Monocular 3D Object Detection: An Extrinsic Parameter Free Approach

• URL: http://arxiv.org/abs/2106.15796v1
• Date: Wed, 30 Jun 2021 03:35:51 GMT
• Title: Monocular 3D Object Detection: An Extrinsic Parameter Free Approach
• Authors: Yunsong Zhou, Yuan He, Hongzi Zhu, Cheng Wang, Hongyang Li, Qinhong Jiang
• Abstract summary: We propose a novel method to capture camera pose to formulate the detector free from extrinsic perturbation. A converter is designed to rectify perturbative features in the latent space. Experiments demonstrate our method yields the best performance compared with the other state-of-the-arts.
• Score: 29.723079686571825
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monocular 3D object detection is an important task in autonomous driving. It can be easily intractable where there exists ego-car pose change w.r.t. ground plane. This is common due to the slight fluctuation of road smoothness and slope. Due to the lack of insight in industrial application, existing methods on open datasets neglect the camera pose information, which inevitably results in the detector being susceptible to camera extrinsic parameters. The perturbation of objects is very popular in most autonomous driving cases for industrial products. To this end, we propose a novel method to capture camera pose to formulate the detector free from extrinsic perturbation. Specifically, the proposed framework predicts camera extrinsic parameters by detecting vanishing point and horizon change. A converter is designed to rectify perturbative features in the latent space. By doing so, our 3D detector works independent of the extrinsic parameter variations and produces accurate results in realistic cases, e.g., potholed and uneven roads, where almost all existing monocular detectors fail to handle. Experiments demonstrate our method yields the best performance compared with the other state-of-the-arts by a large margin on both KITTI 3D and nuScenes datasets.

Related papers

• Rotation Matters: Generalized Monocular 3D Object Detection for Various Camera Systems [15.47493325786152]
  3D object detection performance is significantly reduced when applied to a camera system different from the system used to capture the training datasets. A 3D detector trained on datasets from a passenger car mostly fails to regress accurate 3D bounding boxes for a camera mounted on a bus. We propose a generalized 3D object detection method that can be universally applied to various camera systems.
  arXiv  Detail & Related papers  (2023-10-09T02:52:22Z)
• Tame a Wild Camera: In-the-Wild Monocular Camera Calibration [12.55056916519563]
  Previous methods for the monocular camera calibration rely on specific 3D objects or strong geometry prior. Our method is assumption-free and calibrates the complete $4$ Degree-of-Freedom (DoF) intrinsic parameters. We demonstrate downstream applications in image manipulation detection & restoration, uncalibrated two-view pose estimation, and 3D sensing.
  arXiv  Detail & Related papers  (2023-06-19T14:55:26Z)
• Multi-Modal 3D Object Detection by Box Matching [109.43430123791684]
  We propose a novel Fusion network by Box Matching (FBMNet) for multi-modal 3D detection. With the learned assignments between 3D and 2D object proposals, the fusion for detection can be effectively performed by combing their ROI features.
  arXiv  Detail & Related papers  (2023-05-12T18:08:51Z)
• Towards Model Generalization for Monocular 3D Object Detection [57.25828870799331]
  We present an effective unified camera-generalized paradigm (CGP) for Mono3D object detection. We also propose the 2D-3D geometry-consistent object scaling strategy (GCOS) to bridge the gap via an instance-level augment. Our method called DGMono3D achieves remarkable performance on all evaluated datasets and surpasses the SoTA unsupervised domain adaptation scheme.
  arXiv  Detail & Related papers  (2022-05-23T23:05:07Z)
• Homography Loss for Monocular 3D Object Detection [54.04870007473932]
  A differentiable loss function, termed as Homography Loss, is proposed to achieve the goal, which exploits both 2D and 3D information. Our method yields the best performance compared with the other state-of-the-arts by a large margin on KITTI 3D datasets.
  arXiv  Detail & Related papers  (2022-04-02T03:48:03Z)
• Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task [48.555440807415664]
  We present the first high-diversity challenging Roadside Perception 3D dataset- Rope3D from a novel view. The dataset consists of 50k images and over 1.5M 3D objects in various scenes. We propose to leverage the geometry constraint to solve the inherent ambiguities caused by various sensors, viewpoints.
  arXiv  Detail & Related papers  (2022-03-25T12:13:23Z)
• 3D-VField: Learning to Adversarially Deform Point Clouds for Robust 3D Object Detection [111.32054128362427]
  In safety-critical settings, robustness on out-of-distribution and long-tail samples is fundamental to circumvent dangerous issues. We substantially improve the generalization of 3D object detectors to out-of-domain data by taking into account deformed point clouds during training. We propose and share open source CrashD: a synthetic dataset of realistic damaged and rare cars.
  arXiv  Detail & Related papers  (2021-12-09T08:50:54Z)
• MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation [55.96577490779591]
  Methods need to have a degree of 'camera independence' in order to benefit from large and heterogeneous training data. We show that more data does not automatically guarantee a better performance, but rather, methods need to have a degree of 'camera independence' in order to benefit from large and heterogeneous training data.
  arXiv  Detail & Related papers  (2021-10-01T14:56:37Z)
• 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)

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.