LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB

• URL: http://arxiv.org/abs/2006.09738v1
• Date: Wed, 17 Jun 2020 09:27:38 GMT
• Title: LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB
• Authors: Michael F\"urst and Oliver Wasenm\"uller and Didier Stricker
• Abstract summary: The current state-of-the-art on the KITTI benchmark performs suboptimal in detecting the position of pedestrians at long range. We propose an approach specifically targeting long range 3D pedestrian detection (LRPD), leveraging the density of RGB and the precision of LiDAR. This leads to a significant improvement in mAP on long range compared to the current state-of-the art.
• Score: 12.650574326251023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While short range 3D pedestrian detection is sufficient for emergency breaking, long range detections are required for smooth breaking and gaining trust in autonomous vehicles. The current state-of-the-art on the KITTI benchmark performs suboptimal in detecting the position of pedestrians at long range. Thus, we propose an approach specifically targeting long range 3D pedestrian detection (LRPD), leveraging the density of RGB and the precision of LiDAR. Therefore, for proposals, RGB instance segmentation and LiDAR point based proposal generation are combined, followed by a second stage using both sensor modalities symmetrically. This leads to a significant improvement in mAP on long range compared to the current state-of-the art. The evaluation of our LRPD approach was done on the pedestrians from the KITTI benchmark.

Related papers

• Better Monocular 3D Detectors with LiDAR from the Past [64.6759926054061]
  Camera-based 3D detectors often suffer inferior performance compared to LiDAR-based counterparts due to inherent depth ambiguities in images. In this work, we seek to improve monocular 3D detectors by leveraging unlabeled historical LiDAR data. We show consistent and significant performance gain across multiple state-of-the-art models and datasets with a negligible additional latency of 9.66 ms and a small storage cost.
  arXiv  Detail & Related papers  (2024-04-08T01:38:43Z)
• Towards Long-Range 3D Object Detection for Autonomous Vehicles [4.580520623362462]
  3D object detection at long range is crucial for ensuring the safety and efficiency of self driving vehicles. Most current state of the art LiDAR based methods are range limited due to sparsity at long range. We investigate two ways to improve long range performance of current LiDAR based 3D detectors.
  arXiv  Detail & Related papers  (2023-10-07T13:39:46Z)
• An Empirical Analysis of Range for 3D Object Detection [70.54345282696138]
  We present an empirical analysis of far-field 3D detection using the long-range detection dataset Argoverse 2.0. Near-field LiDAR measurements are dense and optimally encoded by small voxels, while far-field measurements are sparse and are better encoded with large voxels. We propose simple techniques to efficiently ensemble models for long-range detection that improve efficiency by 33% and boost accuracy by 3.2% CDS.
  arXiv  Detail & Related papers  (2023-08-08T05:29:26Z)
• Far3Det: Towards Far-Field 3D Detection [67.38417186733487]
  We focus on the task of far-field 3D detection (Far3Det) of objects beyond a certain distance from an observer. Far3Det is particularly important for autonomous vehicles (AVs) operating at highway speeds. We develop a method to find well-annotated scenes from the nuScenes dataset and derive a well-annotated far-field validation set. We propose a Far3Det evaluation protocol and explore various 3D detection methods for Far3Det.
  arXiv  Detail & Related papers  (2022-11-25T02:07:57Z)
• LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection [26.278496981844317]
  We propose variants of the 3D AP metric to be more permissive with respect to depth estimation errors. Specifically, our novel longitudinal error tolerant metrics, LET-3D-AP and LET-3D-APL, allow longitudinal localization errors up to a given tolerance. We find that state-of-the-art camera-based detectors can outperform popular LiDAR-based detectors with our new metrics past 10% depth error tolerance.
  arXiv  Detail & Related papers  (2022-06-15T17:57:41Z)
• RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection [44.024530632421836]
  Range Sparse Net (RSN) is a simple, efficient, and accurate 3D object detector. RSN predicts foreground points from range images and applies sparse convolutions on the selected foreground points to detect objects. RSN is ranked first in the leaderboard based on the APH/LEVEL 1 metrics for LiDAR-based pedestrian and vehicle detection.
  arXiv  Detail & Related papers  (2021-06-25T00:23:55Z)
• PLUME: Efficient 3D Object Detection from Stereo Images [95.31278688164646]
  Existing methods tackle the problem in two steps: first depth estimation is performed, a pseudo LiDAR point cloud representation is computed from the depth estimates, and then object detection is performed in 3D space. We propose a model that unifies these two tasks in the same metric space. Our approach achieves state-of-the-art performance on the challenging KITTI benchmark, with significantly reduced inference time compared with existing methods.
  arXiv  Detail & Related papers  (2021-01-17T05:11:38Z)
• Robust Long-Term Object Tracking via Improved Discriminative Model Prediction [77.72450371348016]
  We propose an improved discriminative model prediction method for robust long-term tracking based on a pre-trained short-term tracker. The proposed method achieves comparable performance to the state-of-the-art long-term trackers.
  arXiv  Detail & Related papers  (2020-08-11T14:31:11Z)
• Road Curb Detection and Localization with Monocular Forward-view Vehicle Camera [74.45649274085447]
  We propose a robust method for estimating road curb 3D parameters using a calibrated monocular camera equipped with a fisheye lens. Our approach is able to estimate the vehicle to curb distance in real time with mean accuracy of more than 90%.
  arXiv  Detail & Related papers  (2020-02-28T00:24:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.