http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115222663-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_c1714fa0fb12035460eccbdb6011c37a |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20028 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10016 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30232 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0004 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-002 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
| filingDate | 2022-06-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_87cfaf2085fdc3c9620f38b53ffe5392 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d3e2c5475bf9a04fb70b419105850aa8 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9e9327166f8891aad5fdea71133937da http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ed7eefc70e55bcf3e8a16130a8c87924 |
| publicationDate | 2022-10-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-115222663-A |
| titleOfInvention | A method for identifying the package number of an iron and steel plant |
| abstract | The invention discloses a method for identifying a package number in an iron and steel plant. First, by deploying a monitoring camera, a switch, a video recorder and a server, the image acquisition, transmission and storage of the steel/iron ladle hoisting process in the workshop are realized; then the acquired images are marked and stored. The yolov3 target detection neural network is used for training, and the ear/hook detection model and the single-digit detection model are established; finally, the monitoring camera images are collected according to a certain period, and the following operations are performed for each image: first use the ear/hook detection model. The detection model detects whether the steel/iron ladle is dropped; if a drop is detected, the single-digit detection model is called to detect the numbers and their coordinates in the image, and calculates the number of numbers, the size of X between the numbers, and the confidence degree. package number. The invention can eliminate the interference of bag-dropping behavior and numbers in other ranges, reduce the recognition area, and reduce the recognition time; and through the deep learning neural network, it can well adapt to the complex environment of the steel workshop and extract deeper image features. |
| priorityDate | 2022-06-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
| Predicate | Subject |
|---|---|
| isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID23925 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419491185 |
Total number of triples: 25.