** | 21 | "notes": "This repository contains the data related to the paper ** | ||
22 | \"Deep Granulometry: Image based estimation of concrete aggregate size | 22 | \"Deep Granulometry: Image based estimation of concrete aggregate size | ||
23 | distributions using deep learning\" ** where a deep learning based | 23 | distributions using deep learning\" ** where a deep learning based | ||
24 | method is proposed for the image based determination of concrete | 24 | method is proposed for the image based determination of concrete | ||
25 | aggregate grading curves (cf. video).\r\n\r\n[![Watch the | 25 | aggregate grading curves (cf. video).\r\n\r\n[![Watch the | ||
26 | enen.github.io/resources/images/2023_DeepGranulometry.mp4)\r\n\r\nMore | 26 | enen.github.io/resources/images/2023_DeepGranulometry.mp4)\r\n\r\nMore | ||
27 | specifically, the data set consists of images showing concrete | 27 | specifically, the data set consists of images showing concrete | ||
28 | aggregate particles and reference data of the particle size | 28 | aggregate particles and reference data of the particle size | ||
29 | distribution (grading curves) associated to each image. \r\nIt is | 29 | distribution (grading curves) associated to each image. \r\nIt is | ||
30 | distinguished between the **CoarseAggregateData** and the | 30 | distinguished between the **CoarseAggregateData** and the | ||
31 | **FineAggregateData**. \r\n \r\n \r\n\r\n\r\n\r\n# Coarse | 31 | **FineAggregateData**. \r\n \r\n \r\n\r\n\r\n\r\n# Coarse | ||
32 | Aggregate Data\r\nThe __coarse__ data consists of aggregate samples | 32 | Aggregate Data\r\nThe __coarse__ data consists of aggregate samples | ||
33 | with different particles sizes ranging from 0.1 mm to 32 mm. The | 33 | with different particles sizes ranging from 0.1 mm to 32 mm. The | ||
34 | grading curves are designed by linearly interpolation between a very | 34 | grading curves are designed by linearly interpolation between a very | ||
35 | fine and a very coarse distribution for three variants with maximum | 35 | fine and a very coarse distribution for three variants with maximum | ||
36 | grain sizes of 8 mm, 16 mm, and 32 mm, respectively. For each variant, | 36 | grain sizes of 8 mm, 16 mm, and 32 mm, respectively. For each variant, | ||
37 | we designed eleven grading curves, resulting in a total number 33, | 37 | we designed eleven grading curves, resulting in a total number 33, | ||
38 | which are shown in the figure below. For each sample, we acquired 50 | 38 | which are shown in the figure below. For each sample, we acquired 50 | ||
39 | images with a GSD of 0.125 mm, resulting in a data set of 1650 images | 39 | images with a GSD of 0.125 mm, resulting in a data set of 1650 images | ||
40 | in total. Example images for a subset of the\r\ngrading curves of this | 40 | in total. Example images for a subset of the\r\ngrading curves of this | ||
41 | data set are shown in the following figure.\r\n\r\n![Example images | 41 | data set are shown in the following figure.\r\n\r\n![Example images | ||
42 | and grading curves of the coarse data | 42 | and grading curves of the coarse data | ||
43 | source/8cb30616-5b24-4028-9c1d-ea250ac8ac84/download/examplecoarse.png | 43 | source/8cb30616-5b24-4028-9c1d-ea250ac8ac84/download/examplecoarse.png | ||
44 | \" \")\r\n\r\n \r\n \r\n\r\n# Fine Aggregate Data\r\nSimilar | 44 | \" \")\r\n\r\n \r\n \r\n\r\n# Fine Aggregate Data\r\nSimilar | ||
45 | to the previous data set, the __fine__ data set contains grading | 45 | to the previous data set, the __fine__ data set contains grading | ||
