http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114565847-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_9083f8824b83211e2a0503686f35ca06 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2431 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V40-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-26 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V20-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-75 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V20-10 |
filingDate | 2022-02-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_00bceb4b7a74650f6fdfd730e5376bce http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3f49e3e2dcd22594c405faf37f87c3f4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0c6d1dfd80f5e44bc92d6d7c9e637248 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ac628291032fff05b4e147272f8e2866 |
publicationDate | 2022-05-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114565847-A |
titleOfInvention | A Visual SLAM Method in Dynamic Environment Based on Instance Segmentation |
abstract | The invention provides a visual SLAM method in a dynamic environment based on instance segmentation, and mainly solves the problem that the pose estimation accuracy of the visual SLAM method in a dynamic environment is seriously disturbed. The method introduces SOLOV2 instance segmentation module, which processes the input image as an independent module and outputs instance segmentation results. Based on the HTTP communication protocol, the data transmission method between the two is designed, so that the instance segmentation method is relatively simple to deploy. Instance segmentation results are stored in masked form and compressed in RLE format to save memory usage. Taking images, depth images, and instance segmentation results as input, we design a human-object connection detection method for identifying semi-static objects. Based on semantic prior information and semi-static target detection results, dynamic targets and static targets are separated. After removing the feature points obtained on dynamic objects, the accuracy of the estimated trajectory is significantly improved. |
priorityDate | 2022-02-25-04:00^^<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/CID21327 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419582264 |
Total number of triples: 23.