Object Disparity

• URL: http://arxiv.org/abs/2108.07939v1
• Date: Wed, 18 Aug 2021 02:11:28 GMT
• Title: Object Disparity
• Authors: Ynjiun Paul Wang
• Abstract summary: This paper proposes a different approach for solving a 3D object distance detection by detecting object disparity directly without going through a dense pixel disparity. An example squeezenet Object Disparity-SSD was constructed to demonstrate an efficient object disparity detection with comparable accuracy compared with Kitti dataset pixel disparity ground truth.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most of stereo vision works are focusing on computing the dense pixel disparity of a given pair of left and right images. A camera pair usually required lens undistortion and stereo calibration to provide an undistorted epipolar line calibrated image pair for accurate dense pixel disparity computation. Due to noise, object occlusion, repetitive or lack of texture and limitation of matching algorithms, the pixel disparity accuracy usually suffers the most at those object boundary areas. Although statistically the total number of pixel disparity errors might be low (under 2% according to the Kitti Vision Benchmark of current top ranking algorithms), the percentage of these disparity errors at object boundaries are very high. This renders the subsequence 3D object distance detection with much lower accuracy than desired. This paper proposed a different approach for solving a 3D object distance detection by detecting object disparity directly without going through a dense pixel disparity computation. An example squeezenet Object Disparity-SSD (OD-SSD) was constructed to demonstrate an efficient object disparity detection with comparable accuracy compared with Kitti dataset pixel disparity ground truth. Further training and testing results with mixed image dataset captured by several different stereo systems may suggest that an OD-SSD might be agnostic to stereo system parameters such as a baseline, FOV, lens distortion, even left/right camera epipolar line misalignment.

Related papers

• Multi-View Keypoints for Reliable 6D Object Pose Estimation [12.436320203635143]
  We propose a novel multi-view approach to combine heatmap and keypoint estimates into a probability density map over 3D space. We demonstrate an average pose estimation error of approximately 0.5mm and 2 degrees across a variety of difficult low-feature and reflective objects.
  arXiv  Detail & Related papers  (2023-03-29T16:28:11Z)
• Monocular 3D Object Detection with Depth from Motion [74.29588921594853]
  We take advantage of camera ego-motion for accurate object depth estimation and detection. Our framework, named Depth from Motion (DfM), then uses the established geometry to lift 2D image features to the 3D space and detects 3D objects thereon. Our framework outperforms state-of-the-art methods by a large margin on the KITTI benchmark.
  arXiv  Detail & Related papers  (2022-07-26T15:48:46Z)
• Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data [80.14669385741202]
  We propose a self-supervised pre-training method for 3D perception models tailored to autonomous driving data. We leverage the availability of synchronized and calibrated image and Lidar sensors in autonomous driving setups. Our method does not require any point cloud nor image annotations.
  arXiv  Detail & Related papers  (2022-03-30T12:40:30Z)
• High-Resolution Depth Maps Based on TOF-Stereo Fusion [27.10059147107254]
  We propose a novel TOF-stereo fusion method based on an efficient seed-growing algorithm. We show that the proposed algorithm outperforms 2D image-based stereo algorithms. The algorithm potentially exhibits real-time performance on a single CPU.
  arXiv  Detail & Related papers  (2021-07-30T15:11:42Z)
• 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)
• Self-supervised spectral matching network for hyperspectral target detection [8.831857715361624]
  Given a few target samples, it aims to identify the specific target pixels such as airplane, vehicle, ship, from the entire hyperspectral image. In general, the background pixels take the majority of the image and complexly distributed. A spectral mixing based self-supervised paradigm is designed for hyperspectral data to obtain an effective feature representation.
  arXiv  Detail & Related papers  (2021-05-10T02:32:58Z)
• SMD-Nets: Stereo Mixture Density Networks [68.56947049719936]
  We propose Stereo Mixture Density Networks (SMD-Nets), a simple yet effective learning framework compatible with a wide class of 2D and 3D architectures. Specifically, we exploit bimodal mixture densities as output representation and show that this allows for sharp and precise disparity estimates near discontinuities. We carry out comprehensive experiments on a new high-resolution and highly realistic synthetic stereo dataset, consisting of stereo pairs at 8Mpx resolution, as well as on real-world stereo datasets.
  arXiv  Detail & Related papers  (2021-04-08T16:15:46Z)
• 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)
• Adjusting Bias in Long Range Stereo Matching: A semantics guided approach [14.306250516592305]
  We propose a pair of novel depth-based loss functions for foreground and background, separately. These loss functions are tunable and can balance the inherent bias of the stereo learning algorithms. Our solution yields substantial improvements in disparity and depth estimation, particularly for objects located at distances beyond 50 meters.
  arXiv  Detail & Related papers  (2020-09-10T01:47:53Z)
• Wasserstein Distances for Stereo Disparity Estimation [62.09272563885437]
  Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values.
  arXiv  Detail & Related papers  (2020-07-06T21:37:50Z)

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.