Amplifying the Anterior-Posterior Difference via Data Enhancement -- A More Robust Deep Monocular Orientation Estimation Solution

• URL: http://arxiv.org/abs/2012.11431v1
• Date: Mon, 21 Dec 2020 15:36:13 GMT
• Title: Amplifying the Anterior-Posterior Difference via Data Enhancement -- A More Robust Deep Monocular Orientation Estimation Solution
• Authors: Chenchen Zhao and Hao Li
• Abstract summary: Existing deep-learning based monocular orientation estimation algorithms face the problem of confusion between the anterior and posterior parts of the objects. We propose a pretraining method which focuses on predicting the left/right semicircle in which the orientation of the object is located. Experiment results show that the proposed semicircle prediction enhances the accuracy of orientation estimation, and mitigates the problem stated above.
• Score: 7.540176446791261
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing deep-learning based monocular orientation estimation algorithms faces the problem of confusion between the anterior and posterior parts of the objects, caused by the feature similarity of such parts in typical objects in traffic scenes such as cars and pedestrians. While difficult to solve, the problem may lead to serious orientation estimation errors, and pose threats to the upcoming decision making process of the ego vehicle, since the predicted tracks of objects may have directions opposite to ground truths. In this paper, we mitigate this problem by proposing a pretraining method. The method focuses on predicting the left/right semicircle in which the orientation of the object is located. The trained semicircle prediction model is then integrated into the orientation angle estimation model which predicts a value in range $[0, \pi]$. Experiment results show that the proposed semicircle prediction enhances the accuracy of orientation estimation, and mitigates the problem stated above. With the proposed method, a backbone achieves similar state-of-the-art orientation estimation performance to existing approaches with well-designed network structures.

Related papers

• Orient Anything [4.342241136871849]
  We introduce a two-stage orientation pipeline that achieves state of the art performance on up-axis estimation. Unlike previous work, we train and evaluate our method on all of Shapenet rather than a subset of classes.
  arXiv  Detail & Related papers  (2024-10-02T23:46:45Z)
• Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive? [93.10694819127608]
  We propose a unified evaluation pipeline for forecasting methods with real-world perception inputs. Our in-depth study uncovers a substantial performance gap when transitioning from curated to perception-based data.
  arXiv  Detail & Related papers  (2023-06-15T17:03:14Z)
• Deep Projective Rotation Estimation through Relative Supervision [31.05330535795121]
  Deep learning has offered a way to develop image-based orientation estimators. These estimators often require training on a large labeled dataset. We propose a new algorithm for selfsupervised orientation estimation.
  arXiv  Detail & Related papers  (2022-11-21T04:58:07Z)
• RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation [103.74918834553247]
  Category-level object pose estimation aims to predict the 6D pose as well as the 3D metric size of arbitrary objects from a known set of categories. Recent methods harness shape prior adaptation to map the observed point cloud into the canonical space and apply Umeyama algorithm to recover the pose and size. We propose a novel geometry-guided Residual Object Bounding Box Projection network RBP-Pose that jointly predicts object pose and residual vectors.
  arXiv  Detail & Related papers  (2022-07-30T14:45:20Z)
• ConvPoseCNN2: Prediction and Refinement of Dense 6D Object Poses [23.348510362258402]
  We propose a fully-convolutional extension of the PoseCNN method, which densely predicts object translations and orientations. This has several advantages such as improving the spatial resolution of the orientation predictions. We demonstrate that our method achieves the same accuracy as PoseCNN on the challenging YCB-Video dataset.
  arXiv  Detail & Related papers  (2022-05-23T08:32:09Z)
• Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encoding [121.66374635092097]
  Trajectories obtained from object detection and tracking are inevitably noisy. We propose a trajectory predictor directly based on detection results without relying on explicitly formed trajectories.
  arXiv  Detail & Related papers  (2022-02-03T09:09:56Z)
• Learning Output Embeddings in Structured Prediction [73.99064151691597]
  A powerful and flexible approach to structured prediction consists in embedding the structured objects to be predicted into a feature space of possibly infinite dimension. A prediction in the original space is computed by solving a pre-image problem. In this work, we propose to jointly learn a finite approximation of the output embedding and the regression function into the new feature space.
  arXiv  Detail & Related papers  (2020-07-29T09:32:53Z)
• Pillar-based Object Detection for Autonomous Driving [33.021347169775474]
  We present a simple and flexible object detection framework optimized for autonomous driving. Building on the observation that point clouds in this application are extremely sparse, we propose a practical pillar-based approach to fix the issue caused by anchors. Our algorithm incorporates a cylindrical projection into multi-view feature learning, predicts bounding box parameters per pillar rather than per point or per anchor, and includes an aligned pillar-to-point projection module to improve the final prediction.
  arXiv  Detail & Related papers  (2020-07-20T17:59:28Z)
• Uncertainty quantification in imaging and automatic horizon tracking: a Bayesian deep-prior based approach [0.5156484100374059]
  Uncertainty quantification (UQ) deals with a probabilistic description of the solution nonuniqueness and data noise sensitivity. In this paper, we focus on how UQ trickles down to horizon tracking for the determination of stratigraphic models.
  arXiv  Detail & Related papers  (2020-04-01T04:26:33Z)
• Robust 6D Object Pose Estimation by Learning RGB-D Features [59.580366107770764]
  We propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-02-29T06:24:55Z)
• Composing Normalizing Flows for Inverse Problems [89.06155049265641]
  We propose a framework for approximate inference that estimates the target conditional as a composition of two flow models. Our method is evaluated on a variety of inverse problems and is shown to produce high-quality samples with uncertainty.
  arXiv  Detail & Related papers  (2020-02-26T19:01:11Z)

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.