Deep Person Detection in 2D Range Data
Explore this paper's citation graph
Summary
The deep learning based wheelchair and walker detector DROW is shown to be generalization to people, including small modifications that significantly boost DROW's performance, and the DROW dataset is extended with person annotations, making this the largest dataset of person annotations in 2D range data.
- Type
- preprint
- Published
- 2018-04-06
- Cited by
- 18
- References
- 33
- Access
- Open access
- OpenAlex
- https://openalex.org/W2796372625
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:4719179
Keywords
Computer science, Artificial intelligence, Wheelchair, Robot, Crowds
References
- Person tracking and following with 2D laser scanners
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Playing Atari with Deep Reinforcement Learning
- People detection and distinction of their walking aids in 2D laser range data based on generic distance-invariant features
- Dropout: a simple way to prevent neural networks from overfitting
- Going deeper with convolutions
- Human detection using multimodal and multidimensional features
- Using Boosted Features for the Detection of People in 2D Range Data
- Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures
- Automatic Differentiation: Techniques and Applications
- Are we ready for autonomous driving? The KITTI vision benchmark suite
- Place-dependent people tracking
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition
- DROW: Real-Time Deep Learning-Based Wheelchair Detection in 2-D Range Data
- End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks
- The STRANDS Project: Long-Term Autonomy in Everyday Environments
- Convolutional Two-Stream Network Fusion for Video Action Recognition
- On multi-modal people tracking from mobile platforms in very crowded and dynamic environments
- Aggregated Residual Transformations for Deep Neural Networks
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Cited by
- Human Detection in Crowded Situations by Combining Stereo Depth and Deeply-Learned Models
- DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data
- Pseudo-Image and Sparse Points: Vehicle Detection With 2D LiDAR Revisited by Deep Learning-Based Methods
- Laser-Based People Detection and Obstacle Avoidance for a Hospital Transport Robot
- Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera
- Deep Leg Tracking by Detection and Gait Analysis in 2D Range Data for Intelligent Robotic Assistants
- From Perception to Navigation in Environments with Persons: An Indoor Evaluation of the State of the Art
- MARF: Multiscale Adaptive-Switch Random Forest for Leg Detection With 2-D Laser Scanners
- 2D vs. 3D LiDAR-based Person Detection on Mobile Robots
- The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
- Autonomous Navigation in Dynamic Human Environments with an Embedded 2D LiDAR-based Person Tracker
- Embedded 2D LiDAR-Based Person Tracking for Safe Navigation in Assistive Autonomous Robots
- FROG: a new people detection dataset for knee-high 2D range finders
- Social robot navigation: a review and benchmarking of learning-based methods
- Real-Time 2D LiDAR Object Detection Using Three-Frame RGB Scan Encoding
- Domain and Modality Gaps for LiDAR-based Person Detection on Mobile Robots
- Vision-Based Person-Following Algorithm for Assistive Elderly-Care Quadruped Robots
- LiDAR Point Cloud Feature Learning with One-Class SVM for Efficient Human Recognition in Indoor Environment
Related papers
- Mask R-CNN
- The WILDTRACK Multi-Camera Person Dataset
- Improving the reliability of 3D people tracking system by means of deep-learning
- Adapted deep feature fusion for person re-identification in aerial images
- A Classification-Lock Tracking Strategy Allowing a Person-Following Robot to Operate in a Complicated Indoor Environment
- CamLoc: Pedestrian Location Estimation through Body Pose Estimation on Smart Cameras
- MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?