46 | curves for the fine\r\nfraction of concrete aggregate of 0 to 2 mm | 46 | curves for the fine\r\nfraction of concrete aggregate of 0 to 2 mm | ||
47 | with a GSD of 28.5 $\\mu$m.\r\nWe defined two base distributions of | 47 | with a GSD of 28.5 $\\mu$m.\r\nWe defined two base distributions of | ||
48 | different shapes for the upper and lower bound, respectively, | 48 | different shapes for the upper and lower bound, respectively, | ||
49 | resulting in two interpolated grading curve sets (Set A and Set B). In | 49 | resulting in two interpolated grading curve sets (Set A and Set B). In | ||
50 | total, 1700\r\nimages of 34 different particle size distributions were | 50 | total, 1700\r\nimages of 34 different particle size distributions were | ||
51 | acquired. Example images of the data set and the corresponding grading | 51 | acquired. Example images of the data set and the corresponding grading | ||
52 | curves are shown in the figure below.\r\n![Example images and grading | 52 | curves are shown in the figure below.\r\n![Example images and grading | ||
53 | curves of the finedata | 53 | curves of the finedata | ||
54 | resource/c56f4298-9663-457f-aaa7-0ba113fec4c9/download/examplefine.png | 54 | resource/c56f4298-9663-457f-aaa7-0ba113fec4c9/download/examplefine.png | ||
55 | \" \")\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n## Related | 55 | \" \")\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n## Related | ||
56 | publications:\r\nIf you make use of the proposed data, please cite one | 56 | publications:\r\nIf you make use of the proposed data, please cite one | ||
57 | of the publication listed below. \r\n\r\n* **Coenen, M., Beyer, D., | 57 | of the publication listed below. \r\n\r\n* **Coenen, M., Beyer, D., | ||
58 | and Haist, M., 2023**: Granulometry Transformer: Image-based | 58 | and Haist, M., 2023**: Granulometry Transformer: Image-based | ||
59 | Granulometry of Concrete Aggregate for an automated Concrete | 59 | Granulometry of Concrete Aggregate for an automated Concrete | ||
60 | Production Control. In: Proceedings of the European Conference on | 60 | Production Control. In: Proceedings of the European Conference on | ||
61 | Computing in Construction (EC3).\r\n\r\n* **Coenen, M., Beyer, D., | 61 | Computing in Construction (EC3).\r\n\r\n* **Coenen, M., Beyer, D., | ||
62 | Ponick, A., Heipke, C. and Haist, M., 2023**: Deep Granulometry: Image | 62 | Ponick, A., Heipke, C. and Haist, M., 2023**: Deep Granulometry: Image | ||
63 | based estimation of concrete aggregate size distributions using deep | 63 | based estimation of concrete aggregate size distributions using deep | ||
64 | learning. _To be published_.\r\n\r\n## Source Code \r\nSource code for | 64 | learning. _To be published_.\r\n\r\n## Source Code \r\nSource code for | ||
65 | CNN based prediction of grading curves using the data set can be found | 65 | CNN based prediction of grading curves using the data set can be found | ||
66 | on github under following | 66 | on github under following | ||
67 | [Link](https://github.com/MaximilianCoenen/DeepGranulometry.git).", | 67 | [Link](https://github.com/MaximilianCoenen/DeepGranulometry.git).", | ||
68 | "num_resources": 4, | 68 | "num_resources": 4, | ||
69 | "num_tags": 5, | 69 | "num_tags": 5, | ||
70 | "organization": { | 70 | "organization": { | ||
71 | "approval_status": "approved", | 71 | "approval_status": "approved", | ||
72 | "created": "2021-10-14T10:15:54.910241", | 72 | "created": "2021-10-14T10:15:54.910241", | ||
73 | "description": "Appelstra\u00dfe 9a\r\n__30167 | 73 | "description": "Appelstra\u00dfe 9a\r\n__30167 | ||
