Homography Guided Temporal Fusion for Road Line and Marking Segmentation

• URL: http://arxiv.org/abs/2404.07626v1
• Date: Thu, 11 Apr 2024 10:26:40 GMT
• Title: Homography Guided Temporal Fusion for Road Line and Marking Segmentation
• Authors: Shan Wang, Chuong Nguyen, Jiawei Liu, Kaihao Zhang, Wenhan Luo, Yanhao Zhang, Sundaram Muthu, Fahira Afzal Maken, Hongdong Li,
• Abstract summary: Road lines and markings are frequently occluded in the presence of moving vehicles, shadow, and glare. We propose a Homography Guided Fusion (HomoFusion) module to exploit temporally-adjacent video frames for complementary cues. We show that exploiting available camera intrinsic data and ground plane assumption for cross-frame correspondence can lead to a light-weight network with significantly improved performances in speed and accuracy.
• Score: 73.47092021519245
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reliable segmentation of road lines and markings is critical to autonomous driving. Our work is motivated by the observations that road lines and markings are (1) frequently occluded in the presence of moving vehicles, shadow, and glare and (2) highly structured with low intra-class shape variance and overall high appearance consistency. To solve these issues, we propose a Homography Guided Fusion (HomoFusion) module to exploit temporally-adjacent video frames for complementary cues facilitating the correct classification of the partially occluded road lines or markings. To reduce computational complexity, a novel surface normal estimator is proposed to establish spatial correspondences between the sampled frames, allowing the HomoFusion module to perform a pixel-to-pixel attention mechanism in updating the representation of the occluded road lines or markings. Experiments on ApolloScape, a large-scale lane mark segmentation dataset, and ApolloScape Night with artificial simulated night-time road conditions, demonstrate that our method outperforms other existing SOTA lane mark segmentation models with less than 9\% of their parameters and computational complexity. We show that exploiting available camera intrinsic data and ground plane assumption for cross-frame correspondence can lead to a light-weight network with significantly improved performances in speed and accuracy. We also prove the versatility of our HomoFusion approach by applying it to the problem of water puddle segmentation and achieving SOTA performance.

Related papers

• Leveraging Road Area Semantic Segmentation with Auxiliary Steering Task [0.0]
  We propose a CNN-based method that can leverage the steering wheel angle information to improve the road area semantic segmentation. We demonstrate the effectiveness of the proposed approach on two challenging data sets for autonomous driving.
  arXiv  Detail & Related papers  (2022-12-19T13:25:09Z)
• Monocular BEV Perception of Road Scenes via Front-to-Top View Projection [57.19891435386843]
  We present a novel framework that reconstructs a local map formed by road layout and vehicle occupancy in the bird's-eye view. Our model runs at 25 FPS on a single GPU, which is efficient and applicable for real-time panorama HD map reconstruction.
  arXiv  Detail & Related papers  (2022-11-15T13:52:41Z)
• Correlating sparse sensing for large-scale traffic speed estimation: A Laplacian-enhanced low-rank tensor kriging approach [76.45949280328838]
  We propose a Laplacian enhanced low-rank tensor (LETC) framework featuring both lowrankness and multi-temporal correlations for large-scale traffic speed kriging. We then design an efficient solution algorithm via several effective numeric techniques to scale up the proposed model to network-wide kriging.
  arXiv  Detail & Related papers  (2022-10-21T07:25:57Z)
• Extrinsic Camera Calibration with Semantic Segmentation [60.330549990863624]
  We present an extrinsic camera calibration approach that automatizes the parameter estimation by utilizing semantic segmentation information. Our approach relies on a coarse initial measurement of the camera pose and builds on lidar sensors mounted on a vehicle. We evaluate our method on simulated and real-world data to demonstrate low error measurements in the calibration results.
  arXiv  Detail & Related papers  (2022-08-08T07:25:03Z)
• Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion [51.11295961195151]
  We exploit the characteristics of the foggy image sequence of driving scenes to densify the confident pseudo labels. Based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion scheme. Our scheme helps the adaptive model achieve 51.92% and 53.84% mean intersection-over-union (mIoU) on two publicly available natural foggy datasets.
  arXiv  Detail & Related papers  (2022-06-10T05:16:50Z)
• Cross-Camera Trajectories Help Person Retrieval in a Camera Network [124.65912458467643]
  Existing methods often rely on purely visual matching or consider temporal constraints but ignore the spatial information of the camera network. We propose a pedestrian retrieval framework based on cross-camera generation, which integrates both temporal and spatial information. To verify the effectiveness of our method, we construct the first cross-camera pedestrian trajectory dataset.
  arXiv  Detail & Related papers  (2022-04-27T13:10:48Z)
• A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection [1.653688760901944]
  This study proposes a novel hybrid spatial-temporal sequence-to-one deep learning architecture. The proposed model can effectively handle challenging driving scenes and outperforms available state-of-the-art methods with a large margin.
  arXiv  Detail & Related papers  (2021-10-05T15:47:45Z)
• Multi-Model Learning for Real-Time Automotive Semantic Foggy Scene Understanding via Domain Adaptation [17.530091734327296]
  We propose an efficient end-to-end automotive semantic scene understanding approach that is robust to foggy weather conditions. Our approach incorporates RGB colour, depth and luminance images via distinct encoders with dense connectivity. Our model achieves comparable performance to contemporary approaches at a fraction of the overall model complexity.
  arXiv  Detail & Related papers  (2020-12-09T21:04:05Z)

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.