| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_72b1a0580183c94d612c0df2ff5b8aa8
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_1bc3713da8210a8fce35069339dbb191
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_48fdbfb2ad0183c6f64c65f0b3c9885b |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y02A10-40 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-10 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-28
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-26
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-48
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-30
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
| filingDate |
2021-11-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1e3aacc059a97f1b9a2f59a7dbbe0469
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9fcca3823128d8042c6d58ae8341450c
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c1a80156682e31b63b33f1c7ad9822cd
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b2a4a7df40060874d688b619cddc63b3
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9ad5d8e79f85e57b130f56cfeb7cb751
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b276f46c07c1f7dfaa55d9e43a0816b1
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_bcf13ba53db9e47d2ddc0b6c180c5f2b
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_556675a4ad29360c5cceb6624c70e49f
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_bebd465856769d9932f30e6655281a4d |
| publicationDate |
2022-06-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-114581658-A |
| titleOfInvention |
A computer vision-based target detection method and device |
| abstract |
The invention discloses a target detection method and device based on computer vision in a complex environment. The method includes: collecting an RGB image of a foreground area, preprocessing the RGB image of the foreground area, and obtaining a segmentation binary value of the foreground target area Analyze the segmentation binary image of the foreground target area to extract various morphological features of the target area; analyze the various morphological features of the target area, divide the target area into occluded isolated target areas and overlapping the target area; performing contour segmentation on the occluded isolated target area and the overlapping target area to extract an effective contour segment; using a circle fitting method to perform circle fitting on the target shape in the effective contour segment, The combined circle performs comprehensive analysis to locate the potential target area; eliminates interference, identifies and obtains the specific target of the potential target area; the embodiment of the present invention can improve the detection accuracy of target instances in the natural complex environment. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115648224-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115690430-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115690430-A |
| priorityDate |
2021-11-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |