http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114445371-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_8d4803b67140ec2a993d39f7bc919b6e |
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10032 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0002 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate | 2022-01-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_404ad2dd50356a7575304dce29bb03fa http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_59d892c9be42ee0610927ac4d4bb7c45 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8d598453ba6551c690b2d66b5670b6f4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8ac75bbc1b1019bd6ad82cbab561d63b http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b35953324fb12f4fae032b5aa6402c61 |
publicationDate | 2022-05-06-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114445371-A |
titleOfInvention | Remote sensing image target detection method and device based on ellipse intersection ratio |
abstract | The invention discloses a remote sensing image target detection method and device based on ellipse intersection and ratio, and belongs to the technical field of computer vision. The method includes: acquiring an original image, converting the labeling information of the target in the original image into ellipse labeling, and then inputting it to target detection. The target detector includes a backbone network, an RRPN network and a RoIHead network that are connected in sequence, and the regression loss functions of the RRPN network and the RoIHead network both use an ellipse intersection loss function; the backbone network is used to extract the multi-scale feature map of the input image; Taking the multi-scale feature map as the input of the RRPN network, the rotation candidate frame of the target is obtained; using the multi-scale feature map and the rotation candidate frame as the input of the RoIHead network, the detection result of the original image is obtained. The invention converts the labeling information of the target in the original image into ellipse labeling, and proposes a calculation method of ellipse intersection ratio to calculate the coincidence degree between the prediction frame and the target frame, thereby improving the effect of remote sensing image target detection. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115019181-A |
priorityDate | 2022-01-27-04:00^^<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/CID121841 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419513513 |
Total number of triples: 25.