Corpus ID: 235899144

Diff-Net: Image Feature Difference based High-Definition Map Change Detection

@article{He2021DiffNetIF,
  title={Diff-Net: Image Feature Difference based High-Definition Map Change Detection},
  author={Lei He and Shengjie Jiang and Xiaoqing Liang and Ning Wang and Shiyu Song},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.07030}
}
  • Lei He, Shengjie Jiang, +2 authors Shiyu Song
  • Published 2021
  • Computer Science
  • ArXiv
Up-to-date High-Definition (HD) maps are essential for self-driving cars. To achieve constantly updated HD maps, we present a deep neural network (DNN), Diff-Net, to detect changes in them. Compared to traditional methods based on object detectors, the essential design in our work is a parallel feature difference calculation structure that infers map changes by comparing features extracted from the camera and rasterized images. To generate these rasterized images, we project map elements onto… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 43 REFERENCES
HD Map Change Detection with Cross-Domain Deep Metric Learning
TLDR
A novel framework for HD map change detection that can be used to maintain an up-to-date HD map and can robustly detect changes against noises due to dynamic objects and error in vehicle poses is proposed. Expand
Street-view change detection with deconvolutional networks
TLDR
This work proposes a system for performing structural change detection in street-view videos captured by a vehicle-mounted monocular camera over time, and introduces a new urban change detection dataset which is an order of magnitude larger than existing datasets and contains challenging changes due to seasonal and lighting variations. Expand
Weakly Supervised Silhouette-based Semantic Scene Change Detection
TLDR
This paper presents a novel semantic scene change detection scheme with only weak supervision that proposes a new siamese network structure with the introduction of correlation layer and creates a publicly available dataset for semantic change detection. Expand
SSD: Single Shot MultiBox Detector
TLDR
The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component. Expand
Change Detection Based on Deep Siamese Convolutional Network for Optical Aerial Images
TLDR
A novel supervised change detection method based on a deep siamese convolutional network for optical aerial images that is comparable, even better, with the two state-of-the-art methods in terms of F-measure. Expand
Learning to Measure Change: Fully Convolutional Siamese Metric Networks for Scene Change Detection
TLDR
Thresholded Contrastive Loss (TCL) is proposed with a more tolerant strategy to punish noisy changes to address the issue of large viewpoint differences and a novel fully Convolutional siamese metric Network (CosimNet) to measure changes by customizing implicit metrics. Expand
Image-Based 4-d Reconstruction Using 3-d Change Detection
TLDR
The proposed framework employs an initial 3-d model which is continuously updated with changes in the environment to form a full 4-d representation which is enabled by a novel algorithm that infers3-d changes with respect to the model at one time step from images taken at a subsequent time step. Expand
Detecting Changes in 3D Structure of a Scene from Multi-view Images Captured by a Vehicle-Mounted Camera
TLDR
The proposed method is compared with the methods that use multi-view stereo to reconstruct the scene structures of the two time points and then differentiate them to detect changes, and the experimental results show that the proposed method outperforms such MVS-based methods. Expand
Geometric Change Detection in Urban Environments Using Images
TLDR
The proposed method can be used to significantly optimize the process of updating the 3D model of an urban environment that is changing overtime, by restricting this process to only those areas where changes are detected. Expand
Fast Image-Based Geometric Change Detection Given a 3D Model
TLDR
A focus of the approach is that it can be executed fast enough to allow the operation on a mobile system and it finds inconsistencies between pairs of images by re-projecting an image onto another one by passing through the given 3D model. Expand
...
1
2
3
4
5
...