Towards a Better Match in Siamese Network Based Visual Object Tracker

Abstract

Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance. Despite the great success, this tracking framework still suffers from several limitations. First, it cannot properly handle large object rotation. Second, tracking gets easily distracted when the background contains salient objects. In this paper, we propose two simple yet effective mechanisms, namely angle estimation and spatial masking, to address these issues. The objective is to extract more representative features so that a better match can be obtained between the same object from different frames. The resulting tracker, named Siam-BM, not only significantly improves the tracking performance, but more importantly maintains the realtime capability. Evaluations on the VOT2017 dataset show that Siam-BM achieves an EAO of 0.335, which makes it the best-performing realtime tracker to date.

SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

“…Every patch of the same size as the target gets a similarity score, and the one with the highest score is identified as the new target location. There are also a great number of follow-up work [16,54,51], among which SA-Siam [18,17] and SiamRPN [27,60] are most related to ours.…”

“…However, it is difficult to attend to both requirements in a single network. SA-Siam [18] and Siam-BM [17] adopt a two-branch network to encode images into two embedding spaces, one for semantic similarity (more robust) and the other for appearance similarity (more discriminative). This typical parallel structure does not take advantage of the innate proposal capability of Figure 2.…”

“…SiamFC [2] 0.607 0.516 0.582 86 DSiamM [16] 0.656 --25 RASNet [51] 0.670 -0.642 83 SiamRPN [27] 0.658 0.592 0.637 200 SA-Siam [18] 0.677 0.610 0.657 50 StructSiam [59] 0.637 -0.621 45 MemTrack [54] 0.642 -0.626 50 DaSiamRPN [60] 0.656 0.602 0.658 160 Siam-BM [17] 0.684 0.617 0.662 48…”

Fast Online Object Tracking and Segmentation: A Unifying Approach

“…In particular, our threebranch variant significantly outperforms the very recent and top performing DaSiamRPN [63], achieving a EAO of 0.380 while running at 55 frames per second. Even without box regression branch, our simpler two-branch variant (SiamMask-2B) achieves a high EAO of 0.334, which is in par with SA Siam R [15] and superior to any other real-time method in the published literature. Finally, in SiamMask-Opt, the strategy proposed in [54] to find the optimal rotated rectangle from a binary mask brings the best overall performance (and a particularly high accuracy), but comes at a significant computational cost.…”

“…Our method is motivated by the success of fast tracking approaches based on fullyconvolutional Siamese networks [3] trained offline on millions of pairs of video frames (e.g. [28,63,15,60]) and by the very recent availability of YouTube-VOS [58], a large video dataset with pixel-wise annotations. We aim at retaining the offline trainability and online speed of these methods while at the same time significantly refining their representation of the target object, which is limited to a simple axis-aligned bounding box.…”