LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection

• URL: http://arxiv.org/abs/2206.07705v2
• Date: Fri, 3 May 2024 19:00:47 GMT
• Title: LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection
• Authors: Wei-Chih Hung, Vincent Casser, Henrik Kretzschmar, Jyh-Jing Hwang, Dragomir Anguelov,
• Abstract summary: 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.
• Score: 26.278496981844317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The 3D Average Precision (3D AP) relies on the intersection over union between predictions and ground truth objects. However, camera-only detectors have limited depth accuracy, which may cause otherwise reasonable predictions that suffer from such longitudinal localization errors to be treated as false positives. We therefore 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 of the prediction boxes up to a given tolerance. To evaluate the proposed metrics, we also construct a new test set for the Waymo Open Dataset, tailored to camera-only 3D detection methods. Surprisingly, we find that state-of-the-art camera-based detectors can outperform popular LiDAR-based detectors with our new metrics past at 10% depth error tolerance, suggesting that existing camera-based detectors already have the potential to surpass LiDAR-based detectors in downstream applications. We believe the proposed metrics and the new benchmark dataset will facilitate advances in the field of camera-only 3D detection by providing more informative signals that can better indicate the system-level performance.

Related papers

• Sparse Points to Dense Clouds: Enhancing 3D Detection with Limited LiDAR Data [68.18735997052265]
  We propose a balanced approach that combines the advantages of monocular and point cloud-based 3D detection. Our method requires only a small number of 3D points, that can be obtained from a low-cost, low-resolution sensor. The accuracy of 3D detection improves by 20% compared to the state-of-the-art monocular detection methods.
  arXiv  Detail & Related papers  (2024-04-10T03:54:53Z)
• Improving LiDAR 3D Object Detection via Range-based Point Cloud Density Optimization [13.727464375608765]
  Existing 3D object detectors tend to perform well on the point cloud regions closer to the LiDAR sensor as opposed to on regions that are farther away. We observe that there is a learning bias in detection models towards the dense objects near the sensor and show that the detection performance can be improved by simply manipulating the input point cloud density at different distance ranges.
  arXiv  Detail & Related papers  (2023-06-09T04:11:43Z)
• Collaboration Helps Camera Overtake LiDAR in 3D Detection [49.58433319402405]
  Camera-only 3D detection provides a simple solution for localizing objects in 3D space compared to LiDAR-based detection systems. Our proposed collaborative camera-only 3D detection (CoCa3D) enables agents to share complementary information with each other through communication. Results show that CoCa3D improves previous SOTA performances by 44.21% on DAIR-V2X, 30.60% on OPV2V+, 12.59% on CoPerception-UAVs+ for AP@70.
  arXiv  Detail & Related papers  (2023-03-23T03:50:41Z)
• Is Pseudo-Lidar needed for Monocular 3D Object detection? [32.772699246216774]
  We propose an end-to-end, single stage, monocular 3D object detector, DD3D, that can benefit from depth pre-training like pseudo-lidar methods, but without their limitations. Our architecture is designed for effective information transfer between depth estimation and 3D detection, allowing us to scale with the amount of unlabeled pre-training data.
  arXiv  Detail & Related papers  (2021-08-13T22:22:51Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)
• Delving into Localization Errors for Monocular 3D Object Detection [85.77319416168362]
  Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving. In this work, we quantify the impact introduced by each sub-task and find the localization error' is the vital factor in restricting monocular 3D detection.
  arXiv  Detail & Related papers  (2021-03-30T10:38:01Z)
• Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues [28.806932489163888]
  We propose a novel 3D object detection modality that exploits temporal illumination cues from a low-cost monocular gated imager. We assess the proposed method on a novel 3D detection dataset that includes gated imagery captured in over 10,000 km of driving data.
  arXiv  Detail & Related papers  (2021-02-06T16:06:51Z)
• 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)
• Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
  Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space. We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step. This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
  arXiv  Detail & Related papers  (2020-08-31T17:10:48Z)

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.