A Multi-Stage Approach for Fast Person Re-identification
One of the goals of person re-identification systems is to support video-surveillance operators and forensic investigators to find an individual of interest in videos taken by a network of non-overlapping cameras. This is attained by sorting images of pre
- PDF / 553,679 Bytes
- 11 Pages / 439.37 x 666.142 pts Page_size
- 64 Downloads / 166 Views
Abstract. One of the goals of person re-identification systems is to support video-surveillance operators and forensic investigators to find an individual of interest in videos taken by a network of non-overlapping cameras. This is attained by sorting images of previously observed individuals for decreasing values of their similarity with the query individual. Several appearance-based descriptors have been proposed so far, together with ad hoc similarity measures, mostly aimed at improving ranking quality. We address instead the issue of the processing time required to compute the similarity values, and propose a multi-stage ranking approach to attain a trade-off with ranking quality, for any given descriptor. We give a preliminary evaluation of our approach on the benchmark VIPeR data set, using different state-of-the-art descriptors.
1
Introduction
Person re-identification is a computer vision task consisting in recognizing an individual who had previously been observed over a network of video surveillance cameras with non-overlapping fields of view [1]. One of its applications is to support surveillance operators and forensic investigators in retrieving videos where an individual of interest appears, using an image of that individual as a query (probe). To this aim, the video frames or tracks of all the individuals recorded by the camera network (template gallery) are sorted by decreasing similarity to the probe, allowing the operator to find the occurrences (if any) of the individual of interest, ideally, in the top positions. This task is challenging in typically unconstrained surveillance settings, due to low image resolution, unconstrained pose, illumination changes, and occlusions, which do not allow to exploit strong biometrics like face. Clothing appearance is therefore one of the most widely used cues, although cues like gait and anthropometric measures have also been investigated. Most of the existing person re-identification techniques are based on a specific descriptor of clothing appearance (typically including color and texture), and a specific similarity measure between a pair of descriptors which can be either manually defined or learnt from data [1,3,4,6,12]. Their focus is to improve recognition accuracy, i.e., ranking quality. c Springer International Publishing AG 2016 A. Robles-Kelly et al. (Eds.): S+SSPR 2016, LNCS 10029, pp. 63–73, 2016. DOI: 10.1007/978-3-319-49055-7 6
64
B. Lavi et al.
In this work we address the complementary issue of the processing time required to compute the similarity measure (matching score). Many of the similarity measures defined so far are indeed rather complex, and require a relatively high processing time (e.g., [3,16]). Moreover, in real-world application scenarios the template gallery can be very large, and even when a single matching score is fast to compute (e.g., the Euclidean distance between fixed-length feature vectors [12]), computing it for all templates is time-consuming. This issue has been addressed so far only by a few works [2,9,15]. Inspired by the mu
Data Loading...
