Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-Temporal Path Proposals

@article{Shen2017LearningDN,
  title={Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-Temporal Path Proposals},
  author={Yantao Shen and Tong Xiao and Hongsheng Li and Shuai Yi and Xiaogang Wang},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1918-1927}
}
Vehicle re-identification is an important problem and has many applications in video surveillance and intelligent transportation. It gains increasing attention because of the recent advances of person re-identification techniques. However, unlike person re-identification, the visual differences between pairs of vehicle images are usually subtle and even challenging for humans to distinguish. Incorporating additional spatio-temporal information is vital for solving the challenging re… 

Figures and Tables from this paper

Discriminative Feature Representation with Spatio-temporal Cues for Vehicle Re-identification
TLDR
Experimental results on two public datasets demonstrate DFR-ST outperforms the state-of-the-art methods, which validate the effectiveness of the proposed method.
Large Scale Vehicle Re-Identification by Knowledge Transfer from Simulated Data and Temporal Attention
TLDR
This work addresses the re-id task by relying on well-proven design choices from the closely related person re-identification literature, and explicitly address viewpoint and occlusions variation.
Multi-View Spatial Attention Embedding for Vehicle Re-Identification
TLDR
A multi-view branch network where each branch learns a viewpoint-specific feature without parameter sharing performs substantially better than the general feature learned by an uniform network to alleviate negative effects of viewpoint variance.
Background Segmentation for Vehicle Re-Identification
TLDR
This paper constructs a vehicle segmentation dataset and develops a vehicle Re-ID framework with a background interference removal (BIR) mechanism to improve the vehicle re-identification performance as well as robustness against complex background in large-scale spatio-temporal scenes.
Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification
TLDR
This work proposes an end-to-end RNN-based Hierarchical Attention (RNN-HA) classification model for vehicle re-identification and demonstrates that the proposed model achieves superior performance over state-of-the-art methods.
Multi-Task Mutual Learning for Vehicle Re-Identification
TLDR
A novel Multi-Task Mutual Learning (MTML) deep model to learn discriminative features simultaneously from multiple branches by fusing features from the final convolutional feature maps from all branches is proposed.
Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network
TLDR
This work proposes a dedicated Semantics-guided Part Attention Network (SPAN) to robustly predict part attention masks for different views of vehicles given only image-level semantic labels during training and introduces Co-occurrence Part-attentive Distance Metric (CPDM) which places greater emphasis on co-occurring vehicle parts when evaluating the feature distance of two images.
Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification
TLDR
A novel deep neural network called a multi-attention-based soft partition (MUSP) network to solve vehicle re-identification, which does not use metadata and only uses multiple soft attentions to identify a specific vehicle area.
HSS-GCN: A Hierarchical Spatial Structural Graph Convolutional Network for Vehicle Re-identification
TLDR
A hierarchical spatial structural graph convolutional network (HSS-GCN) for vehicle Re-ID is proposed, in which a hierarchical spatial structure graph is constructed with the global region and local regions as nodes and a two-hierarchy relationship as edges.
Urban Area Vehicle Re-Identification With Self-Attention Stair Feature Fusion and Temporal Bayesian Re-Ranking
TLDR
An Self-Attention Stair Feature Fusion model to learn the discriminative features for vehicle Re-ID and a Temporal Bayesian Re-Ranking method to exploit the spatial-temporal information in the vehicles’ travel patterns are proposed.
...
...

References

SHOWING 1-10 OF 48 REFERENCES
A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance
TLDR
This paper proposes a novel deep learning-based approach to PROgressive Vehicle re-ID, called “PROVID”, which treats vehicle Re-Id as two specific progressive search processes: coarse-to-fine search in the feature space, and near- to-distantsearch in the real world surveillance environment.
Deep Relative Distance Learning: Tell the Difference between Similar Vehicles
TLDR
A Deep Relative Distance Learning (DRDL) method is proposed which exploits a two-branch deep convolutional network to project raw vehicle images into an Euclidean space where distance can be directly used to measure the similarity of arbitrary two vehicles.
Large-scale vehicle re-identification in urban surveillance videos
TLDR
A large-scale benchmark dataset for vehicle Re-Id in the real-world urban surveillance scenario, named “VeRi”, which contains over 40,000 bounding boxes of 619 vehicles captured by 20 cameras in unconstrained traffic scene and proposes a baseline which combines the color, texture, and highlevel semantic information extracted by deep neural network.
Joint Detection and Identification Feature Learning for Person Search
TLDR
A new deep learning framework for person search that jointly handles pedestrian detection and person re-identification in a single convolutional neural network and converges much faster and better than the conventional Softmax loss.
Vehicle Re-identification for Automatic Video Traffic Surveillance
  • Dominik Zapletal, A. Herout
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2016
TLDR
The proposed method works with a high accuracy and in 85 milliseconds of the CPU (Core i7) computation time per one vehicle re-identification assuming the fullHD resolution video input.
An improved deep learning architecture for person re-identification
TLDR
This work presents a deep convolutional architecture with layers specially designed to address the problem of re-identification, and significantly outperforms the state of the art on both a large data set and a medium-sized data set, and is resistant to over-fitting.
Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function
TLDR
A novel multi-channel parts-based convolutional neural network model under the triplet framework for person re-identification that significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based ones, on the challenging i-LIDS, VIPeR, PRID2011 and CUHK01 datasets.
Object Detection in Videos with Tubelet Proposal Networks
TLDR
A framework for object detection in videos is proposed, which consists of a novel tubelet proposal network to efficiently generate spatiotemporal proposals, and a Long Short-term Memory network that incorporates temporal information from tubelet proposals for achieving high object detection accuracy in videos.
Vehicle tracking across nonoverlapping cameras using joint kinematic and appearance features
TLDR
A vehicle tracking algorithm using input from a network of nonoverlapping cameras based on a novel statistical formulation that uses joint kinematic and image appearance information to link local tracks of the same vehicles into global tracks with longer persistence is described.
...
...