Segmentation and Recognition Using Structure from Motion Point Clouds

By Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur, Roberto Cipolla. 2008

1,111 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering

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

In Environmental Engineering

Citations in the corpus

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation (2016, methodology): “We used the split and image 2http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/ resolution from [1], which consists of 367 frames for training, 101 frames for validation and 233 frames for test.”
ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes (2021, background): “Detection and Segmentation Datasets Many datasets for image segmentation have been proposed with the goal of densely recognizing general objects and “stuff” in image scenes like street view [7, 17, 61], natural scenes [9, 20, 35, 44,65], and indoor spaces [13,19,53].”
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (2015, methodology): “, Random Forest [26], [27] or Boosting [28], [29] to predict the class probabilities of the center pixel.”
Spatio-temporal video autoencoder with differentiable memory (2015, methodology): “We trained our architecture on Camvid dataset Brostow et al. (2008), which consists of road scene RGB videos, with about 10k training frames in total, among which 468 are labelled, and about 7k testing frames, among which 233 are labelled.”
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation (2018, methodology): “Then we report our final results on Cityscapes [9], CamVid [2] and COCO-Stuff [3] benchmarks compared with other algorithms.”
Ieee Transactions on Pattern Analysis and Machine Intelligence Segmentation of Moving Objects by Long Term Video Analysis (2014, neutral): “Ommer et al. [48] couple motion segmentation with a recognition task, in [70] tracking and detection is combined with geometric information for 3D scene modeling, [14] focus on road scene understanding, and [62] reconstruct 3D point clouds for semantic segmentation and object recognition.”
FasterSeg: Searching for Faster Real-time Semantic Segmentation (2019, background): “After that, we report our ﬁnal accuracy and latency on Cityscapes, CamVid (Brostow et al., 2008), and BDD (Yu et al., 2018b).”
TRADI: Tracking deep neural network weight distributions (2019, methodology): “In the second experiment, we train a Enet DNN [43] for semantic segmentation on CamVid dataset [7].”
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments (2018, methodology): “The datasets proposed for semantic segmentation that focus on autonomous navigation are Cityscapes [5], KITTI [15], Camvid [2, 1], Leuven [12] and the Daimler Dataset [21].”
Geo-semantic segmentation (2015, methodology): “In particular, semantic segmentation of images taken from urban areas has been studied in the past few years [10, 14, 2, 4].”
CAP: Context-Aware Pruning for Semantic Segmentation (2021, methodology): “We empirically evaluate the performance of our method on various networks and two benchmarks (i.e., CamVid [3] and Cityscapes [7]).”
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans (2020, background): “early work [7, 14] focused on offline processing, recent years have seen a surge of interest towards real-time metric-”
Knowledge Distillation for Semantic Segmentation Using Channel and Spatial Correlations and Adaptive Cross Entropy (2020, methodology): “We also experimented on the Camvid dataset to demonstrate the effectiveness of our distillation method.”
Structured class-labels in random forests for semantic image labelling (2011, methodology): “We list the scores of our experiments according to the same evaluation criteria as used in [27, 9, 14] and additionally include the more strict average intersection vs.”