Geometric Context from Videos
By S. H. Raza, Matthias Grundmann, Irfan Essa. 2013
44 citations recorded by the source corpus.
We present a novel algorithm for estimating the broad 3D geometric structure of outdoor video scenes. Leveraging spatio-temporal video segmentation, we decompose a dynamic scene captured by a video into geometric classes, based on predictions made by region-classifiers that are trained on appearance and motion features. By examining the homogeneity of the prediction, we combine predictions across multiple segmentation hierarchy levels alleviating the need to determine the granularity a priori. We built a novel, extensive dataset on geometric context of video to evaluate our method, consisting of over 100 ground-truth annotated outdoor videos with over 20,000 frames. To further scale beyond this dataset, we propose a semi-supervised learning framework to expand the pool of labeled data with high confidence predictions obtained from unlabeled data. Our system produces an accurate prediction of geometric context of video achieving 96% accuracy across main geometric classes.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Hanqing Lu
- Dacheng Tao
- Adriana Romero
- Michal Drozdzal
- Xiaogang Wang
- Alan L. Yuille
- Jiashi Feng
Citations in the corpus
- The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation (2016, methodology): “We evaluate our model on two challenging benchmarks for urban scene understanding, Camvid [2] and Gatech [22], and confirm the potential of DenseNets for semantic segmentation by improving the state-of-the-art.”
- Stacked Deconvolutional Network for Semantic Segmentation (2017, methodology): “To show the effectiveness of our approach, we carry out comprehensive experiments on PASCAL VOC 2012 dataset [22], CamVid dataset [23] and GATECH dataset [24].”
- Deep End2End Voxel2Voxel Prediction (2015, unknown): “e will report results for both options in our experiments. 4. Application I: Video Semantic Segmentation Dataset. Our experiments for video semantic segmentation are carried out on the GATECH dataset [20], which comes with a public training/test split. The training set contains 63 videos while the t”
- Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey (2020, background): “.10% 31.84% GCN[91] 2017 PASCAL VOC 2012 Cityscapes [124] 82.2% 76.9% PSPNet [90] 2017 PASCAL VOC 2012 Cityscapes 85.4% 80.2% FC-DenseNet103 [115] 2017 CamVid road scene segmentation Gatech[125] 66.9% 79.4% Gated-SCNN [94] 2019 Cityscapes 82.8% for classication, detection and even for segmenta”