74 | Hannover__\r\n\r\nTel.: +49 511762-3722 \r\n\r\nFax: +49 511762-4736 | 74 | Hannover__\r\n\r\nTel.: +49 511762-3722 \r\n\r\nFax: +49 511762-4736 | ||
75 | \r\n\r\nE-Mail: institut@baustoff.uni-hannover.de | 75 | \r\n\r\nE-Mail: institut@baustoff.uni-hannover.de | ||
76 | \r\n\r\nhttps://www.baustoff.uni-hannover.de/\r\n", | 76 | \r\n\r\nhttps://www.baustoff.uni-hannover.de/\r\n", | ||
77 | "id": "c5907647-9127-4a15-819b-9d61da4e3ec6", | 77 | "id": "c5907647-9127-4a15-819b-9d61da4e3ec6", | ||
78 | "image_url": "", | 78 | "image_url": "", | ||
79 | "is_organization": true, | 79 | "is_organization": true, | ||
80 | "name": "institut-fur-baustoffe", | 80 | "name": "institut-fur-baustoffe", | ||
81 | "state": "active", | 81 | "state": "active", | ||
82 | "title": "Institut f\u00fcr Baustoffe", | 82 | "title": "Institut f\u00fcr Baustoffe", | ||
83 | "type": "organization" | 83 | "type": "organization" | ||
84 | }, | 84 | }, | ||
85 | "owner_org": "c5907647-9127-4a15-819b-9d61da4e3ec6", | 85 | "owner_org": "c5907647-9127-4a15-819b-9d61da4e3ec6", | ||
86 | "private": false, | 86 | "private": false, | ||
87 | "relationships_as_object": [], | 87 | "relationships_as_object": [], | ||
88 | "relationships_as_subject": [], | 88 | "relationships_as_subject": [], | ||
89 | "repository_name": "Leibniz University Hannover", | 89 | "repository_name": "Leibniz University Hannover", | ||
90 | "resources": [ | 90 | "resources": [ | ||
91 | { | 91 | { | ||
92 | "cache_last_updated": null, | 92 | "cache_last_updated": null, | ||
93 | "cache_url": null, | 93 | "cache_url": null, | ||
94 | "created": "2022-11-21T12:37:43.012343", | 94 | "created": "2022-11-21T12:37:43.012343", | ||
95 | "description": "", | 95 | "description": "", | ||
96 | "format": "PNG", | 96 | "format": "PNG", | ||
97 | "hash": "", | 97 | "hash": "", | ||
98 | "id": "8cb30616-5b24-4028-9c1d-ea250ac8ac84", | 98 | "id": "8cb30616-5b24-4028-9c1d-ea250ac8ac84", | ||
99 | "last_modified": "2022-11-21T12:37:42.974381", | 99 | "last_modified": "2022-11-21T12:37:42.974381", | ||
n | 100 | "metadata_modified": "2023-05-02T07:05:19.331411", | n | 100 | "metadata_modified": "2023-08-04T08:46:26.293491", |
101 | "mimetype": "image/png", | 101 | "mimetype": "image/png", | ||
102 | "mimetype_inner": null, | 102 | "mimetype_inner": null, | ||
103 | "name": "ExampleCoarse.png", | 103 | "name": "ExampleCoarse.png", | ||
104 | "package_id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | 104 | "package_id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | ||
105 | "position": 0, | 105 | "position": 0, | ||
106 | "resource_type": null, | 106 | "resource_type": null, | ||
107 | "size": 4725003, | 107 | "size": 4725003, | ||
108 | "state": "active", | 108 | "state": "active", | ||
109 | "url": | 109 | "url": | ||
110 | urce/8cb30616-5b24-4028-9c1d-ea250ac8ac84/download/examplecoarse.png", | 110 | urce/8cb30616-5b24-4028-9c1d-ea250ac8ac84/download/examplecoarse.png", | ||
111 | "url_type": "" | 111 | "url_type": "" | ||
112 | }, | 112 | }, | ||
113 | { | 113 | { | ||
114 | "cache_last_updated": null, | 114 | "cache_last_updated": null, | ||
115 | "cache_url": null, | 115 | "cache_url": null, | ||
116 | "created": "2022-11-21T12:37:55.172826", | 116 | "created": "2022-11-21T12:37:55.172826", | ||
117 | "description": "", | 117 | "description": "", | ||
118 | "format": "PNG", | 118 | "format": "PNG", | ||
119 | "hash": "", | 119 | "hash": "", | ||
120 | "id": "c56f4298-9663-457f-aaa7-0ba113fec4c9", | 120 | "id": "c56f4298-9663-457f-aaa7-0ba113fec4c9", | ||
121 | "last_modified": "2022-11-21T12:37:55.132145", | 121 | "last_modified": "2022-11-21T12:37:55.132145", | ||
