Detecting Road Obstacles by Erasing Them

• URL: http://arxiv.org/abs/2012.13633v3
• Date: Sun, 8 Oct 2023 22:30:49 GMT
• Title: Detecting Road Obstacles by Erasing Them
• Authors: Krzysztof Lis, Sina Honari, Pascal Fua, Mathieu Salzmann
• Abstract summary: We select image patches and inpaint them with the surrounding road texture, which tends to remove obstacles from those patches. We then use a network trained to recognize discrepancies between the original patch and the inpainted one, which signals an erased obstacle.
• Score: 101.45116269051692
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector. Instead, we select image patches and inpaint them with the surrounding road texture, which tends to remove obstacles from those patches. We then use a network trained to recognize discrepancies between the original patch and the inpainted one, which signals an erased obstacle.

Related papers

• 3D StreetUnveiler with Semantic-Aware 2DGS [66.90611944550392]
  StreetUnveiler learns a 3D representation of an empty street from crowded observations. We divide the empty street scene into observed, partial-observed, and unobserved regions. Experiments conducted on the street scene dataset successfully reconstructed a 3D representation of the empty street.
  arXiv  Detail & Related papers  (2024-05-28T17:57:12Z)
• FlowMap: Path Generation for Automated Vehicles in Open Space Using Traffic Flow [32.8563901381583]
  FlowMap is a path generation framework for automated vehicles based on traffic flows. A path generation algorithm on traffic flow fields (TFFs) is proposed to generate human-like paths.
  arXiv  Detail & Related papers  (2023-05-02T17:27:37Z)
• Perspective Aware Road Obstacle Detection [104.57322421897769]
  We show that road obstacle detection techniques ignore the fact that, in practice, the apparent size of the obstacles decreases as their distance to the vehicle increases. We leverage this by computing a scale map encoding the apparent size of a hypothetical object at every image location. We then leverage this perspective map to generate training data by injecting onto the road synthetic objects whose size corresponds to the perspective foreshortening.
  arXiv  Detail & Related papers  (2022-10-04T17:48:42Z)
• You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors [12.946967210071032]
  Adversarial patches can fool facial recognition systems, surveillance systems and self-driving cars. Most existing adversarial patches can be outwitted, disabled and rejected by an adversarial patch detector. We present a novel approach, a Low-Detectable Adversarial Patch, which attacks an object detector with texture-consistent adversarial patches.
  arXiv  Detail & Related papers  (2021-09-30T14:47:29Z)
• CP-loss: Connectivity-preserving Loss for Road Curb Detection in Autonomous Driving with Aerial Images [10.300623192980753]
  Road curb detection is important for autonomous driving. Most of the current methods detect road curbs online using vehicle-mounted sensors, such as cameras or 3-D Lidars. In this paper, we detect road curbs offline using high-resolution aerial images.
  arXiv  Detail & Related papers  (2021-07-26T01:36:58Z)
• iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving [11.576868193291997]
  Road curbs are an essential capability for autonomous driving. Usually, road curbs are detected on-line using vehicle-mounted sensors, such as video cameras and 3-D Lidars. We propose a novel solution to detect road curbs off-line using aerial images.
  arXiv  Detail & Related papers  (2021-03-31T14:40:31Z)
• Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection [55.12894776039135]
  State-of-the-art 3D object detectors, based on deep learning, have shown promising accuracy but are prone to over-fit to domain idiosyncrasies. We propose a novel learning approach that drastically reduces this gap by fine-tuning the detector on pseudo-labels in the target domain. We show, on five autonomous driving datasets, that fine-tuning the detector on these pseudo-labels substantially reduces the domain gap to new driving environments.
  arXiv  Detail & Related papers  (2021-03-26T01:18:11Z)
• End-to-End Deep Structured Models for Drawing Crosswalks [98.9901717499058]
  We project both inputs onto the ground surface to produce a top down view of the scene. We then leverage convolutional neural networks to extract semantic cues about the location of the crosswalks. Experiments over crosswalks in a large city area show that 96.6% automation can be achieved.
  arXiv  Detail & Related papers  (2020-12-21T18:59:08Z)
• Promoting Connectivity of Network-Like Structures by Enforcing Region Separation [101.10228007363673]
  We propose a connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures. The main idea behind our loss is to express the connectivity of roads, or canals, in terms of disconnections that they create between background regions of the image. We show, in experiments on two standard road benchmarks and a new data set of irrigation canals, that convnets trained with our loss function recover road connectivity so well.
  arXiv  Detail & Related papers  (2020-09-15T12:21:35Z)
• Detecting Lane and Road Markings at A Distance with Perspective Transformer Layers [5.033948921121557]
  In existing approaches, the detection accuracy often degrades with the increasing distance. This is due to the fact that distant lane and road markings occupy a small number of pixels in the image. Inverse Perspective Mapping can be used to eliminate the perspective distortion, but the inherent can lead to artifacts.
  arXiv  Detail & Related papers  (2020-03-19T03:22:52Z)

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.