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

Abstract

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-identification task. Existing vehicle re-identification methods ignored or used oversimplified models for the spatio-temporal relations between vehicle images. In this paper, we propose a two-stage framework that incorporates complex spatio-temporal information for effectively regularizing the re-identification results. Given a pair of vehicle images with their spatiotemporal information, a candidate visual-spatio-temporal path is first generated by a chain MRF model with a deeply learned potential function, where each visual-spatiotemporal state corresponds to an actual vehicle image with its spatio-temporal information. A Siamese-CNN+Path-LSTM model takes the candidate path as well as the pairwise queries to generate their similarity score. Extensive experiments and analysis show the effectiveness of our proposed method and individual components.

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

“…The method avoids expensive and time consuming crosscamera identity pairwise labeling and relies on cheaper vehicle model. Shen et al (2017) proposed a two stage framework that takes into account the complex spatio-temporal information. The method takes a pair of vehicle images with their spatio-temporal information.…”

Background Segmentation for Vehicle Re-identification

“…Although BIR only uses visual information, our final approach also has a 17% and 12% increase in terms of mAP, as compared with Siamese-CNN+path-LSTM [20] and AFL+CNN [23], which also use spatio-temporal information. It proves that making full use of image information can improve accuracy.…”

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

“…Due to the wide application in urban surveillance and intelligent transportation, vehicle re-ID gains rapidly increasing attention in the past two years. To enhance re-ID capacity, some approaches utilize extra attribute information e.g., model/type, color to guide visionbased representation learning [5,15,17,31,26,38,40,39,18]. For instance, Liu et al [13] introduce a two-branch retrieval pipeline to extract both model and instance differences.…”

“…Yan et al [32] explore multi-grain relationships of vehicles with multi-level attributes. Other works investigate spatial-temporal association, which gains extra benefit from the topology information of cameras [31,26,16]. In comparison with the above-mentioned works, our method only relies on ID supervision and auxiliary viewpoint information, which is relatively resource-efficient, and yet achieves competitive re-ID accuracy.…”

“…Performance on Veri-776. The compared state-of-the-art methods on Veri-776 include FACT+STR [16], XVGAN [38], OIFE+ST [31], S+LSTM [26], RAM [18], ABLN [39], VAMI+STR [40], and GSTE [1], where the names with "+ST" and "+STR" mean that the corresponding methods involve the spatio-temporal information. The results shown in Tab.…”