Pedestrian detection combining RGB and dense LIDAR data

By Cristiano Premebida, João Carreira, Jorge P. Batista, Urbano Jose C. Nunes. 2014

201 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering, 3D Vision & Pose

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

In 3D Vision & Pose

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.”
Voting for Voting in Online Point Cloud Object Detection (2015, background): “As examples serve [14, 15] who in addition also take into account appearance information from a regular camera image.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “This is known as the aperture problem and can only be solved by introducing an additional constraint which is Figure 23: The Yosemite sequence generated by Quam (1984) and the corresponding ground truth flow created by Heeger (1988).”
Object Classification Using CNN-Based Fusion of Vision and LIDAR in Autonomous Vehicle Environment (2018, methodology): “This system can also be applied in outdoor scenarios and long sensing range compared with structured light systems such as Microsoft Kinect [25], [28].”
3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection (2016, unknown): “08 Fusion-DPM [57] - 59.”
Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, background): “In [137], instead of using sparse laser points directly, the author reconstructed the dense depth map from the point cloud by upsampling the points.”
Multiview random forest of local experts combining RGB and LIDAR data for pedestrian detection (2015, methodology): “At learning time, each tree learns one of the characteristic configurations of local patches, thus accommodating for different flexible articulations occurring in the training set.”
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].”
3D Object Proposals for Accurate Object Class Detection (2015, unknown): “08 - - Fusion-DPM [41] - - - 59.”
Ten Years of Pedestrian Detection, What Have We Learned? (2014, methodology): “They consider stereo images [45], optical ﬂow (using previous frames, e.g. MultiFtr+Motion [22] and ACF+SDt [42]), tracking [46], or data from other sensors (such as lidar [47] or radar).”
Pedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison (2016, background): “Another recent trend has been to complement those appearance-based features, computed from single frames, with additional motion and depth features such as in [21–25].”
DepthCN: Vehicle detection using 3D-LIDAR and ConvNet (2017, methodology): “In this regard, examples of non-deep learning object detection approaches are presented in [3], [10]– [13].”
Filtered channel features for pedestrian detection (2015, methodology): “Note that our results also improve over methods using LIDAR + Image, such as Fusion-DPM [30] ( 46 .”
Multimodal End-to-End Autonomous Driving (2019, unknown): “[109] obtain it from LiDAR point clouds.”
LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks (2018, methodology): “For this reason, it is common practice [14], [25], [26] to upsample the LIDAR images before processing them with machine learning algorithms.”
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.”
Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review (2020, background): “This dense depth-image is up-sampled using sparse depth-images (from point cloud) and images [108].”