Multiview random forest of local experts combining RGB and LIDAR data for pedestrian detection

By Alejandro González, Gabriel Villalonga, Jiaolong Xu, David Vázquez, Jaume Amores, Antonio M. López. 2015

86 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

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 Multimodal Learning

Citations in the corpus

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (2017, methodology): “Several methods project point clouds into a perspective view and apply image-based feature extraction techniques [30, 15, 22].”
Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks (2016, methodology): “Despite only using point cloud data, Vote3Deep still performs better than these ([20], [21]) in the majority of test cases and only slightly worse in the remaining ones at a considerably faster detection speed.”
Orientation-boosted Voxel Nets for 3D Object Recognition (2016, background): “ry to detect objects directly in the 2D space of the image. Wang & Posner [36] were among the ﬁrst ones to utilize point clouds to obtain object proposals. In another line of work Gonzalez et al. [11] and Chen et al. [5] mix both 2D and 3D data for detection. Many authors, including Li et al. [2”
MVX-Net: Multimodal VoxelNet for 3D Object Detection (2019, background): “Due to the high computational and memory cost, several approaches based on BEV representation were developed ([27], [14], [42]).”
3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection (2016, unknown): “92 MV-RGBD-RFz [55] 76.”
STD: Sparse-to-Dense 3D Object Detector for Point Cloud (2019, background): “Most existing work transforms sparse point clouds to compact representation by projecting them to images [4, 14, 9, 25, 7] or subdividing them into equally distributed voxels [23, 32, 37, 35].”
Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions (2018, methodology): “There are various examples in the literature for either fusing the sensor data at the beginning (Early Fusion) [6], [7], [14], or at the end of the fusion process (Late Fusion) [2], [12] so that it is difficult to decide, which sensor fusion approach is suited, especially since the object detectors ”
Scale-Aware Fast R-CNN for Pedestrian Detection (2015, methodology): “Hand-crafted Model: The models based on hand-crafted features have been widely used for object detection [2], [5], [8]–[10], [13], [18], [19], [30], [39], [51], [54], [61], [62].”
Pedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison (2016, methodology): “We thus propose to use an approach similar to [25]: for each candidate window, we extract HOG and LBP features over each modality and then combine them into a single feature vector to feed the classifier.”
3DSSD: Point-Based 3D Single Stage Object Detector (2020, methodology): “Several existing methods convert point clouds from sparse formation to compact representations by projecting them to images [4, 11, 8, 18, 5], or subdividing them to equally distributed voxels [16, 26, 33, 29, 28, 12].”
3D Object Proposals for Accurate Object Class Detection (2015, unknown): “38 MV-RGBD-RF [45] - - - 70.”
LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving (2019, methodology): “In addition to using LiDAR data, several previous works use images [5, 15, 22, 17, 26, 21, 9] or high definition maps [27] to improve detections.”
IPOD: Intensive Point-based Object Detector for Point Cloud (2018, unknown): “To deploy CNNs, most existing methods convert 3D point clouds to images by projection [4, 19, 15, 28, 10] or voxelize cloud with a ﬁxed grid [26, 32, 35].”