n | 122 | "metadata_modified": "2023-05-02T07:05:19.331602", | n | 122 | "metadata_modified": "2023-08-04T08:46:26.293626", |
123 | "mimetype": "image/png", | 123 | "mimetype": "image/png", | ||
124 | "mimetype_inner": null, | 124 | "mimetype_inner": null, | ||
125 | "name": "ExampleFine.png", | 125 | "name": "ExampleFine.png", | ||
126 | "package_id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | 126 | "package_id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | ||
127 | "position": 1, | 127 | "position": 1, | ||
128 | "resource_type": null, | 128 | "resource_type": null, | ||
129 | "size": 8352660, | 129 | "size": 8352660, | ||
130 | "state": "active", | 130 | "state": "active", | ||
131 | "url": | 131 | "url": | ||
132 | source/c56f4298-9663-457f-aaa7-0ba113fec4c9/download/examplefine.png", | 132 | source/c56f4298-9663-457f-aaa7-0ba113fec4c9/download/examplefine.png", | ||
133 | "url_type": "" | 133 | "url_type": "" | ||
134 | }, | 134 | }, | ||
135 | { | 135 | { | ||
136 | "cache_last_updated": null, | 136 | "cache_last_updated": null, | ||
137 | "cache_url": null, | 137 | "cache_url": null, | ||
138 | "created": "2022-11-23T10:12:07.222415", | 138 | "created": "2022-11-23T10:12:07.222415", | ||
139 | "description": "MD5 Checksum: 9269a3640aa88ef89a73ce1c7d66a463", | 139 | "description": "MD5 Checksum: 9269a3640aa88ef89a73ce1c7d66a463", | ||
140 | "format": "ZIP", | 140 | "format": "ZIP", | ||
141 | "hash": "", | 141 | "hash": "", | ||
142 | "id": "0f3be986-e6fe-481e-844e-544f26249a27", | 142 | "id": "0f3be986-e6fe-481e-844e-544f26249a27", | ||
143 | "last_modified": null, | 143 | "last_modified": null, | ||
n | 144 | "metadata_modified": "2023-05-02T07:05:19.331760", | n | 144 | "metadata_modified": "2023-08-04T08:46:26.293755", |
145 | "mimetype": "application/zip", | 145 | "mimetype": "application/zip", | ||
146 | "mimetype_inner": null, | 146 | "mimetype_inner": null, | ||
147 | "name": "CoarseAggregateData.zip", | 147 | "name": "CoarseAggregateData.zip", | ||
148 | "package_id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | 148 | "package_id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | ||
149 | "position": 2, | 149 | "position": 2, | ||
150 | "resource_type": null, | 150 | "resource_type": null, | ||
151 | "size": null, | 151 | "size": null, | ||
152 | "state": "active", | 152 | "state": "active", | ||
153 | "url": | 153 | "url": | ||
154 | aset/upload/users/baustoff/deep_granulometry/CoarseAggregateData.zip", | 154 | aset/upload/users/baustoff/deep_granulometry/CoarseAggregateData.zip", | ||
155 | "url_type": "" | 155 | "url_type": "" | ||
156 | }, | 156 | }, | ||
157 | { | 157 | { | ||
158 | "cache_last_updated": null, | 158 | "cache_last_updated": null, | ||
159 | "cache_url": null, | 159 | "cache_url": null, | ||
160 | "created": "2022-11-23T10:12:42.500872", | 160 | "created": "2022-11-23T10:12:42.500872", | ||
161 | "description": "MD5 Checksum: 2972810aa13c8c06a01afb5fbe1ace8b", | 161 | "description": "MD5 Checksum: 2972810aa13c8c06a01afb5fbe1ace8b", | ||
162 | "format": "ZIP", | 162 | "format": "ZIP", | ||
163 | "hash": "", | 163 | "hash": "", | ||
164 | "id": "8a491282-309f-4f1b-9b44-49da330a128a", | 164 | "id": "8a491282-309f-4f1b-9b44-49da330a128a", | ||
165 | "last_modified": null, | 165 | "last_modified": null, | ||
n | 166 | "metadata_modified": "2023-05-02T07:05:19.331891", | n | 166 | "metadata_modified": "2023-08-04T08:46:26.293870", |
167 | "mimetype": "application/zip", | 167 | "mimetype": "application/zip", | ||
168 | "mimetype_inner": null, | 168 | "mimetype_inner": null, | ||
169 | "name": "FineAggregateData.zip", | 169 | "name": "FineAggregateData.zip", | ||
