Vehicle Re-Identification by Deep Hidden Multi-View Inference

Abstract

Vehicle re-identification (re-ID) is an area that has received far less attention in the computer vision community than the prevalent person re-ID. Possible reasons for this slow progress are the lack of appropriate research data and the special 3D structure of a vehicle. Previous works have generally focused on some specific views (e.g., front); but, these methods are less effective in realistic scenarios, where vehicles usually appear in arbitrary views to cameras. In this paper, we focus on the uncertainty of vehicle viewpoint in re-ID, proposing two end-to-end deep architectures: the Spatially Concatenated ConvNet and convolutional neural network (CNN)-LSTM bi-directional loop. Our models exploit the great advantages of the CNN and long short-term memory (LSTM) to learn transformations across different viewpoints of vehicles. Thus, a multi-view vehicle representation containing all viewpoints' information can be inferred from the only one input view, and then used for learning to measure distance. To verify our models, we also introduce a Toy Car RE-ID data set with images from multiple viewpoints of 200 vehicles. We evaluate our proposed methods on the Toy Car RE-ID data set and the public Multi-View Car, VehicleID, and VeRi data sets. Experimental results illustrate that our models achieve consistent improvements over the state-of-the-art vehicle re-ID approaches.

Vehicle Re-Identification Using Quadruple Directional Deep Learning Features

“…Although the rank-5 identification rate of the proposed QD-DLF method is a bit lower than that of PROVID [1], the proposed QD-DLF method achieves much higher MAP and rank-1 identification rate, and thus is still superior to PROVID [1]. Secondly, compared with those single modal deep learning based vehicle re-identification methods (i.e., NuFACT [1], DenseNet121 [25], SCCN-Ft+CLBL-8-Ft [12], ABLN-Ft-16 [11], FACT [2], GoogLeNet [26] and VGG-CNN-M-1024 [3]), the proposed QD-DLF methods shows a larger accuracy improvement. Specifically, the best single modal deep learning based vehicle re-identification method, i.e., NuFACT [1], only obtains a 48.47% MAP, a 76.76% rank-1 identification rate and a 91.42% rank-5 identification rate, which are much lower than those of the proposed QD-DLF method.…”

“…Moreover, it can be seen that SCCN-Ft+CLBL-8-Ft [12] and ABLN-Ft-16 [11] do not obviously show the superiority on the VeRi database, although they specially consider the viewpoint variation. This is because each vehicle in the VeRi database is not densely captured by different camera viewpoints, which does not fully meet the requirement of the training data for CCN-Ft+CLBL-8-Ft [12] and ABLN-Ft-16 [11], limiting the performance improvement.…”

A survey of advances in vision-based vehicle re-identification

“…The method works well for the pair of images that are spatially and temporally close to each other. Zhou et al (2018) addressed multi-view V-reID problem by generating multi-view features for each query image which can be considered as a descriptive representation containing all information from the multiple views. The method extracts features from one image that belong to one view.…”

“…9, different vehicles, from VeRi-776 dataset, in terms of color, type, model, and different viewpoints are shown. Zhou et al (2018) collected Toy Car ReID dataset. This is the first synthetic vehicle dataset collected in an indoor environment using multiple cameras.…”

“…The 8 handcrafted feature based methods are: the 3d and color information (3DCI)Woesler (2003), the edge-map distances (EMD)Shan et al (2005), the 3d and piecewise model (3DPM)Guo et al (2008), the 3d pose and illumination model (3DPIM)Hou et al (2009), the attribute based model (ABM)Feris et al (2012), the multi-pose model (MPM)Zheng et al (2015), the bounding box model (BBM)Zapletal and (2016), and the license number plate (LNP)Watchar and (2017). The 12 deep feature methods are: the progressive vehicle re-identification (PROVID)Liu et al (2016c), the deep relative distance learning (DRDL)Liu et al (2016a), the deep color and texture (DCT)Liu et al (2016b), the orientation invariant model (OIM)Wang et al (2017), the visual spatio-temporal model (VSTM)Shen et al (2017), the cross-level vehicle recognition (CLVR)Kanacı et al (2017), the triplet-wise training (TWT)Zhang et al (2017), the feature fusing model (FFM)Tang et al (2017), the deep joint discriminative learning (DJDL)Li et al (2017b), the Null space based Fusion of Color and Attribute feature (NuFACT)Liu et al (2018), the multi-view feature (MVF)Zhou et al (2018), and the group sensitive triplet embedding (GSTE)Bai et al (2018).…”