후회하지말고 최선을 다해서

Dataset 교통 표지판(Traffic Sign)을 예측하기 위해서는 해당 데이터셋이 필요하다. 다행히 독일 신경정보학 연구원들은 43개의 교통 표지판과 관련된 모두 다른 4만여 개의 이미지를 포함한 데이터셋을 만들었다. 이는 2011년에 만들어진 GTSRB(German Traffic Sign Recognition Benchmark)라고 불리는 데이터셋이다. https://sid.erda.dk/public/archives/daaeac0d7ce1152aea9b61d9f1e19370/published-archive.html Public Archive: daaeac0d7ce1152aea9b61d9f1e19370 Support ERDA User Guide Questions about ERDA? Please c..

Mask RCNN gitbub: https://github.com/jeonds1127/Mask_RCNN > Instance Segmentation Classification: There is a balloon in this image. Semantic Segmentation: These are all the balloon pixels. Object Detection: There are 7 balloons in this image at these locations. We’re starting to account for objects that overlap. Instance Segmentation: There are 7 balloons at these locations, and these are the pi..

Darknet link : https://github.com/AlexeyAB/darknet

1. Mesh-Flow-Video-Stabilization https://github.com/sudheerachary/Mesh-Flow-Video-Stabilization http://www.liushuaicheng.org/eccv2016/meshflow.pdf The MeshFlow is a spatial smooth sparse motion field with motion vectors only at the mesh vertexes. The MeshFlow is produced by assigning each vertex an unique motion vector via two median filters. The path smoothing is conducted on the vertex profile..