VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregation

• URL: http://arxiv.org/abs/2411.13186v1
• Date: Wed, 20 Nov 2024 10:36:41 GMT
• Title: VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregation
• Authors: Chengjie Huang, Vahdat Abdelzad, Sean Sedwards, Krzysztof Czarnecki,
• Abstract summary: We propose an efficient adaptive method, which we call VADet, for variable aggregation. VADet performs aggregation per object, with the number of frames determined by an object's observed properties, such as speed and point density. To demonstrate its benefits, we apply VADet to three popular single-stage detectors and achieve state-of-the-art performance on a dataset.
• Score: 4.33608942673382
• License:
• Abstract: Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects responding differently to the number of aggregated frames. To address this limitation, we propose an efficient adaptive method, which we call Variable Aggregation Detection (VADet). Instead of aggregating the entire scene using a fixed number of frames, VADet performs aggregation per object, with the number of frames determined by an object's observed properties, such as speed and point density. VADet thus reduces the inherent trade-offs of fixed aggregation and is not architecture specific. To demonstrate its benefits, we apply VADet to three popular single-stage detectors and achieve state-of-the-art performance on the Waymo dataset.

Related papers

• Scale-Invariant Feature Disentanglement via Adversarial Learning for UAV-based Object Detection [18.11107031800982]
  We propose to improve single-stage inference accuracy through learning scale-invariant features. We apply our approach to three state-of-the-art lightweight detection frameworks on three benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-24T11:40:22Z)
• 3D Video Object Detection with Learnable Object-Centric Global Optimization [65.68977894460222]
  Correspondence-based optimization is the cornerstone for 3D scene reconstruction but is less studied in 3D video object detection. We propose BA-Det, an end-to-end optimizable object detector with object-centric temporal correspondence learning and featuremetric object bundle adjustment.
  arXiv  Detail & Related papers  (2023-03-27T17:39:39Z)
• 3DMODT: Attention-Guided Affinities for Joint Detection & Tracking in 3D Point Clouds [95.54285993019843]
  We propose a method for joint detection and tracking of multiple objects in 3D point clouds. Our model exploits temporal information employing multiple frames to detect objects and track them in a single network.
  arXiv  Detail & Related papers  (2022-11-01T20:59:38Z)
• DFA: Dynamic Feature Aggregation for Efficient Video Object Detection [15.897168900583774]
  We propose a vanilla dynamic aggregation module that adaptively selects the frames for feature enhancement. We extend the vanilla dynamic aggregation module to a more effective and reconfigurable deformable version. On the ImageNet VID benchmark, integrated with our proposed methods, FGFA and SELSA can improve the inference speed by 31% and 76% respectively.
  arXiv  Detail & Related papers  (2022-10-02T17:54:15Z)
• ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers [73.29057814695459]
  ComplETR is designed to explicitly complete missing annotations in partially annotated dense scene datasets. This reduces the need to annotate every object instance in the scene thereby reducing annotation cost. We show performance improvement for several popular detectors such as Faster R-CNN, Cascade R-CNN, CenterNet2, and Deformable DETR.
  arXiv  Detail & Related papers  (2022-09-13T00:11:16Z)
• CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion [34.42289908350286]
  3D Multi-object tracking (MOT) ensures consistency during continuous dynamic detection. It can be challenging to accurately track the irregular motion of objects for LiDAR-based methods. We propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT)
  arXiv  Detail & Related papers  (2022-09-06T14:41:38Z)
• Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes [82.4186966781934]
  We introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules. With negligible extra overhead, Ret3D achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-08-18T03:48:58Z)
• SALISA: Saliency-based Input Sampling for Efficient Video Object Detection [58.22508131162269]
  We propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection. We show that SALISA significantly improves the detection of small objects.
  arXiv  Detail & Related papers  (2022-04-05T17:59:51Z)
• Pattern-Aware Data Augmentation for LiDAR 3D Object Detection [7.394029879643516]
  We propose pattern-aware ground truth sampling, a data augmentation technique that downsamples an object's point cloud based on the LiDAR's characteristics. We improve the performance of PV-RCNN on the car class by more than 0.7 percent on the KITTI validation split at distances greater than 25 m.
  arXiv  Detail & Related papers  (2021-11-30T19:14:47Z)
• 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.