Computer vision

46 metoder i denne familie.

Udvalgte

BaggrundssubtraktionBackground subtraction is a video processing technique that separates moving foreground objects from a static or slowly changing background by comparing each frame to a learned or BlobdetektionBlob detection is a technique for identifying regions of interest (blobs)—connected, homogeneous areas that differ from their surroundings—at multiple scales. Introduced by Lindebe Canny kantdetektionThe Canny edge detector, introduced by John Canny in 1986, is a multi-stage algorithm for identifying edges in digital images where significant intensity changes occur. Canny's met CNN-billedklassifikationCNN image classification uses deep convolutional architectures such as ResNet (He et al., 2016), VGG and EfficientNet (Tan & Le, 2019) to sort images into categories. Stacked convo KonturanalyseContour analysis is the process of detecting and analyzing the boundaries of objects in images by identifying connected edges and extracting shape information. The Suzuki-Abe algor DETR (Detection Transformer)DETR (Detection Transformer) is an end-to-end framework for object detection introduced by Carion et al. in 2020 that reformulates detection as a direct set prediction problem usin

Reading path

This topic's most-referenced foundational methods, in the order they were developed — a place to start if you're new here.

Morfologiske billedoperationer1982by Jean Serra
Konturanalyse1985by Satoshi Suzuki and Keiichi Abe
Harris hjørnedetektion1988by Chris Harris and Mike Stephens
Blobdetektion1998by Tony Lindeberg
Overførselslæring med billedklassifikation2010–2012by Pan, S. J. & Yang, Q. (transfer learning framework); Krizhevsky, Sutskever & Hinton (deep CNN backbone)
Billedklassifikation2012 (deep CNN era); conceptual roots 1989 (LeCun)by Krizhevsky, A.; Sutskever, I.; Hinton, G. E.
Objektdetektion2014–2016by Girshick, R. et al. (R-CNN); Redmon, J. et al. (YOLO)
Semantisk segmentering2015by Long, J., Shelhamer, E., & Darrell, T.

all methods on this shelf ↓

Alle metoder 46

Baggrundssubtraktion Blobdetektion Canny kantdetektion CNN-billedklassifikation Konturanalyse DETR (Detection Transformer)Domæne-adaptiv billedklassifikation Forklarlig Billedklassifikation Forklarlig objektdetektering Forklarlig Semantisk Segmentering Few-Shot Objektdetektering Finjusteret billedklassifikation Fintunet Semantisk Segmentering Fully Convolutional Network (FCN)Harris hjørnedetektion Histogramudligning Hough-transformationen Billedklassifikation Morfologiske billedoperationer Lucas-Kanade optisk flow Mask R-CNN: Instanssegmentering med pixel-niveau masker Tosproget Billedklassifikation Flersproget semantisk segmentering Multimodal billedklassifikation Multimodal Objektdetektion Multimodal Semantisk Segmentering Objektdetektion ORB Feature Descriptor Pixelbaseret billedklassifikation Scale-Space Teori Selv-overvåget billedklassifikation Selv-superviseret objektgenkendelse Selv-overvåget semantisk segmentering Semantisk segmentering Semi-overvåget billedklassifikation Semi-overvåget objektdetektering Semi-overvåget semantisk segmentering SIFT Feature Detection Stereo-matchning Overførselslæring med billedklassifikation Transfer Learning med Objektdetektering Watershed Segmentering Svag superviseret billedklassifikation Svag superviseret objektdetektering Svagt superviseret semantisk segmentering YOLO (You Only Look Once)