Tracking Persons-of-Interest via Adaptive Discriminative Features
Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically different in multiple shots due to significant variations in scale, pose, expression, illumination, and make-up. Low-level features used i
- PDF / 7,039,685 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 78 Downloads / 175 Views
2
Xi’an Jiaotong University, Xi’an, China University of Illinois, Urbana-Champaign, Champaign, USA [email protected] 3 Hanyang University, Seoul, South Korea 4 University of California, Merced, USA http://shunzhang.me.pn/papers/eccv2016/
Abstract. Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically different in multiple shots due to significant variations in scale, pose, expression, illumination, and make-up. Low-level features used in existing multitarget tracking methods are not effective for identifying faces with such large appearance variations. In this paper, we tackle this problem by learning discriminative, video-specific face features using convolutional neural networks (CNNs). Unlike existing CNN-based approaches that are only trained on large-scale face image datasets offline, we further adapt the pre-trained face CNN to specific videos using automatically discovered training samples from tracklets. Our network directly optimizes the embedding space so that the Euclidean distances correspond to a measure of semantic face similarity. This is technically realized by minimizing an improved triplet loss function. With the learned discriminative features, we apply the Hungarian algorithm to link tracklets within each shot and the hierarchical clustering algorithm to link tracklets across multiple shots to form final trajectories. We extensively evaluate the proposed algorithm on a set of TV sitcoms and music videos and demonstrate significant performance improvement over existing techniques.
1
Introduction
Multi-target tracking (MTT) aims at locating all targets of interest (e.g., faces, players, and cars), and inferring their trajectories in a video sequence over time while maintaining their identities. Multi-face tracking is one important domain of MTT that applies to numerous high-level video understanding tasks such as face recognition, content-based retrieval, surveillance, and group interaction analysis. The goal of multi-face tracking in unconstrained scenarios is to track faces in videos that are generated from multiple moving cameras with different views or scenes as shown in Fig. 1. Examples include automatic character tracking in c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part V, LNCS 9909, pp. 415–433, 2016. DOI: 10.1007/978-3-319-46454-1 26
416
S. Zhang et al.
Fig. 1. We focus on tracking multiple faces according to their unknown identities in unconstrained videos, which consist of many shots from different cameras. The main challenge is to address large face appearance variations from different shots due to changes in pose, view angle, scale, makeup, illumination, camera motion and heavy occlusions.
movies, TV sitcoms, or music videos. It has attracted increased attention in recent years due to the fast growing popularity of such videos on the Internet. Unlike tracking in the constrained counterparts (e.g., a video from a single camera that is either fixed or moved slowly) where the main chal
Data Loading...
