ScholarGate
Asistent
Machine learningDeep learning / NLP / CV

Multimodalna semantička segmentacija

Multimodalna semantička segmentacija dodeljuje semantičku klasnu oznaku svakom pikselu u sceni fuzijom informacija iz dva ili više senzorskih modaliteta — najčešće RGB slika uparenih sa mapama dubine (RGB-D), LiDAR oblacima tačaka, termalnim kamerama ili tekstualnim opisima. Duboke enkoder-dekoder mreže uče da poravnaju i fuzionišu komplementarne signale iz svakog modaliteta, proizvodeći gušću i precizniju segmentaciju od bilo kog pristupa sa jednim modalitetom.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Hazirbas, C., Ma, L., Domokos, C., & Cremers, D. (2016). FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture. In Proceedings of the Asian Conference on Computer Vision (ACCV). Springer. link
  2. Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., & Stiefelhagen, R. (2023). CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers. IEEE Transactions on Intelligent Transportation Systems, 24(12), 14801–14813. DOI: 10.1109/TITS.2023.3300537

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Multimodal Semantic Segmentation (Multi-Sensor Pixel-Level Scene Understanding). ScholarGate. https://scholargate.app/sr/deep-learning/multimodal-semantic-segmentation

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateMultimodal Semantic Segmentation (Multimodal Semantic Segmentation (Multi-Sensor Pixel-Level Scene Understanding)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/multimodal-semantic-segmentation · Skup podataka: https://doi.org/10.5281/zenodo.20539026