170 | "package_id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | 170 | "package_id": "1bf33963-a111-48fb-a662-9c6fa9b248af", | ||
171 | "position": 3, | 171 | "position": 3, | ||
172 | "resource_type": null, | 172 | "resource_type": null, | ||
173 | "size": null, | 173 | "size": null, | ||
174 | "state": "active", | 174 | "state": "active", | ||
175 | "url": | 175 | "url": | ||
176 | ataset/upload/users/baustoff/deep_granulometry/FineAggregateData.zip", | 176 | ataset/upload/users/baustoff/deep_granulometry/FineAggregateData.zip", | ||
177 | "url_type": "" | 177 | "url_type": "" | ||
178 | } | 178 | } | ||
179 | ], | 179 | ], | ||
t | t | 180 | "services_used_list": "", | ||
180 | "source_metadata_created": "2022-11-21T11:37:21.373303", | 181 | "source_metadata_created": "2022-11-21T11:37:21.373303", | ||
181 | "source_metadata_modified": "2023-04-27T19:11:53.801633", | 182 | "source_metadata_modified": "2023-04-27T19:11:53.801633", | ||
182 | "state": "active", | 183 | "state": "active", | ||
183 | "tags": [ | 184 | "tags": [ | ||
184 | { | 185 | { | ||
185 | "display_name": "CNN", | 186 | "display_name": "CNN", | ||
186 | "id": "66ec0da0-d205-4a39-90c6-bae7e7b1cbd6", | 187 | "id": "66ec0da0-d205-4a39-90c6-bae7e7b1cbd6", | ||
187 | "name": "CNN", | 188 | "name": "CNN", | ||
188 | "state": "active", | 189 | "state": "active", | ||
189 | "vocabulary_id": null | 190 | "vocabulary_id": null | ||
190 | }, | 191 | }, | ||
191 | { | 192 | { | ||
192 | "display_name": "Concrete Aggregate", | 193 | "display_name": "Concrete Aggregate", | ||
193 | "id": "6baffc3f-c876-4adb-ae93-2a2ea8d221e1", | 194 | "id": "6baffc3f-c876-4adb-ae93-2a2ea8d221e1", | ||
194 | "name": "Concrete Aggregate", | 195 | "name": "Concrete Aggregate", | ||
195 | "state": "active", | 196 | "state": "active", | ||
196 | "vocabulary_id": null | 197 | "vocabulary_id": null | ||
197 | }, | 198 | }, | ||
198 | { | 199 | { | ||
199 | "display_name": "computer vision", | 200 | "display_name": "computer vision", | ||
200 | "id": "f650b4e3-9955-49b0-ba7b-2d302a990978", | 201 | "id": "f650b4e3-9955-49b0-ba7b-2d302a990978", | ||
201 | "name": "computer vision", | 202 | "name": "computer vision", | ||
202 | "state": "active", | 203 | "state": "active", | ||
203 | "vocabulary_id": null | 204 | "vocabulary_id": null | ||
204 | }, | 205 | }, | ||
205 | { | 206 | { | ||
206 | "display_name": "deep learning", | 207 | "display_name": "deep learning", | ||
207 | "id": "19e41883-3799-4184-9e0e-26c95795b119", | 208 | "id": "19e41883-3799-4184-9e0e-26c95795b119", | ||
208 | "name": "deep learning", | 209 | "name": "deep learning", | ||
209 | "state": "active", | 210 | "state": "active", | ||
210 | "vocabulary_id": null | 211 | "vocabulary_id": null | ||
211 | }, | 212 | }, | ||
212 | { | 213 | { | ||
213 | "display_name": "granulometry", | 214 | "display_name": "granulometry", | ||
214 | "id": "4593ebf2-7d9c-4c6c-bbdc-694f0fc0f59f", | 215 | "id": "4593ebf2-7d9c-4c6c-bbdc-694f0fc0f59f", | ||
215 | "name": "granulometry", | 216 | "name": "granulometry", | ||
216 | "state": "active", | 217 | "state": "active", | ||
217 | "vocabulary_id": null | 218 | "vocabulary_id": null | ||
218 | } | 219 | } | ||
219 | ], | 220 | ], | ||
220 | "terms_of_usage": "Yes", | 221 | "terms_of_usage": "Yes", | ||
221 | "title": "Deep Granulometry", | 222 | "title": "Deep Granulometry", | ||
222 | "type": "vdataset", | 223 | "type": "vdataset", | ||
223 | "url": "https://data.uni-hannover.de/dataset/deep-granulometry", | 224 | "url": "https://data.uni-hannover.de/dataset/deep-granulometry", | ||
224 | "version": "" | 225 | "version": "" | ||
225 | } | 226 | } |