Street-view change detection with deconvolutional networks

By Pablo Fernández Alcantarilla, Simon Stent, Germán Ros, Roberto Arroyo, Riccardo Gherardi. Autonomous Robots, 2016

371 citations recorded by the source corpus.

We propose a system for performing structural change detection in street-view videos captured by a vehicle-mounted monocular camera over time. Our approach is motivated by the need for more frequent and efficient updates in the large-scale maps used in autonomous vehicle navigation. Our method chains a multi-sensor fusion SLAM and fast dense 3D reconstruction pipeline, which provide coarsely registered image pairs to a deep Deconvolutional Network (DN) for pixel-wise change detection. We investigate two DN architectures for change detection, the first one is based on the idea of stacking contraction and expansion blocks while the second one is based on the idea of Fully Convolutional Networks. To train and evaluate our networks we introduce 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. Our method outperforms existing literature on this dataset, which we make available to the community, and an existing panoramic change detection dataset, demonstrating its wide applicability.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/b02aacf33655cb2d4d1d3a42500180c779d0a0c3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Artificial intelligence applications in the development of autonomous vehicles: a survey (2020, methodology): “[21] Image Y Y Y Y Human-driven test car Deep CNN”
SwinSUNet: Pure Transformer Network for Remote Sensing Image Change Detection (2022, methodology): “We compared SwinSUNet with several excellent methods, such as CDNet [48], FC-EF [20], FC-Siam-conc [20], FC-Siam-diff [20], DASNet [22] and STANet [21].”
End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++ (2019, methodology): “To verify the superiority and effectiveness of our proposed CD method, some SOTA IB-DLCD approaches are compared, which are described as follows: 1) Change detection network (CDNet) [56] was proposed for pixel-wise CD in street view scenes, which consists of contraction blocks and expansion blocks, ”
Mobile Edge Intelligence and Computing for the Internet of Vehicles (2019, background): “Furthermore, HD maps are dynamic and need to be updated with timely changes [62], for which we need to collect fresh HD data timely and detect changes from the fresh data [63].”
Fusion and binarization of CNN features for robust topological localization across seasons (2016, methodology): “In these cases, geometric change detection [34] could be applied to detect”
Optical Remote Sensing Image Change Detection Based on Attention Mechanism and Image Difference (2021, methodology): “CDNet [45] was designed for street view change detection.”
DASNet: Dual Attentive Fully Convolutional Siamese Networks for Change Detection in High-Resolution Satellite Images (2020, methodology): “CDNet [25] , FC-EF, FC-Siam-Conc, FC-Siam-Diff in”
3D Human Pose Estimation from a Single Image via Distance Matrix Regression (2016, methodology): “Following previous works [4, 24], we explored an architecture with a contractive and an expansive part.”
Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring (2019, methodology): “CNNs have also been used to identify changes in urban scenes [146].”
Transformers in Remote Sensing: A Survey (2022, neutral): “Figure 8: Results of different CD methods visualized, such as FC-EF [62], FC-Siam-Conc [62], FC-Siam-Diff [62], CDNet [63], DASNet [64], STANet [61], and SwinSUNet [56] compared to (a)–(d) sample imagery sets the WHU-CD [60] test set.”